./data/seginw/Airplane-Parts is data path ! /scratch/work/mingqiao/Anaconda/anaconda/envs/prompt_sam/lib/python3.8/site-packages/torch/functional.py:445: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:2157.) return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined] Some weights of the model checkpoint at bert-base-uncased were not used when initializing BertModel: ['cls.seq_relationship.weight', 'cls.predictions.transform.LayerNorm.weight', 'cls.predictions.transform.dense.weight', 'cls.seq_relationship.bias', 'cls.predictions.bias', 'cls.predictions.transform.LayerNorm.bias', 'cls.predictions.transform.dense.bias'] - This IS expected if you are initializing BertModel from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model). - This IS NOT expected if you are initializing BertModel from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model). final text_encoder_type: bert-base-uncased loading annotations into memory... Done (t=0.00s) creating index... index created! final text_encoder_type: bert-base-uncased Input text prompt: Airplane . Body . Cockpit . Engine . Wing . huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) /scratch/work/mingqiao/Anaconda/anaconda/envs/prompt_sam/lib/python3.8/site-packages/transformers/modeling_utils.py:884: FutureWarning: The `device` argument is deprecated and will be removed in v5 of Transformers. warnings.warn( test_ap_on_seginw.py:119: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor'). topk_boxes = topk_indexes // prob.shape[2] Accumulating evaluation results... DONE (t=0.03s). Accumulating evaluation results... DONE (t=0.03s). IoU metric: bbox Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.338 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.458 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.323 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.389 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.445 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.595 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.352 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.548 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.548 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.480 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.625 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.702 IoU metric: segm Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.372 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.543 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.406 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.385 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.394 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.638 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.446 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.583 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.583 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.500 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.575 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.726 Final results: [0.37176255846370426, 0.5427763428516764, 0.40631351832279866, 0.38518387553041017, 0.39392101380467714, 0.6379270069864128, 0.44616666666666666, 0.5825, 0.5825, 0.5, 0.575, 0.7261904761904763] ./data/seginw/Bottles is data path ! /scratch/work/mingqiao/Anaconda/anaconda/envs/prompt_sam/lib/python3.8/site-packages/torch/functional.py:445: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:2157.) return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined] Some weights of the model checkpoint at bert-base-uncased were not used when initializing BertModel: ['cls.seq_relationship.weight', 'cls.predictions.bias', 'cls.seq_relationship.bias', 'cls.predictions.transform.dense.weight', 'cls.predictions.transform.LayerNorm.bias', 'cls.predictions.transform.dense.bias', 'cls.predictions.transform.LayerNorm.weight'] - This IS expected if you are initializing BertModel from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model). - This IS NOT expected if you are initializing BertModel from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model). final text_encoder_type: bert-base-uncased loading annotations into memory... Done (t=0.00s) creating index... index created! final text_encoder_type: bert-base-uncased Input text prompt: bottle . can . label . huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) /scratch/work/mingqiao/Anaconda/anaconda/envs/prompt_sam/lib/python3.8/site-packages/transformers/modeling_utils.py:884: FutureWarning: The `device` argument is deprecated and will be removed in v5 of Transformers. warnings.warn( test_ap_on_seginw.py:119: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor'). topk_boxes = topk_indexes // prob.shape[2] Accumulating evaluation results... DONE (t=0.02s). Accumulating evaluation results... DONE (t=0.02s). IoU metric: bbox Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.673 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.742 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.696 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = -1.000 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.673 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.529 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.854 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.860 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = -1.000 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.860 IoU metric: segm Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.654 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.741 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.674 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = -1.000 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.654 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.531 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.837 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.851 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = -1.000 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.851 Final results: [0.6538754148998803, 0.7410354550908884, 0.6744079215241758, -1.0, -1.0, 0.654252260228313, 0.5314524555903867, 0.8370254266805991, 0.8509926854754443, -1.0, -1.0, 0.8509926854754443] ./data/seginw/Brain-Tumor is data path ! /scratch/work/mingqiao/Anaconda/anaconda/envs/prompt_sam/lib/python3.8/site-packages/torch/functional.py:445: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:2157.) return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined] Some weights of the model checkpoint at bert-base-uncased were not used when initializing BertModel: ['cls.predictions.transform.dense.bias', 'cls.seq_relationship.bias', 'cls.predictions.bias', 'cls.predictions.transform.LayerNorm.bias', 'cls.seq_relationship.weight', 'cls.predictions.transform.dense.weight', 'cls.predictions.transform.LayerNorm.weight'] - This IS expected if you are initializing BertModel from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model). - This IS NOT expected if you are initializing BertModel from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model). final text_encoder_type: bert-base-uncased loading annotations into memory... Done (t=0.00s) creating index... index created! final text_encoder_type: bert-base-uncased Input text prompt: tumor . huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) /scratch/work/mingqiao/Anaconda/anaconda/envs/prompt_sam/lib/python3.8/site-packages/transformers/modeling_utils.py:884: FutureWarning: The `device` argument is deprecated and will be removed in v5 of Transformers. warnings.warn( test_ap_on_seginw.py:119: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor'). topk_boxes = topk_indexes // prob.shape[2] Accumulating evaluation results... DONE (t=0.02s). Accumulating evaluation results... DONE (t=0.02s). IoU metric: bbox Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.125 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.195 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.147 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.310 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.112 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.000 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.565 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.697 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.633 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.781 IoU metric: segm Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.119 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.191 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.137 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.312 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.095 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.000 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.522 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.641 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.605 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.688 Final results: [0.11908336385093755, 0.19069205611404016, 0.13702961991060095, -1.0, 0.31183846516583935, 0.09478281391513398, 0.0, 0.5216216216216216, 0.6405405405405405, -1.0, 0.6047619047619047, 0.6875] ./data/seginw/Chicken is data path ! /scratch/work/mingqiao/Anaconda/anaconda/envs/prompt_sam/lib/python3.8/site-packages/torch/functional.py:445: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:2157.) return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined] Some weights of the model checkpoint at bert-base-uncased were not used when initializing BertModel: ['cls.predictions.transform.LayerNorm.weight', 'cls.seq_relationship.bias', 'cls.predictions.transform.LayerNorm.bias', 'cls.predictions.transform.dense.bias', 'cls.seq_relationship.weight', 'cls.predictions.bias', 'cls.predictions.transform.dense.weight'] - This IS expected if you are initializing BertModel from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model). - This IS NOT expected if you are initializing BertModel from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model). final text_encoder_type: bert-base-uncased loading annotations into memory... Done (t=0.00s) creating index... index created! final text_encoder_type: bert-base-uncased Input text prompt: chicken . huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) /scratch/work/mingqiao/Anaconda/anaconda/envs/prompt_sam/lib/python3.8/site-packages/transformers/modeling_utils.py:884: FutureWarning: The `device` argument is deprecated and will be removed in v5 of Transformers. warnings.warn( test_ap_on_seginw.py:119: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor'). topk_boxes = topk_indexes // prob.shape[2] Accumulating evaluation results... DONE (t=0.01s). Accumulating evaluation results... DONE (t=0.00s). IoU metric: bbox Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.753 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.930 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.825 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.771 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.753 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.036 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.340 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.836 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.820 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.840 IoU metric: segm Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.845 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.930 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.930 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.853 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.843 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.040 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.360 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.900 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.900 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.900 Final results: [0.8451795608945394, 0.9302970297029702, 0.9302970297029702, -1.0, 0.8527581329561527, 0.8426157159059557, 0.039999999999999994, 0.36, 0.9, -1.0, 0.9, 0.8999999999999998] ./data/seginw/Cows is data path ! /scratch/work/mingqiao/Anaconda/anaconda/envs/prompt_sam/lib/python3.8/site-packages/torch/functional.py:445: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:2157.) return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined] Some weights of the model checkpoint at bert-base-uncased were not used when initializing BertModel: ['cls.seq_relationship.bias', 'cls.predictions.bias', 'cls.predictions.transform.LayerNorm.bias', 'cls.predictions.transform.LayerNorm.weight', 'cls.predictions.transform.dense.bias', 'cls.predictions.transform.dense.weight', 'cls.seq_relationship.weight'] - This IS expected if you are initializing BertModel from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model). - This IS NOT expected if you are initializing BertModel from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model). final text_encoder_type: bert-base-uncased loading annotations into memory... Done (t=0.00s) creating index... index created! final text_encoder_type: bert-base-uncased Input text prompt: cow . huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) /scratch/work/mingqiao/Anaconda/anaconda/envs/prompt_sam/lib/python3.8/site-packages/transformers/modeling_utils.py:884: FutureWarning: The `device` argument is deprecated and will be removed in v5 of Transformers. warnings.warn( test_ap_on_seginw.py:119: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor'). topk_boxes = topk_indexes // prob.shape[2] processed 29/60 images. time: 17.52s, ETA: 18.73s processed 59/60 images. time: 34.58s, ETA: 0.59s Accumulating evaluation results... DONE (t=0.04s). Accumulating evaluation results... DONE (t=0.03s). IoU metric: bbox Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.586 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.810 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.700 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.611 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.697 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.164 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.726 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.803 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.792 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.896 IoU metric: segm Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.475 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.804 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.551 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.465 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.803 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.146 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.609 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.657 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.637 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.837 Final results: [0.47473772585007035, 0.8036291536123708, 0.5513112398764473, -1.0, 0.4654262525715694, 0.8030318598671368, 0.14600760456273762, 0.609125475285171, 0.6574144486692015, -1.0, 0.6368644067796609, 0.837037037037037] ./data/seginw/Electric-Shaver is data path ! /scratch/work/mingqiao/Anaconda/anaconda/envs/prompt_sam/lib/python3.8/site-packages/torch/functional.py:445: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:2157.) return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined] Some weights of the model checkpoint at bert-base-uncased were not used when initializing BertModel: ['cls.predictions.transform.dense.weight', 'cls.seq_relationship.weight', 'cls.seq_relationship.bias', 'cls.predictions.transform.LayerNorm.bias', 'cls.predictions.transform.dense.bias', 'cls.predictions.transform.LayerNorm.weight', 'cls.predictions.bias'] - This IS expected if you are initializing BertModel from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model). - This IS NOT expected if you are initializing BertModel from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model). final text_encoder_type: bert-base-uncased loading annotations into memory... Done (t=0.00s) creating index... index created! final text_encoder_type: bert-base-uncased Input text prompt: caorau . huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) /scratch/work/mingqiao/Anaconda/anaconda/envs/prompt_sam/lib/python3.8/site-packages/transformers/modeling_utils.py:884: FutureWarning: The `device` argument is deprecated and will be removed in v5 of Transformers. warnings.warn( test_ap_on_seginw.py:119: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor'). topk_boxes = topk_indexes // prob.shape[2] Accumulating evaluation results... DONE (t=0.01s). Accumulating evaluation results... DONE (t=0.01s). IoU metric: bbox Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.832 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.860 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.856 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = -1.000 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.832 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.817 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.917 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.933 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = -1.000 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.933 IoU metric: segm Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.717 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.860 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.856 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = -1.000 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.717 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.717 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.800 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.825 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = -1.000 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.825 Final results: [0.7165321184016832, 0.8601922038699978, 0.855851447213687, -1.0, -1.0, 0.7165465765509106, 0.7166666666666667, 0.8, 0.8250000000000002, -1.0, -1.0, 0.8250000000000002] ./data/seginw/Elephants is data path ! /scratch/work/mingqiao/Anaconda/anaconda/envs/prompt_sam/lib/python3.8/site-packages/torch/functional.py:445: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:2157.) return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined] Some weights of the model checkpoint at bert-base-uncased were not used when initializing BertModel: ['cls.predictions.transform.LayerNorm.bias', 'cls.seq_relationship.bias', 'cls.predictions.transform.LayerNorm.weight', 'cls.seq_relationship.weight', 'cls.predictions.bias', 'cls.predictions.transform.dense.bias', 'cls.predictions.transform.dense.weight'] - This IS expected if you are initializing BertModel from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model). - This IS NOT expected if you are initializing BertModel from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model). final text_encoder_type: bert-base-uncased loading annotations into memory... Done (t=0.00s) creating index... index created! final text_encoder_type: bert-base-uncased Input text prompt: elephant . huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) /scratch/work/mingqiao/Anaconda/anaconda/envs/prompt_sam/lib/python3.8/site-packages/transformers/modeling_utils.py:884: FutureWarning: The `device` argument is deprecated and will be removed in v5 of Transformers. warnings.warn( test_ap_on_seginw.py:119: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor'). topk_boxes = topk_indexes // prob.shape[2] processed 29/99 images. time: 17.06s, ETA: 41.17s processed 59/99 images. time: 33.76s, ETA: 22.89s processed 89/99 images. time: 50.56s, ETA: 5.68s Accumulating evaluation results... DONE (t=0.07s). Accumulating evaluation results... DONE (t=0.06s). IoU metric: bbox Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.802 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.930 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.878 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.407 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.676 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.862 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.479 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.867 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.913 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.750 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.889 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.934 IoU metric: segm Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.779 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.925 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.897 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.335 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.624 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.845 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.463 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.833 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.875 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.767 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.841 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.898 Final results: [0.7790590802927754, 0.9254450462620254, 0.8971852036361958, 0.33477266645583476, 0.6243254495795106, 0.8452943210233075, 0.46269430051813465, 0.8331606217616582, 0.8751295336787563, 0.7666666666666666, 0.8412698412698413, 0.8975806451612904] ./data/seginw/Fruits is data path ! /scratch/work/mingqiao/Anaconda/anaconda/envs/prompt_sam/lib/python3.8/site-packages/torch/functional.py:445: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:2157.) return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined] Some weights of the model checkpoint at bert-base-uncased were not used when initializing BertModel: ['cls.seq_relationship.weight', 'cls.seq_relationship.bias', 'cls.predictions.transform.LayerNorm.weight', 'cls.predictions.bias', 'cls.predictions.transform.LayerNorm.bias', 'cls.predictions.transform.dense.bias', 'cls.predictions.transform.dense.weight'] - This IS expected if you are initializing BertModel from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model). - This IS NOT expected if you are initializing BertModel from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model). final text_encoder_type: bert-base-uncased loading annotations into memory... Done (t=0.00s) creating index... index created! final text_encoder_type: bert-base-uncased Input text prompt: apple . lemon . orange . pear . strawberry . huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) /scratch/work/mingqiao/Anaconda/anaconda/envs/prompt_sam/lib/python3.8/site-packages/transformers/modeling_utils.py:884: FutureWarning: The `device` argument is deprecated and will be removed in v5 of Transformers. warnings.warn( test_ap_on_seginw.py:119: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor'). topk_boxes = topk_indexes // prob.shape[2] Accumulating evaluation results... DONE (t=0.02s). Accumulating evaluation results... DONE (t=0.02s). IoU metric: bbox Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.817 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.881 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.881 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.900 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.801 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.853 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.883 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.883 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.900 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.879 IoU metric: segm Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.823 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.881 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.881 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.900 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.840 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.877 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.877 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.877 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.900 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.871 Final results: [0.8229372937293729, 0.8811881188118812, 0.8811881188118812, -1.0, 0.9, 0.8395214521452145, 0.8766666666666666, 0.8766666666666666, 0.8766666666666666, -1.0, 0.9, 0.8708333333333332] ./data/seginw/Garbage is data path ! /scratch/work/mingqiao/Anaconda/anaconda/envs/prompt_sam/lib/python3.8/site-packages/torch/functional.py:445: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:2157.) return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined] Some weights of the model checkpoint at bert-base-uncased were not used when initializing BertModel: ['cls.predictions.transform.LayerNorm.weight', 'cls.predictions.transform.dense.bias', 'cls.seq_relationship.weight', 'cls.predictions.transform.LayerNorm.bias', 'cls.predictions.bias', 'cls.seq_relationship.bias', 'cls.predictions.transform.dense.weight'] - This IS expected if you are initializing BertModel from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model). - This IS NOT expected if you are initializing BertModel from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model). final text_encoder_type: bert-base-uncased loading annotations into memory... Done (t=0.00s) creating index... index created! final text_encoder_type: bert-base-uncased Input text prompt: bin . garbage . pavement . road . huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) /scratch/work/mingqiao/Anaconda/anaconda/envs/prompt_sam/lib/python3.8/site-packages/transformers/modeling_utils.py:884: FutureWarning: The `device` argument is deprecated and will be removed in v5 of Transformers. warnings.warn( test_ap_on_seginw.py:119: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor'). topk_boxes = topk_indexes // prob.shape[2] processed 29/142 images. time: 17.12s, ETA: 66.69s processed 59/142 images. time: 33.84s, ETA: 47.60s processed 89/142 images. time: 50.57s, ETA: 30.11s processed 119/142 images. time: 67.31s, ETA: 13.01s Accumulating evaluation results... DONE (t=0.12s). Accumulating evaluation results... DONE (t=0.11s). IoU metric: bbox Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.327 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.381 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.343 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.800 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.016 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.359 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.554 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.838 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.870 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.800 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.416 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.904 IoU metric: segm Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.240 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.344 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.245 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.700 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.011 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.270 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.450 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.715 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.750 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.700 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.370 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.775 Final results: [0.23984946480794195, 0.34440975880441643, 0.24493111381440405, 0.6999999999999998, 0.011394498966858627, 0.2704801856523395, 0.4502885303105833, 0.714641323596345, 0.7504036237048408, 0.7, 0.37, 0.7750871371275784] ./data/seginw/Ginger-Garlic is data path ! /scratch/work/mingqiao/Anaconda/anaconda/envs/prompt_sam/lib/python3.8/site-packages/torch/functional.py:445: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:2157.) return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined] Some weights of the model checkpoint at bert-base-uncased were not used when initializing BertModel: ['cls.predictions.bias', 'cls.predictions.transform.dense.weight', 'cls.seq_relationship.weight', 'cls.predictions.transform.dense.bias', 'cls.predictions.transform.LayerNorm.bias', 'cls.predictions.transform.LayerNorm.weight', 'cls.seq_relationship.bias'] - This IS expected if you are initializing BertModel from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model). - This IS NOT expected if you are initializing BertModel from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model). final text_encoder_type: bert-base-uncased loading annotations into memory... Done (t=0.00s) creating index... index created! final text_encoder_type: bert-base-uncased Input text prompt: garlic . ginger . huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) /scratch/work/mingqiao/Anaconda/anaconda/envs/prompt_sam/lib/python3.8/site-packages/transformers/modeling_utils.py:884: FutureWarning: The `device` argument is deprecated and will be removed in v5 of Transformers. warnings.warn( test_ap_on_seginw.py:119: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor'). topk_boxes = topk_indexes // prob.shape[2] Accumulating evaluation results... DONE (t=0.02s). Accumulating evaluation results... DONE (t=0.01s). IoU metric: bbox Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.500 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.587 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.506 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.900 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.554 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.198 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.830 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.864 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.900 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.860 IoU metric: segm Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.458 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.536 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.536 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.833 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.617 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.152 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.825 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.833 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.900 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.828 Final results: [0.45770140543466103, 0.5362198866945519, 0.5362198866945519, -1.0, 0.8333333333333331, 0.61653449719972, 0.15227272727272728, 0.8250000000000002, 0.8333333333333334, -1.0, 0.9, 0.8283333333333334] ./data/seginw/Hand is data path ! /scratch/work/mingqiao/Anaconda/anaconda/envs/prompt_sam/lib/python3.8/site-packages/torch/functional.py:445: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:2157.) return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined] Some weights of the model checkpoint at bert-base-uncased were not used when initializing BertModel: ['cls.predictions.transform.LayerNorm.bias', 'cls.predictions.transform.LayerNorm.weight', 'cls.seq_relationship.weight', 'cls.predictions.bias', 'cls.seq_relationship.bias', 'cls.predictions.transform.dense.weight', 'cls.predictions.transform.dense.bias'] - This IS expected if you are initializing BertModel from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model). - This IS NOT expected if you are initializing BertModel from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model). final text_encoder_type: bert-base-uncased loading annotations into memory... Done (t=0.00s) creating index... index created! final text_encoder_type: bert-base-uncased Input text prompt: Hand-Segmentation . hand . huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) /scratch/work/mingqiao/Anaconda/anaconda/envs/prompt_sam/lib/python3.8/site-packages/transformers/modeling_utils.py:884: FutureWarning: The `device` argument is deprecated and will be removed in v5 of Transformers. warnings.warn( test_ap_on_seginw.py:119: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor'). topk_boxes = topk_indexes // prob.shape[2] processed 29/60 images. time: 17.14s, ETA: 18.32s processed 59/60 images. time: 33.76s, ETA: 0.57s Accumulating evaluation results... DONE (t=0.02s). Accumulating evaluation results... DONE (t=0.02s). IoU metric: bbox Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.727 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.964 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.672 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = -1.000 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.727 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.677 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.978 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.978 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = -1.000 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.978 IoU metric: segm Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.700 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.865 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.669 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = -1.000 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.701 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.732 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.957 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.960 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = -1.000 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.960 Final results: [0.7003227776302794, 0.8646994176470184, 0.668706973961466, -1.0, -1.0, 0.700833790065008, 0.7316666666666667, 0.9566666666666664, 0.96, -1.0, -1.0, 0.96] ./data/seginw/Hand-Metal is data path ! /scratch/work/mingqiao/Anaconda/anaconda/envs/prompt_sam/lib/python3.8/site-packages/torch/functional.py:445: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:2157.) return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined] Some weights of the model checkpoint at bert-base-uncased were not used when initializing BertModel: ['cls.predictions.transform.LayerNorm.weight', 'cls.predictions.transform.LayerNorm.bias', 'cls.seq_relationship.weight', 'cls.predictions.transform.dense.bias', 'cls.predictions.transform.dense.weight', 'cls.seq_relationship.bias', 'cls.predictions.bias'] - This IS expected if you are initializing BertModel from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model). - This IS NOT expected if you are initializing BertModel from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model). final text_encoder_type: bert-base-uncased loading annotations into memory... Done (t=0.00s) creating index... index created! final text_encoder_type: bert-base-uncased Input text prompt: hand . metal . huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) /scratch/work/mingqiao/Anaconda/anaconda/envs/prompt_sam/lib/python3.8/site-packages/transformers/modeling_utils.py:884: FutureWarning: The `device` argument is deprecated and will be removed in v5 of Transformers. warnings.warn( test_ap_on_seginw.py:119: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor'). topk_boxes = topk_indexes // prob.shape[2] processed 29/65 images. time: 19.00s, ETA: 23.59s processed 59/65 images. time: 37.25s, ETA: 3.79s Accumulating evaluation results... DONE (t=0.05s). Accumulating evaluation results... DONE (t=0.04s). IoU metric: bbox Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.809 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.907 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.878 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.335 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.842 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.638 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.916 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.936 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.925 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.936 IoU metric: segm Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.812 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.903 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.838 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.401 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.841 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.648 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.895 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.920 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.950 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.918 Final results: [0.8121789329447096, 0.9030538252178439, 0.838088667673718, -1.0, 0.40079395110389504, 0.8412446351829378, 0.6481588287488909, 0.8953194321206743, 0.9201197870452529, -1.0, 0.95, 0.918161094224924] ./data/seginw/House-Parts is data path ! /scratch/work/mingqiao/Anaconda/anaconda/envs/prompt_sam/lib/python3.8/site-packages/torch/functional.py:445: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:2157.) return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined] Some weights of the model checkpoint at bert-base-uncased were not used when initializing BertModel: ['cls.predictions.transform.dense.bias', 'cls.predictions.transform.LayerNorm.weight', 'cls.predictions.bias', 'cls.seq_relationship.weight', 'cls.predictions.transform.dense.weight', 'cls.predictions.transform.LayerNorm.bias', 'cls.seq_relationship.bias'] - This IS expected if you are initializing BertModel from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model). - This IS NOT expected if you are initializing BertModel from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model). final text_encoder_type: bert-base-uncased loading annotations into memory... Done (t=0.01s) creating index... index created! final text_encoder_type: bert-base-uncased Input text prompt: aluminium door . aluminium window . cellar window . mint cond roof . plaster . plastic door . plastic window . plate fascade . wooden door . wooden fascade . wooden window . worn cond roof . huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) /scratch/work/mingqiao/Anaconda/anaconda/envs/prompt_sam/lib/python3.8/site-packages/transformers/modeling_utils.py:884: FutureWarning: The `device` argument is deprecated and will be removed in v5 of Transformers. warnings.warn( test_ap_on_seginw.py:119: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor'). topk_boxes = topk_indexes // prob.shape[2] processed 29/201 images. time: 17.34s, ETA: 102.87s processed 59/201 images. time: 34.32s, ETA: 82.60s processed 89/201 images. time: 51.40s, ETA: 64.68s processed 119/201 images. time: 68.36s, ETA: 47.11s processed 149/201 images. time: 85.34s, ETA: 29.78s processed 179/201 images. time: 102.35s, ETA: 12.58s Accumulating evaluation results... DONE (t=0.32s). Accumulating evaluation results... DONE (t=0.31s). IoU metric: bbox Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.100 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.146 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.109 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.045 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.093 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.202 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.250 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.424 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.444 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.261 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.472 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.623 IoU metric: segm Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.084 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.133 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.091 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.035 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.092 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.237 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.213 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.380 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.399 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.300 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.447 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.532 Final results: [0.0839369503518368, 0.13324443075485487, 0.09087955414171642, 0.03460548832158848, 0.09229989479713643, 0.2373282085016308, 0.21279789555869985, 0.38007611852667167, 0.3994163453307902, 0.2999476543663722, 0.44685679943218604, 0.5316890238375782] ./data/seginw/HouseHold-Items is data path ! /scratch/work/mingqiao/Anaconda/anaconda/envs/prompt_sam/lib/python3.8/site-packages/torch/functional.py:445: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:2157.) return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined] Some weights of the model checkpoint at bert-base-uncased were not used when initializing BertModel: ['cls.seq_relationship.bias', 'cls.predictions.transform.dense.weight', 'cls.predictions.transform.LayerNorm.bias', 'cls.predictions.transform.LayerNorm.weight', 'cls.predictions.transform.dense.bias', 'cls.seq_relationship.weight', 'cls.predictions.bias'] - This IS expected if you are initializing BertModel from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model). - This IS NOT expected if you are initializing BertModel from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model). final text_encoder_type: bert-base-uncased loading annotations into memory... Done (t=0.00s) creating index... index created! final text_encoder_type: bert-base-uncased Input text prompt: bottle . mouse . perfume . phone . huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) /scratch/work/mingqiao/Anaconda/anaconda/envs/prompt_sam/lib/python3.8/site-packages/transformers/modeling_utils.py:884: FutureWarning: The `device` argument is deprecated and will be removed in v5 of Transformers. warnings.warn( test_ap_on_seginw.py:119: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor'). topk_boxes = topk_indexes // prob.shape[2] Accumulating evaluation results... DONE (t=0.01s). Accumulating evaluation results... DONE (t=0.01s). IoU metric: bbox Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.601 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.626 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.626 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = -1.000 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.601 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.700 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.700 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.700 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = -1.000 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.700 IoU metric: segm Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.601 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.626 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.626 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = -1.000 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.601 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.700 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.700 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.700 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = -1.000 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.700 Final results: [0.600990099009901, 0.6262376237623762, 0.6262376237623762, -1.0, -1.0, 0.600990099009901, 0.7, 0.7, 0.7, -1.0, -1.0, 0.7] ./data/seginw/Nutterfly-Squireel is data path ! /scratch/work/mingqiao/Anaconda/anaconda/envs/prompt_sam/lib/python3.8/site-packages/torch/functional.py:445: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:2157.) return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined] Some weights of the model checkpoint at bert-base-uncased were not used when initializing BertModel: ['cls.predictions.transform.LayerNorm.bias', 'cls.seq_relationship.weight', 'cls.seq_relationship.bias', 'cls.predictions.transform.dense.weight', 'cls.predictions.transform.dense.bias', 'cls.predictions.transform.LayerNorm.weight', 'cls.predictions.bias'] - This IS expected if you are initializing BertModel from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model). - This IS NOT expected if you are initializing BertModel from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model). final text_encoder_type: bert-base-uncased loading annotations into memory... Done (t=0.01s) creating index... index created! final text_encoder_type: bert-base-uncased Input text prompt: butterfly . squirrel . huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) /scratch/work/mingqiao/Anaconda/anaconda/envs/prompt_sam/lib/python3.8/site-packages/transformers/modeling_utils.py:884: FutureWarning: The `device` argument is deprecated and will be removed in v5 of Transformers. warnings.warn( test_ap_on_seginw.py:119: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor'). topk_boxes = topk_indexes // prob.shape[2] processed 29/237 images. time: 17.10s, ETA: 122.65s processed 59/237 images. time: 33.96s, ETA: 102.45s processed 89/237 images. time: 50.83s, ETA: 84.52s processed 119/237 images. time: 67.69s, ETA: 67.12s processed 149/237 images. time: 84.53s, ETA: 49.93s processed 179/237 images. time: 101.52s, ETA: 32.90s processed 209/237 images. time: 118.36s, ETA: 15.86s Accumulating evaluation results... DONE (t=0.14s). Accumulating evaluation results... DONE (t=0.14s). IoU metric: bbox Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.811 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.981 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.890 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.571 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.700 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.817 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.808 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.903 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.914 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.700 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.767 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.918 IoU metric: segm Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.713 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.933 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.777 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.367 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.800 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.726 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.713 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.808 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.830 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.367 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.800 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.837 Final results: [0.7134906859873504, 0.9333371456515335, 0.7768842940014018, 0.3673267326732673, 0.8, 0.7259981156697042, 0.7129020979020979, 0.8075174825174825, 0.8295104895104893, 0.36666666666666664, 0.8, 0.836582614465826] ./data/seginw/Phones is data path ! /scratch/work/mingqiao/Anaconda/anaconda/envs/prompt_sam/lib/python3.8/site-packages/torch/functional.py:445: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:2157.) return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined] Some weights of the model checkpoint at bert-base-uncased were not used when initializing BertModel: ['cls.predictions.transform.LayerNorm.bias', 'cls.predictions.transform.dense.bias', 'cls.seq_relationship.bias', 'cls.predictions.transform.dense.weight', 'cls.predictions.transform.LayerNorm.weight', 'cls.predictions.bias', 'cls.seq_relationship.weight'] - This IS expected if you are initializing BertModel from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model). - This IS NOT expected if you are initializing BertModel from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model). final text_encoder_type: bert-base-uncased loading annotations into memory... Done (t=0.00s) creating index... index created! final text_encoder_type: bert-base-uncased Input text prompt: phone . huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) /scratch/work/mingqiao/Anaconda/anaconda/envs/prompt_sam/lib/python3.8/site-packages/transformers/modeling_utils.py:884: FutureWarning: The `device` argument is deprecated and will be removed in v5 of Transformers. warnings.warn( test_ap_on_seginw.py:119: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor'). topk_boxes = topk_indexes // prob.shape[2] Accumulating evaluation results... DONE (t=0.01s). Accumulating evaluation results... DONE (t=0.01s). IoU metric: bbox Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.380 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.466 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.466 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.292 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.570 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.850 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.151 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.638 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.815 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.713 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.841 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.850 IoU metric: segm Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.354 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.467 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.463 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.249 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.673 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.800 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.141 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.595 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.769 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.675 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.793 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.800 Final results: [0.3538872401429167, 0.4668995779859205, 0.46259573960473505, 0.24887577384476464, 0.6731690396492017, 0.8, 0.14102564102564102, 0.5948717948717949, 0.7692307692307692, 0.675, 0.7931034482758621, 0.8] ./data/seginw/Poles is data path ! /scratch/work/mingqiao/Anaconda/anaconda/envs/prompt_sam/lib/python3.8/site-packages/torch/functional.py:445: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:2157.) return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined] Some weights of the model checkpoint at bert-base-uncased were not used when initializing BertModel: ['cls.predictions.bias', 'cls.predictions.transform.LayerNorm.bias', 'cls.seq_relationship.bias', 'cls.predictions.transform.LayerNorm.weight', 'cls.seq_relationship.weight', 'cls.predictions.transform.dense.bias', 'cls.predictions.transform.dense.weight'] - This IS expected if you are initializing BertModel from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model). - This IS NOT expected if you are initializing BertModel from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model). final text_encoder_type: bert-base-uncased loading annotations into memory... Done (t=0.00s) creating index... index created! final text_encoder_type: bert-base-uncased Input text prompt: poles . huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) /scratch/work/mingqiao/Anaconda/anaconda/envs/prompt_sam/lib/python3.8/site-packages/transformers/modeling_utils.py:884: FutureWarning: The `device` argument is deprecated and will be removed in v5 of Transformers. warnings.warn( test_ap_on_seginw.py:119: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor'). topk_boxes = topk_indexes // prob.shape[2] Accumulating evaluation results... DONE (t=0.01s). Accumulating evaluation results... DONE (t=0.01s). IoU metric: bbox Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.442 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.442 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.442 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = -1.000 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.442 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.667 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.667 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.667 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = -1.000 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.667 IoU metric: segm Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.233 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.442 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.112 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = -1.000 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.368 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.367 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.367 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.400 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = -1.000 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.400 Final results: [0.2325367019460567, 0.4422442244224422, 0.1122112211221122, -1.0, -1.0, 0.3675907590759076, 0.36666666666666664, 0.36666666666666664, 0.4, -1.0, -1.0, 0.4] ./data/seginw/Puppies is data path ! /scratch/work/mingqiao/Anaconda/anaconda/envs/prompt_sam/lib/python3.8/site-packages/torch/functional.py:445: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:2157.) return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined] Some weights of the model checkpoint at bert-base-uncased were not used when initializing BertModel: ['cls.predictions.transform.dense.bias', 'cls.seq_relationship.weight', 'cls.predictions.bias', 'cls.predictions.transform.LayerNorm.weight', 'cls.seq_relationship.bias', 'cls.predictions.transform.dense.weight', 'cls.predictions.transform.LayerNorm.bias'] - This IS expected if you are initializing BertModel from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model). - This IS NOT expected if you are initializing BertModel from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model). final text_encoder_type: bert-base-uncased loading annotations into memory... Done (t=0.00s) creating index... index created! final text_encoder_type: bert-base-uncased Input text prompt: puppy . huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) /scratch/work/mingqiao/Anaconda/anaconda/envs/prompt_sam/lib/python3.8/site-packages/transformers/modeling_utils.py:884: FutureWarning: The `device` argument is deprecated and will be removed in v5 of Transformers. warnings.warn( test_ap_on_seginw.py:119: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor'). topk_boxes = topk_indexes // prob.shape[2] Accumulating evaluation results... DONE (t=0.01s). Accumulating evaluation results... DONE (t=0.00s). IoU metric: bbox Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.533 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.547 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.547 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = -1.000 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.533 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.333 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.817 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.817 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = -1.000 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.817 IoU metric: segm Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.501 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.547 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.547 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = -1.000 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.543 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.317 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.767 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.767 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = -1.000 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.767 Final results: [0.5011138613861387, 0.5474422442244224, 0.5474422442244224, -1.0, -1.0, 0.5430693069306931, 0.31666666666666665, 0.7666666666666667, 0.7666666666666667, -1.0, -1.0, 0.7666666666666667] ./data/seginw/Rail is data path ! /scratch/work/mingqiao/Anaconda/anaconda/envs/prompt_sam/lib/python3.8/site-packages/torch/functional.py:445: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:2157.) return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined] Some weights of the model checkpoint at bert-base-uncased were not used when initializing BertModel: ['cls.predictions.transform.LayerNorm.weight', 'cls.predictions.bias', 'cls.seq_relationship.weight', 'cls.seq_relationship.bias', 'cls.predictions.transform.LayerNorm.bias', 'cls.predictions.transform.dense.weight', 'cls.predictions.transform.dense.bias'] - This IS expected if you are initializing BertModel from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model). - This IS NOT expected if you are initializing BertModel from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model). final text_encoder_type: bert-base-uncased loading annotations into memory... Done (t=0.01s) creating index... index created! final text_encoder_type: bert-base-uncased Input text prompt: rail . huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) /scratch/work/mingqiao/Anaconda/anaconda/envs/prompt_sam/lib/python3.8/site-packages/transformers/modeling_utils.py:884: FutureWarning: The `device` argument is deprecated and will be removed in v5 of Transformers. warnings.warn( test_ap_on_seginw.py:119: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor'). topk_boxes = topk_indexes // prob.shape[2] processed 29/1069 images. time: 32.54s, ETA: 1166.95s processed 59/1069 images. time: 64.37s, ETA: 1101.87s processed 89/1069 images. time: 96.02s, ETA: 1057.34s processed 119/1069 images. time: 127.70s, ETA: 1019.46s processed 149/1069 images. time: 159.64s, ETA: 985.67s processed 179/1069 images. time: 191.48s, ETA: 952.04s processed 209/1069 images. time: 223.18s, ETA: 918.34s processed 239/1069 images. time: 254.82s, ETA: 884.96s processed 269/1069 images. time: 286.42s, ETA: 851.79s processed 299/1069 images. time: 318.24s, ETA: 819.56s processed 329/1069 images. time: 350.03s, ETA: 787.31s processed 359/1069 images. time: 381.69s, ETA: 754.87s processed 389/1069 images. time: 413.54s, ETA: 722.90s processed 419/1069 images. time: 445.41s, ETA: 690.97s processed 449/1069 images. time: 477.27s, ETA: 659.03s processed 479/1069 images. time: 509.05s, ETA: 627.01s processed 509/1069 images. time: 541.05s, ETA: 595.27s processed 539/1069 images. time: 573.05s, ETA: 563.48s processed 569/1069 images. time: 604.88s, ETA: 531.53s processed 599/1069 images. time: 636.84s, ETA: 499.69s processed 629/1069 images. time: 668.76s, ETA: 467.82s processed 659/1069 images. time: 700.58s, ETA: 435.87s processed 689/1069 images. time: 732.41s, ETA: 403.94s processed 719/1069 images. time: 764.71s, ETA: 372.25s processed 749/1069 images. time: 796.83s, ETA: 340.44s processed 779/1069 images. time: 828.74s, ETA: 308.52s processed 809/1069 images. time: 860.69s, ETA: 276.61s processed 839/1069 images. time: 892.70s, ETA: 244.72s processed 869/1069 images. time: 924.48s, ETA: 212.77s processed 899/1069 images. time: 956.22s, ETA: 180.82s processed 929/1069 images. time: 988.04s, ETA: 148.90s processed 959/1069 images. time: 1020.05s, ETA: 117.00s processed 989/1069 images. time: 1052.00s, ETA: 85.10s processed 1019/1069 images. time: 1083.84s, ETA: 53.18s processed 1049/1069 images. time: 1115.67s, ETA: 21.27s Accumulating evaluation results... DONE (t=0.44s). Accumulating evaluation results... DONE (t=0.45s). IoU metric: bbox Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.280 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.386 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.334 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = -1.000 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.280 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.283 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.782 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.823 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = -1.000 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.823 IoU metric: segm Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.087 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.183 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.071 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = -1.000 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.088 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.137 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.394 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.535 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = -1.000 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.535 Final results: [0.08714633746169356, 0.1829311717837147, 0.07149778190957137, -1.0, -1.0, 0.08834357115430443, 0.13680751173708922, 0.39352112676056333, 0.5349295774647889, -1.0, -1.0, 0.5349295774647889] ./data/seginw/Salmon-Fillet is data path ! /scratch/work/mingqiao/Anaconda/anaconda/envs/prompt_sam/lib/python3.8/site-packages/torch/functional.py:445: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:2157.) return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined] Some weights of the model checkpoint at bert-base-uncased were not used when initializing BertModel: ['cls.predictions.transform.LayerNorm.bias', 'cls.predictions.bias', 'cls.seq_relationship.weight', 'cls.predictions.transform.dense.bias', 'cls.predictions.transform.dense.weight', 'cls.predictions.transform.LayerNorm.weight', 'cls.seq_relationship.bias'] - This IS expected if you are initializing BertModel from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model). - This IS NOT expected if you are initializing BertModel from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model). final text_encoder_type: bert-base-uncased loading annotations into memory... Done (t=0.00s) creating index... index created! final text_encoder_type: bert-base-uncased Input text prompt: Salmon_fillet . huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) /scratch/work/mingqiao/Anaconda/anaconda/envs/prompt_sam/lib/python3.8/site-packages/transformers/modeling_utils.py:884: FutureWarning: The `device` argument is deprecated and will be removed in v5 of Transformers. warnings.warn( test_ap_on_seginw.py:119: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor'). topk_boxes = topk_indexes // prob.shape[2] processed 29/64 images. time: 15.96s, ETA: 19.26s processed 59/64 images. time: 31.41s, ETA: 2.66s Accumulating evaluation results... DONE (t=0.04s). Accumulating evaluation results... DONE (t=0.04s). IoU metric: bbox Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.490 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.525 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.505 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.230 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.274 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.704 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.505 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.830 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.898 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.777 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.872 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.963 IoU metric: segm Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.329 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.482 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.335 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.165 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.130 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.555 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.384 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.743 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.867 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.846 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.856 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.881 Final results: [0.32945066258866773, 0.48153763935325544, 0.33533874975772254, 0.16460223885907962, 0.13032074611951786, 0.5554636587722717, 0.38412698412698404, 0.7428571428571428, 0.8666666666666666, 0.8461538461538461, 0.8555555555555555, 0.88125] ./data/seginw/Strawberry is data path ! /scratch/work/mingqiao/Anaconda/anaconda/envs/prompt_sam/lib/python3.8/site-packages/torch/functional.py:445: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:2157.) return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined] Some weights of the model checkpoint at bert-base-uncased were not used when initializing BertModel: ['cls.seq_relationship.bias', 'cls.predictions.transform.dense.bias', 'cls.seq_relationship.weight', 'cls.predictions.transform.LayerNorm.weight', 'cls.predictions.transform.LayerNorm.bias', 'cls.predictions.transform.dense.weight', 'cls.predictions.bias'] - This IS expected if you are initializing BertModel from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model). - This IS NOT expected if you are initializing BertModel from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model). final text_encoder_type: bert-base-uncased loading annotations into memory... Done (t=0.00s) creating index... index created! final text_encoder_type: bert-base-uncased Input text prompt: R_strawberry . people . huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) /scratch/work/mingqiao/Anaconda/anaconda/envs/prompt_sam/lib/python3.8/site-packages/transformers/modeling_utils.py:884: FutureWarning: The `device` argument is deprecated and will be removed in v5 of Transformers. warnings.warn( test_ap_on_seginw.py:119: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor'). topk_boxes = topk_indexes // prob.shape[2] processed 29/87 images. time: 16.96s, ETA: 33.92s processed 59/87 images. time: 33.58s, ETA: 15.93s Accumulating evaluation results... DONE (t=0.05s). Accumulating evaluation results... DONE (t=0.04s). IoU metric: bbox Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.748 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.987 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.722 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.414 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.770 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.676 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.869 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.941 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.875 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.942 IoU metric: segm Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.835 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.993 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.971 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.586 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.857 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.781 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.898 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.910 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.725 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.930 Final results: [0.8347980474983986, 0.9934628003104631, 0.9705017231839714, -1.0, 0.5863399566016525, 0.8567764351705033, 0.7814285714285715, 0.8976190476190476, 0.9104761904761904, -1.0, 0.725, 0.9296296296296296] ./data/seginw/Tablets is data path ! /scratch/work/mingqiao/Anaconda/anaconda/envs/prompt_sam/lib/python3.8/site-packages/torch/functional.py:445: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:2157.) return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined] Some weights of the model checkpoint at bert-base-uncased were not used when initializing BertModel: ['cls.seq_relationship.bias', 'cls.predictions.transform.LayerNorm.bias', 'cls.predictions.transform.dense.bias', 'cls.predictions.transform.dense.weight', 'cls.seq_relationship.weight', 'cls.predictions.bias', 'cls.predictions.transform.LayerNorm.weight'] - This IS expected if you are initializing BertModel from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model). - This IS NOT expected if you are initializing BertModel from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model). final text_encoder_type: bert-base-uncased loading annotations into memory... Done (t=0.00s) creating index... index created! final text_encoder_type: bert-base-uncased Input text prompt: tablets . huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) /scratch/work/mingqiao/Anaconda/anaconda/envs/prompt_sam/lib/python3.8/site-packages/transformers/modeling_utils.py:884: FutureWarning: The `device` argument is deprecated and will be removed in v5 of Transformers. warnings.warn( test_ap_on_seginw.py:119: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor'). topk_boxes = topk_indexes // prob.shape[2] Accumulating evaluation results... DONE (t=0.01s). Accumulating evaluation results... DONE (t=0.01s). IoU metric: bbox Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.311 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.406 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.372 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.184 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.623 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.331 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.029 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.619 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.795 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.718 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.802 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.967 IoU metric: segm Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.298 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.395 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.384 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.151 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.511 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.305 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.029 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.595 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.757 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.664 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.771 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.867 Final results: [0.2982550003433559, 0.39498449143433517, 0.3836945109565253, 0.1508459668862955, 0.511325202290415, 0.3045544554455446, 0.02857142857142857, 0.5952380952380952, 0.757142857142857, 0.6636363636363636, 0.7714285714285715, 0.8666666666666666] ./data/seginw/Toolkits is data path ! /scratch/work/mingqiao/Anaconda/anaconda/envs/prompt_sam/lib/python3.8/site-packages/torch/functional.py:445: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:2157.) return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined] Some weights of the model checkpoint at bert-base-uncased were not used when initializing BertModel: ['cls.seq_relationship.weight', 'cls.predictions.transform.dense.bias', 'cls.predictions.transform.LayerNorm.bias', 'cls.predictions.transform.dense.weight', 'cls.seq_relationship.bias', 'cls.predictions.transform.LayerNorm.weight', 'cls.predictions.bias'] - This IS expected if you are initializing BertModel from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model). - This IS NOT expected if you are initializing BertModel from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model). final text_encoder_type: bert-base-uncased loading annotations into memory... Done (t=0.00s) creating index... index created! final text_encoder_type: bert-base-uncased Input text prompt: Allen-key . block . gasket . plier . prism . screw . screwdriver . wrench . huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) /scratch/work/mingqiao/Anaconda/anaconda/envs/prompt_sam/lib/python3.8/site-packages/transformers/modeling_utils.py:884: FutureWarning: The `device` argument is deprecated and will be removed in v5 of Transformers. warnings.warn( test_ap_on_seginw.py:119: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor'). topk_boxes = topk_indexes // prob.shape[2] Accumulating evaluation results... DONE (t=0.03s). Accumulating evaluation results... DONE (t=0.02s). IoU metric: bbox Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.253 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.262 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.262 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.191 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.750 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.358 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.686 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.686 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.623 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 1.000 IoU metric: segm Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.208 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.262 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.214 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.147 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.875 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.314 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.575 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.575 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.510 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.875 Final results: [0.20849053623311048, 0.26240076627506675, 0.21414101276348374, -1.0, 0.14664559409608915, 0.8752475247524752, 0.31388888888888894, 0.575, 0.575, -1.0, 0.51, 0.875] ./data/seginw/Trash is data path ! /scratch/work/mingqiao/Anaconda/anaconda/envs/prompt_sam/lib/python3.8/site-packages/torch/functional.py:445: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:2157.) return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined] Some weights of the model checkpoint at bert-base-uncased were not used when initializing BertModel: ['cls.predictions.bias', 'cls.predictions.transform.LayerNorm.bias', 'cls.seq_relationship.bias', 'cls.seq_relationship.weight', 'cls.predictions.transform.dense.weight', 'cls.predictions.transform.dense.bias', 'cls.predictions.transform.LayerNorm.weight'] - This IS expected if you are initializing BertModel from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model). - This IS NOT expected if you are initializing BertModel from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model). final text_encoder_type: bert-base-uncased loading annotations into memory... Done (t=0.00s) creating index... index created! final text_encoder_type: bert-base-uncased Input text prompt: Aluminium foil . Cigarette . Clear plastic bottle . Corrugated carton . Disposable plastic cup . Drink Can . Egg Carton . Foam cup . Food Can . Garbage bag . Glass bottle . Glass cup . Metal bottle cap . Other carton . Other plastic bottle . Paper cup . Plastic bag - wrapper . Plastic bottle cap . Plastic lid . Plastic straw . Pop tab . Styrofoam piece . huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) /scratch/work/mingqiao/Anaconda/anaconda/envs/prompt_sam/lib/python3.8/site-packages/transformers/modeling_utils.py:884: FutureWarning: The `device` argument is deprecated and will be removed in v5 of Transformers. warnings.warn( test_ap_on_seginw.py:119: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor'). topk_boxes = topk_indexes // prob.shape[2] processed 29/92 images. time: 19.73s, ETA: 42.87s processed 59/92 images. time: 39.27s, ETA: 21.96s processed 89/92 images. time: 58.65s, ETA: 1.98s Accumulating evaluation results... DONE (t=0.21s). Accumulating evaluation results... DONE (t=0.21s). IoU metric: bbox Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.275 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.328 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.301 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.053 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.241 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.478 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.489 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.684 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.701 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.211 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.610 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.916 IoU metric: segm Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.300 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.328 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.309 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.035 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.252 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.541 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.529 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.716 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.732 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.183 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.648 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.915 Final results: [0.2995447021380164, 0.32788319650260095, 0.30904022124747244, 0.03528820806478989, 0.2517823003509626, 0.540812606327837, 0.5293696074000696, 0.7155813183082089, 0.7318013649282556, 0.1825048104131296, 0.6483573717948717, 0.9152714932126698] ./data/seginw/Watermelon is data path ! /scratch/work/mingqiao/Anaconda/anaconda/envs/prompt_sam/lib/python3.8/site-packages/torch/functional.py:445: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:2157.) return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined] Some weights of the model checkpoint at bert-base-uncased were not used when initializing BertModel: ['cls.predictions.bias', 'cls.seq_relationship.weight', 'cls.predictions.transform.LayerNorm.bias', 'cls.predictions.transform.dense.weight', 'cls.predictions.transform.dense.bias', 'cls.seq_relationship.bias', 'cls.predictions.transform.LayerNorm.weight'] - This IS expected if you are initializing BertModel from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model). - This IS NOT expected if you are initializing BertModel from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model). final text_encoder_type: bert-base-uncased loading annotations into memory... Done (t=0.00s) creating index... index created! final text_encoder_type: bert-base-uncased Input text prompt: watermelon . huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) /scratch/work/mingqiao/Anaconda/anaconda/envs/prompt_sam/lib/python3.8/site-packages/transformers/modeling_utils.py:884: FutureWarning: The `device` argument is deprecated and will be removed in v5 of Transformers. warnings.warn( test_ap_on_seginw.py:119: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor'). topk_boxes = topk_indexes // prob.shape[2] Accumulating evaluation results... DONE (t=0.02s). Accumulating evaluation results... DONE (t=0.02s). IoU metric: bbox Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.680 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.846 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.798 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.627 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.508 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.748 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.134 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.649 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.841 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.697 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.770 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.914 IoU metric: segm Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.642 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.846 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.698 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.607 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.453 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.724 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.128 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.629 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.811 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.677 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.820 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.868 Final results: [0.6424268445515833, 0.8460533157850189, 0.6982170113558264, 0.6073057565031484, 0.45327448117803076, 0.7240406288144864, 0.12767857142857142, 0.6294642857142857, 0.8107142857142856, 0.6774193548387097, 0.82, 0.8676056338028169]