# UNet

> [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://arxiv.org/abs/1505.04597)

## Introduction

<!-- [ALGORITHM] -->

<a href="http://lmb.informatik.uni-freiburg.de/people/ronneber/u-net">Official Repo</a>

<a href="https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/unet.py#L225">Code Snippet</a>

## Abstract

<!-- [ABSTRACT] -->

There is large consent that successful training of deep networks requires many thousand annotated training samples. In this paper, we present a network and training strategy that relies on the strong use of data augmentation to use the available annotated samples more efficiently. The architecture consists of a contracting path to capture context and a symmetric expanding path that enables precise localization. We show that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks. Using the same network trained on transmitted light microscopy images (phase contrast and DIC) we won the ISBI cell tracking challenge 2015 in these categories by a large margin. Moreover, the network is fast. Segmentation of a 512x512 image takes less than a second on a recent GPU. The full implementation (based on Caffe) and the trained networks are available at [this http URL](https://lmb.informatik.uni-freiburg.de/people/ronneber/u-net/).

<!-- [IMAGE] -->

<div align=center>
<img src="https://user-images.githubusercontent.com/24582831/142902977-20fe689d-a147-4d92-9690-dbfde8b68dbe.png" width="70%"/>
</div>

## Results and models

### Cityscapes

| Method     | Backbone    | Loss          | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | Device |  mIoU | mIoU(ms+flip) | config                                                                                                                         | download                                                                                                                                                                                                                                                                                                                                                                     |
| ---------- | ----------- | ------------- | --------- | ------: | -------- | -------------- | ------ | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| UNet + FCN | UNet-S5-D16 | Cross Entropy | 512x1024  |  160000 | 17.91    | 3.05           | V100   | 69.10 |         71.05 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/unet/unet-s5-d16_fcn_4xb4-160k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_4x4_512x1024_160k_cityscapes/fcn_unet_s5-d16_4x4_512x1024_160k_cityscapes_20211210_145204-6860854e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_4x4_512x1024_160k_cityscapes/fcn_unet_s5-d16_4x4_512x1024_160k_cityscapes_20211210_145204.log.json) |

### DRIVE

| Method           | Backbone    | Loss                 | Image Size | Crop Size | Stride | Lr schd | Mem (GB) | Inf time (fps) | Device | mDice |  Dice | config                                                                                                                                      | download                                                                                                                                                                                                                                                                                                                                                                                                         |
| ---------------- | ----------- | -------------------- | ---------- | --------- | -----: | ------- | -------- | -------------: | ------ | ----: | ----: | ------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| UNet + FCN       | UNet-S5-D16 | Cross Entropy        | 584x565    | 64x64     |  42x42 | 40000   | 0.680    |              - | V100   | 88.38 | 78.67 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/unet/unet-s5-d16_fcn_4xb4-40k_drive-64x64.py)                       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_64x64_40k_drive/fcn_unet_s5-d16_64x64_40k_drive_20201223_191051-5daf6d3b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/unet_s5-d16_64x64_40k_drive/unet_s5-d16_64x64_40k_drive-20201223_191051.log.json)                                                                                                 |
| UNet + FCN       | UNet-S5-D16 | Cross Entropy + Dice | 584x565    | 64x64     |  42x42 | 40000   | 0.582    |              - | V100   | 88.71 | 79.32 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/unet/unet-s5-d16_fcn_4xb4-ce-1.0-dice-3.0-40k_drive-64x64.py)       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive/fcn_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive_20211210_201820-785de5c2.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive/fcn_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive_20211210_201820.log.json)                         |
| UNet + PSPNet    | UNet-S5-D16 | Cross Entropy        | 584x565    | 64x64     |  42x42 | 40000   | 0.599    |              - | V100   | 88.35 | 78.62 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/unet/unet-s5-d16_pspnet_4xb4-40k_drive-64x64.py)                    | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_64x64_40k_drive/pspnet_unet_s5-d16_64x64_40k_drive_20201227_181818-aac73387.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_64x64_40k_drive/pspnet_unet_s5-d16_64x64_40k_drive-20201227_181818.log.json)                                                                             |
| UNet + PSPNet    | UNet-S5-D16 | Cross Entropy + Dice | 584x565    | 64x64     |  42x42 | 40000   | 0.585    |              - | V100   | 88.76 | 79.42 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/unet/unet-s5-d16_pspnet_4xb4-ce-1.0-dice-3.0-40k_drive-64x64.py)    | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive/pspnet_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive_20211210_201821-22b3e3ba.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive/pspnet_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive_20211210_201821.log.json)             |
| UNet + DeepLabV3 | UNet-S5-D16 | Cross Entropy        | 584x565    | 64x64     |  42x42 | 40000   | 0.596    |              - | V100   | 88.38 | 78.69 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/unet/unet-s5-d16_deeplabv3_4xb4-40k_drive-64x64.py)                 | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_64x64_40k_drive/deeplabv3_unet_s5-d16_64x64_40k_drive_20201226_094047-0671ff20.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_64x64_40k_drive/deeplabv3_unet_s5-d16_64x64_40k_drive-20201226_094047.log.json)                                                                 |
| UNet + DeepLabV3 | UNet-S5-D16 | Cross Entropy + Dice | 584x565    | 64x64     |  42x42 | 40000   | 0.582    |              - | V100   | 88.84 | 79.56 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/unet/unet-s5-d16_deeplabv3_4xb4-ce-1.0-dice-3.0-40k_drive-64x64.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive_20211210_201825-6bf0efd7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_64x64_40k_drive_20211210_201825.log.json) |

### STARE

| Method           | Backbone    | Loss                 | Image Size | Crop Size | Stride | Lr schd | Mem (GB) | Inf time (fps) | Device | mDice |  Dice | config                                                                                                                                        | download                                                                                                                                                                                                                                                                                                                                                                                                                 |
| ---------------- | ----------- | -------------------- | ---------- | --------- | -----: | ------- | -------- | -------------: | ------ | ----: | ----: | --------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| UNet + FCN       | UNet-S5-D16 | Cross Entropy        | 605x700    | 128x128   |  85x85 | 40000   | 0.968    |              - | V100   | 89.78 | 81.02 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/unet/unet-s5-d16_fcn_4xb4-40k_stare-128x128.py)                       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_128x128_40k_stare/fcn_unet_s5-d16_128x128_40k_stare_20201223_191051-7d77e78b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/unet_s5-d16_128x128_40k_stare/unet_s5-d16_128x128_40k_stare-20201223_191051.log.json)                                                                                                 |
| UNet + FCN       | UNet-S5-D16 | Cross Entropy + Dice | 605x700    | 128x128   |  85x85 | 40000   | 0.986    |              - | V100   | 90.65 | 82.70 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/unet/unet-s5-d16_fcn_4xb4-ce-1.0-dice-3.0-40k_stare-128x128.py)       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare/fcn_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare_20211210_201821-f75705a9.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare/fcn_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare_20211210_201821.log.json)                         |
| UNet + PSPNet    | UNet-S5-D16 | Cross Entropy        | 605x700    | 128x128   |  85x85 | 40000   | 0.982    |              - | V100   | 89.89 | 81.22 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/unet/unet-s5-d16_pspnet_4xb4-40k_stare-128x128.py)                    | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_128x128_40k_stare/pspnet_unet_s5-d16_128x128_40k_stare_20201227_181818-3c2923c4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_128x128_40k_stare/pspnet_unet_s5-d16_128x128_40k_stare-20201227_181818.log.json)                                                                             |
| UNet + PSPNet    | UNet-S5-D16 | Cross Entropy + Dice | 605x700    | 128x128   |  85x85 | 40000   | 1.028    |              - | V100   | 90.72 | 82.84 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/unet/unet-s5-d16_pspnet_4xb4-ce-1.0-dice-3.0-40k_stare-128x128.py)    | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare/pspnet_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare_20211210_201823-f1063ef7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare/pspnet_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare_20211210_201823.log.json)             |
| UNet + DeepLabV3 | UNet-S5-D16 | Cross Entropy        | 605x700    | 128x128   |  85x85 | 40000   | 0.999    |              - | V100   | 89.73 | 80.93 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/unet/unet-s5-d16_deeplabv3_4xb4-40k_stare-128x128.py)                 | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_128x128_40k_stare/deeplabv3_unet_s5-d16_128x128_40k_stare_20201226_094047-93dcb93c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_128x128_40k_stare/deeplabv3_unet_s5-d16_128x128_40k_stare-20201226_094047.log.json)                                                                 |
| UNet + DeepLabV3 | UNet-S5-D16 | Cross Entropy + Dice | 605x700    | 128x128   |  85x85 | 40000   | 1.010    |              - | V100   | 90.65 | 82.71 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/unet/unet-s5-d16_deeplabv3_4xb4-ce-1.0-dice-3.0-40k_stare-128x128.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare_20211210_201825-21db614c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_stare_20211210_201825.log.json) |

### CHASE_DB1

| Method           | Backbone    | Loss                 | Image Size | Crop Size | Stride | Lr schd | Mem (GB) | Inf time (fps) | Device | mDice |  Dice | config                                                                                                                                            | download                                                                                                                                                                                                                                                                                                                                                                                                                                 |
| ---------------- | ----------- | -------------------- | ---------- | --------- | -----: | ------- | -------- | -------------: | ------ | ----: | ----: | ------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| UNet + FCN       | UNet-S5-D16 | Cross Entropy        | 960x999    | 128x128   |  85x85 | 40000   | 0.968    |              - | V100   | 89.46 | 80.24 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/unet/unet-s5-d16_fcn_4xb4-40k_chase-db1-128x128.py)                       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_128x128_40k_chase_db1/fcn_unet_s5-d16_128x128_40k_chase_db1_20201223_191051-11543527.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/unet_s5-d16_128x128_40k_chase_db1/unet_s5-d16_128x128_40k_chase_db1-20201223_191051.log.json)                                                                                                 |
| UNet + FCN       | UNet-S5-D16 | Cross Entropy + Dice | 960x999    | 128x128   |  85x85 | 40000   | 0.986    |              - | V100   | 89.52 | 80.40 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/unet/unet-s5-d16_fcn_4xb4-ce-1.0-dice-3.0-40k_chase-db1-128x128.py)       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1/fcn_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1_20211210_201821-1c4eb7cf.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1/fcn_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1_20211210_201821.log.json)                         |
| UNet + PSPNet    | UNet-S5-D16 | Cross Entropy        | 960x999    | 128x128   |  85x85 | 40000   | 0.982    |              - | V100   | 89.52 | 80.36 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/unet/unet-s5-d16_pspnet_4xb4-40k_chase-db1-128x128.py)                    | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_128x128_40k_chase_db1/pspnet_unet_s5-d16_128x128_40k_chase_db1_20201227_181818-68d4e609.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_128x128_40k_chase_db1/pspnet_unet_s5-d16_128x128_40k_chase_db1-20201227_181818.log.json)                                                                             |
| UNet + PSPNet    | UNet-S5-D16 | Cross Entropy + Dice | 960x999    | 128x128   |  85x85 | 40000   | 1.028    |              - | V100   | 89.45 | 80.28 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/unet/unet-s5-d16_pspnet_4xb4-ce-1.0-dice-3.0-40k_chase-db1-128x128.py)    | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1/pspnet_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1_20211210_201823-c0802c4d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1/pspnet_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1_20211210_201823.log.json)             |
| UNet + DeepLabV3 | UNet-S5-D16 | Cross Entropy        | 960x999    | 128x128   |  85x85 | 40000   | 0.999    |              - | V100   | 89.57 | 80.47 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/unet/unet_s5-d16_deeplabv3_4xb4-40k_chase-db1-128x128.py)                 | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_128x128_40k_chase_db1/deeplabv3_unet_s5-d16_128x128_40k_chase_db1_20201226_094047-4c5aefa3.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_128x128_40k_chase_db1/deeplabv3_unet_s5-d16_128x128_40k_chase_db1-20201226_094047.log.json)                                                                 |
| UNet + DeepLabV3 | UNet-S5-D16 | Cross Entropy + Dice | 960x999    | 128x128   |  85x85 | 40000   | 1.010    |              - | V100   | 89.49 | 80.37 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/unet/unet-s5-d16_deeplabv3_4xb4-ce-1.0-dice-3.0-40k_chase-db1-128x128.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1_20211210_201825-4ef29df5.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_128x128_40k_chase-db1_20211210_201825.log.json) |

### HRF

| Method           | Backbone    | Loss                 | Image Size | Crop Size |  Stride | Lr schd | Mem (GB) | Inf time (fps) | Device | mDice |  Dice | config                                                                                                                                      | download                                                                                                                                                                                                                                                                                                                                                                                                         |
| ---------------- | ----------- | -------------------- | ---------- | --------- | ------: | ------- | -------- | -------------: | ------ | ----: | ----: | ------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| UNet + FCN       | UNet-S5-D16 | Cross Entropy        | 2336x3504  | 256x256   | 170x170 | 40000   | 2.525    |              - | V100   | 88.92 | 79.45 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/unet/unet-s5-d16_fcn_4xb4-40k_hrf-256x256.py)                       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_256x256_40k_hrf/fcn_unet_s5-d16_256x256_40k_hrf_20201223_173724-d89cf1ed.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/unet_s5-d16_256x256_40k_hrf/unet_s5-d16_256x256_40k_hrf-20201223_173724.log.json)                                                                                                 |
| UNet + FCN       | UNet-S5-D16 | Cross Entropy + Dice | 2336x3504  | 256x256   | 170x170 | 40000   | 2.623    |              - | V100   | 89.64 | 80.87 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/unet/unet-s5-d16_fcn_4xb4-ce-1.0-dice-3.0-40k_hrf-256x256.py)       | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf/fcn_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf_20211210_201821-c314da8a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf/fcn_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf_20211210_201821.log.json)                         |
| UNet + PSPNet    | UNet-S5-D16 | Cross Entropy        | 2336x3504  | 256x256   | 170x170 | 40000   | 2.588    |              - | V100   | 89.24 | 80.07 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/unet/unet-s5-d16_pspnet_4xb4-40k_hrf-256x256.py)                    | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_256x256_40k_hrf/pspnet_unet_s5-d16_256x256_40k_hrf_20201227_181818-fdb7e29b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_256x256_40k_hrf/pspnet_unet_s5-d16_256x256_40k_hrf-20201227_181818.log.json)                                                                             |
| UNet + PSPNet    | UNet-S5-D16 | Cross Entropy + Dice | 2336x3504  | 256x256   | 170x170 | 40000   | 2.798    |              - | V100   | 89.69 | 80.96 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/unet/unet-s5-d16_pspnet_4xb4-ce-1.0-dice-3.0-40k_hrf-256x256.py)    | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf/pspnet_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf_20211210_201823-53d492fa.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf/pspnet_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf_20211210_201823.log.json)             |
| UNet + DeepLabV3 | UNet-S5-D16 | Cross Entropy        | 2336x3504  | 256x256   | 170x170 | 40000   | 2.604    |              - | V100   | 89.32 | 80.21 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/unet/unet-s5-d16_deeplabv3_4xb4-40k_hrf-256x256.py)                 | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_256x256_40k_hrf/deeplabv3_unet_s5-d16_256x256_40k_hrf_20201226_094047-3a1fdf85.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_256x256_40k_hrf/deeplabv3_unet_s5-d16_256x256_40k_hrf-20201226_094047.log.json)                                                                 |
| UNet + DeepLabV3 | UNet-S5-D16 | Cross Entropy + Dice | 2336x3504  | 256x256   | 170x170 | 40000   | 2.607    |              - | V100   | 89.56 | 80.71 | [config](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/unet/unet-s5-d16_deeplabv3_4xb4-ce-1.0-dice-3.0-40k_hrf-256x256.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf_20211210_202032-59daf7a4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf/deeplabv3_unet_s5-d16_ce-1.0-dice-3.0_256x256_40k_hrf_20211210_202032.log.json) |

Note:

- In  `DRIVE`, `STARE`, `CHASE_DB1`, and `HRF` dataset, `mDice` is mean dice of background and vessel, while `Dice` is dice metric of vessel(foreground) only.

## Citation

```bibtex
@inproceedings{ronneberger2015u,
  title={U-net: Convolutional networks for biomedical image segmentation},
  author={Ronneberger, Olaf and Fischer, Philipp and Brox, Thomas},
  booktitle={International Conference on Medical image computing and computer-assisted intervention},
  pages={234--241},
  year={2015},
  organization={Springer}
}
```