mmsegmentation/configs/unet

U-Net: Convolutional Networks for Biomedical Image Segmentation

Introduction

@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}
}

Results and models

DRIVE

Backbone	Head	Image Size	Crop Size	Stride	Lr schd	Mem (GB)	Inf time (fps)	Dice	config	download
UNet-S5-D16	FCN	584x565	64x64	42x42	40000	0.680	-	78.67	config	model | log
UNet-S5-D16	PSPNet	584x565	64x64	42x42	40000	0.599	-	78.62	config	model | log
UNet-S5-D16	DeepLabV3	584x565	64x64	42x42	40000	0.596	-	78.69	config	model | log

STARE

Backbone	Head	Image Size	Crop Size	Stride	Lr schd	Mem (GB)	Inf time (fps)	Dice	config	download
UNet-S5-D16	FCN	605x700	128x128	85x85	40000	0.968	-	81.02	config	model | log
UNet-S5-D16	PSPNet	605x700	128x128	85x85	40000	0.982	-	81.22	config	model | log
UNet-S5-D16	DeepLabV3	605x700	128x128	85x85	40000	0.999	-	80.93	config	model | log

CHASE_DB1

Backbone	Head	Image Size	Crop Size	Stride	Lr schd	Mem (GB)	Inf time (fps)	Dice	config	download
UNet-S5-D16	FCN	960x999	128x128	85x85	40000	0.968	-	80.24	config	model | log
UNet-S5-D16	PSPNet	960x999	128x128	85x85	40000	0.982	-	80.36	config	model | log
UNet-S5-D16	DeepLabV3	960x999	128x128	85x85	40000	0.999	-	80.47	config	model | log

HRF

Backbone	Head	Image Size	Crop Size	Stride	Lr schd	Mem (GB)	Inf time (fps)	Dice	config	download
UNet-S5-D16	FCN	2336x3504	256x256	170x170	40000	2.525	-	79.45	config	model | log
UNet-S5-D16	PSPNet	2336x3504	256x256	170x170	40000	2.588	-	80.07	config	model | log
UNet-S5-D16	DeepLabV3	2336x3504	256x256	170x170	40000	2.604	-	80.21	config	model | log