Image_Segmentation

Image_Segmentation copied to clipboard

Thank you for sharing your amazing code; the "length" variable in the solver is the total data size, how in the evaluation.py ,the acc and othor metrics is calculated base...

ponykid

tuple index out of range

2

I got "tuple index out of range" with the Attention Unet.

mengluchu

the segmentsation result is transformed to the binary , I think maybe we should use the sigmoid result ,not the binary result

ponykid

SE: 0.0000, SP: 0.0000, PC: 0.0000, F1: 0.0000, JS: 0.0000, DC: 0.0000

9

hello: Since I don't have a GPU, I reduced the number of pictures and the number of iterations.But the result shows 'SE: 0.0000, SP: 0.0000, PC: 0.0000, F1: 0.0000, JS:...

wjj001-dl

Hello,i want to train a multi-class task,What needs to be changed,such as Loss and so on Thank you~

CC-Xiaoyu

Low performance when i train

3

Thanks for sharing useful project I have a question about the score in this repo I had prepared the data ISIC same yours. > 1815 images were used for training,...

tranquangchung

Correction of evaluation metric

2

tested on pytorch==1.2.0 ISIC 2018 dataset first loop result[All default]: Epoch [1/150], Loss: 570.2478, [Training] Acc: 0.8824, SE: 0.7623, SP: 0.9695, PC: 0.7704, F1: 0.6987, JS: 0.5823, DC: 0.6987 [Validation]...

MELSunny

Me encantó

Wendernet927

> hey guys. use pytorch<=1.2.0 (not confirmed) or change the funtion in "evaluation" to fit the calculation of **bool tensor** will sovle the problem

1

> hey guys. use pytorch e.g. change "TP = ((SR==1)+(GT==1))==2" to "TP = SR & GT" thanks, i try it now, and do you have some recommend with pytorch >...

rouchoo

Unstable performances in validation set and prediction collapse

9

Hi everyone, many thanks to @LeeJunHyun for the awesome implementations. I'm using this repo to segment medical grayscale images on a private dataset. I have a problem in the training...

frmrz