TorchSemiSeg

TorchSemiSeg copied to clipboard

Config file of few supervision.

5

It is a very nice work. Thank you so much for your contribution. Is it possible to release scripts for few-supervision on PASCAL VOC 2012, too?

Huiimin5

The performance of default voc8.res50v3+.CPS

3

Hello, I'm training with double 3080 cards. The batchsize can only be set to 4. The learning rate is 0.0025. The ratio of 1 / 8. I've run it three...

swt199211

In Figure 3 in the paper, there's a comparison of fully supervised baselines. How to reproduce these results (especially with HRNet)?

DominikFilipiak

Question about the crop size

3

Thx for your marvelous work! When I was trying to reproduce your work in voc2012 dataset, I felt strange about the size of inputting images after cropping operation, should it...

revaeb

docker error

1

 When I use your docker to train,the error occured,it is likely that the version of cuda driver is too low.But my cuda driver is 465.19.01,which is supported CUDA11.3,the cuda...

ruichen0319

code running error

1

When I train CPS on cityscapes , the code reports errors and interrupts from time to time. Did this happen to you? how to solve? Thanks The error is as...

lily-wei0211

cutmix question

1

Does the cutmix of unlabeled data mix the same image using mask_params? Or, are the other two images mixed by mask_params?

DeepHM

Dear author, i have some question about your work. In your paper, networks have different their init weight. > The two networks have the same structure and their weights, i.e.,...

kirk0221

Hi, I'm facing some conflict issues when trying to install the environment and was wondering if there was anything I could do to resolve the conflicts. I'm in a Linux...

asmakhans

training with one GPU

4

excuse me,i want to know how to train with only one GPU, can you help me? thanks a lot.

wo0423