semantic-segmentation-pytorch

semantic-segmentation-pytorch copied to clipboard

I prepared custom dataset that 7000 images has only floor class and added to ade20k dataset. Now i have dataset with 28000 images. I changed floor annotations color with #040404...

Muratoter

unable to save the model in torchscript format

2

Hi team, Firstly, thanks for your repository. I would like to save the model in torchscript module format rather than the traditional way. when I try to save the model...

IamExperimenting

Can I chnage the number of output classes?

2

Can I chnage the number of output classes? e.g. I Want to reduce the default 150 ouput classes to 10

GooDrYu

# :hammer_and_wrench: Proposed Refactor We have been developing [TorchMetrics](https://github.com/PyTorchLightning/metrics) to be a general-purpose metric and some domain-specific use-cases. In many cases, we have an exact mapping to scikit-learn with verification/testing...

Borda

Since the ADE 20K dataset contains both indoor and outdoor scenes, is is possible to train the ADE20K on only indoor scenes ? Is there any way to filter out...

debasmitdas

Using Single GPU

1

I encountered the issue below.  Is there any codes for implementing with single GPU? Thank you.

suesuekkim

RuntimeError: CUDA error: out of memory

12

I just use one image to test, but get the error below: File "test.py", line 203, in main(cfg, args.gpu) File "test.py", line 129, in main test(segmentation_module, loader_test, gpu) File "test.py",...

HLH13297997663

cant download the pretrained resnet18-imagenet.pth model?

2

something wrong with the url?

OberstWB

Why mIoU uses sum(intersect)/sum(union) instead of mean over IoU?

1

I found the mIoU evaluation codes here: https://github.com/CSAILVision/semantic-segmentation-pytorch/blob/8f27c9b97d2ca7c6e05333d5766d144bf7d8c31b/eval.py#L98 I am wondering what is the motivation of using `sum(intersect)/sum(union)` instead of the mean over sample-wise `intersect / union`? The former one...

hubert0527

hi everyone do you know how can I see the layers and parameters of this network? I use torchsumary but I don't know where should I put summary to see...

ranch-hands