semantic-segmentation-pytorch

semantic-segmentation-pytorch copied to clipboard

pickle.UnpicklingError: invalid load key, '<'.

5

Hi I run into this error with your suggested environment: `pickle.UnpicklingError: invalid load key, '

meteorshowers

Is there any way I can test using CPU

8

Several issues here. After I torch.cuda.set_device(-1) segmentation_module.cuda() and test(segmentation_module, loader_test, -1) do not perform well. Is there any way I can test using CPU?

Songloading

Unable to train

3

solodova

It's stuck in this place when it's running：iterator_train = iter(loader_train)

Chang-007

alisoviy

Hello, In the file models.py, L364, class C1(nn.Module), I am trying to extract ft. I modified by adding a line ft = x, after the L375. Is it the right...

ShravanthiPatil

Hi! Could you recommend which model(s) perform best at small/tiny object segmentation?

RylanSchaeffer

Issues with link for pretrained models

5

Hi, Thanks for making this interesting work available. I am trying to test some of your pre-trained models but all links I can find to http://sceneparsing.csail.mit.edu are dead. Would it...

ThorJonsson

I made custom dataset that has 3 classes. And, I trained hrnet model with pretrained weights. `python train.py --gpus 0,1,2 --cfg config/ade20k-hrnetv2.yaml` Then, I validated a one image used training....

yes89929

How to get learning rate to decrease more slowly?

1

How should I change the value of lr_pow in order to make my learning rate decrease more slowly. Currently the lr_pow is at a default value of 0.9.

yajain