File "/home/mona/venv/torchenc/lib/python3.8/site-packages/torch/cuda/__init__.py", line 172, in _lazy_init torch._C._cuda_init() RuntimeError: CUDA unknown error - this may be due to an incorrectly set up environment, e.g. changing env variable CUDA_VISIBLE_DEVICES after program start. Setting the available devices to be zero. (torchenc) mona@goku:~$ echo $CUDA_VISIBLE_DEVICES

まず test_torch_encoding.py を実行し、モデルの .cuda() 呼び出し、CUDA の初期化警告、およびそれに伴う nvidia-smi の出力を確認します。失敗の原因が報告された環境にあるのか PyTorch-Encoding にあるのかを特定し、再現可能な原因と確認済みの解決策を記録してください。現時点で issue には、完了のためのプロジェクト変更やテストが定義されていません。

Could you please suggest how I should fix this problem?

(torchenc) mona@goku:~$ python test_torch_encoding.py 
/home/mona/venv/torchenc/lib/python3.8/site-packages/torch/cuda/__init__.py:52: UserWarning: CUDA initialization: CUDA unknown error - this may be due to an incorrectly set up environment, e.g. changing env variable CUDA_VISIBLE_DEVICES after program start. Setting the available devices to be zero. (Triggered internally at  /pytorch/c10/cuda/CUDAFunctions.cpp:100.)
  return torch._C._cuda_getDeviceCount() > 0
Traceback (most recent call last):
  File "test_torch_encoding.py", line 5, in <module>
    model = encoding.models.get_model('DeepLab_ResNeSt269_PContext', pretrained=True).cuda()
  File "/home/mona/venv/torchenc/lib/python3.8/site-packages/torch/nn/modules/module.py", line 463, in cuda
    return self._apply(lambda t: t.cuda(device))
  File "/home/mona/venv/torchenc/lib/python3.8/site-packages/torch/nn/modules/module.py", line 359, in _apply
    module._apply(fn)
  File "/home/mona/venv/torchenc/lib/python3.8/site-packages/torch/nn/modules/module.py", line 359, in _apply
    module._apply(fn)
  File "/home/mona/venv/torchenc/lib/python3.8/site-packages/torch/nn/modules/module.py", line 359, in _apply
    module._apply(fn)
  File "/home/mona/venv/torchenc/lib/python3.8/site-packages/torch/nn/modules/module.py", line 381, in _apply
    param_applied = fn(param)
  File "/home/mona/venv/torchenc/lib/python3.8/site-packages/torch/nn/modules/module.py", line 463, in <lambda>
    return self._apply(lambda t: t.cuda(device))
  File "/home/mona/venv/torchenc/lib/python3.8/site-packages/torch/cuda/__init__.py", line 172, in _lazy_init
    torch._C._cuda_init()
RuntimeError: CUDA unknown error - this may be due to an incorrectly set up environment, e.g. changing env variable CUDA_VISIBLE_DEVICES after program start. Setting the available devices to be zero.
(torchenc) mona@goku:~$ echo $CUDA_VISIBLE_DEVICES

(torchenc) mona@goku:~$ nvidia-smi
Sat Jan 30 00:44:47 2021       
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 460.32.03    Driver Version: 460.32.03    CUDA Version: 11.2     |
|-------------------------------+----------------------+----------------------+
| GPU  Name        Persistence-M| Bus-Id        Disp.A | Volatile Uncorr. ECC |
| Fan  Temp  Perf  Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |
|                               |                      |               MIG M. |
|===============================+======================+======================|
|   0  GeForce GTX 165...  Off  | 00000000:01:00.0 Off |                  N/A |
| N/A   47C    P8     3W /  N/A |   1695MiB /  3911MiB |      7%      Default |
|                               |                      |                  N/A |
+-------------------------------+----------------------+----------------------+
                                                                               
+-----------------------------------------------------------------------------+
| Processes:                                                                  |
|  GPU   GI   CI        PID   Type   Process name                  GPU Memory |
|        ID   ID                                                   Usage      |
|=============================================================================|
|    0   N/A  N/A      1155      G   /usr/lib/xorg/Xorg                133MiB |
|    0   N/A  N/A      1773      G   /usr/lib/xorg/Xorg               1124MiB |
|    0   N/A  N/A      1952      G   /usr/bin/gnome-shell              130MiB |
|    0   N/A  N/A      2329      G   ...gAAAAAAAAA --shared-files      167MiB |
|    0   N/A  N/A      2735      G   /usr/lib/firefox/firefox            3MiB |
|    0   N/A  N/A      2923      G   /usr/lib/firefox/firefox            1MiB |
|    0   N/A  N/A      3204      G   /usr/lib/firefox/firefox            1MiB |
|    0   N/A  N/A      3324      G   /usr/lib/firefox/firefox            1MiB |
|    0   N/A  N/A      3456      G   /usr/lib/firefox/firefox            1MiB |
|    0   N/A  N/A      3501      G   /usr/lib/firefox/firefox            1MiB |
|    0   N/A  N/A      3572      G   /usr/lib/firefox/firefox            1MiB |
|    0   N/A  N/A      3623      G   /usr/lib/firefox/firefox            3MiB |
|    0   N/A  N/A     21024      G   ...f_3837.log --shared-files       99MiB |
+-----------------------------------------------------------------------------+
(torchenc) mona@goku:~$ 

The code as in your Website:

import torch
import encoding

# Get the model
model = encoding.models.get_model('DeepLab_ResNeSt269_PContext', pretrained=True).cuda()
model.eval()

# Prepare the image
url = 'https://github.com/zhanghang1989/image-data/blob/master/' + \
      'encoding/segmentation/pcontext/2010_001829_org.jpg?raw=true'
filename = 'example.jpg'
img = encoding.utils.load_image(encoding.utils.download(url, filename)).cuda().unsqueeze(0)

# Make prediction
output = model.evaluate(img)
predict = torch.max(output, 1)[1].cpu().numpy() + 1

# Get color pallete for visualization
mask = encoding.utils.get_mask_pallete(predict, 'pascal_voc')
mask.save('output.png')