Problèmes rencontrés lors de l'exécution de SiamMask

Les problèmes rencontrés:

THCudaCheck FAIL file=/pytorch/aten/src/THC/THCGeneral.cpp line=663 error=11 : invalid argument
Traceback (most recent call last):
  File "../../tools/demo.py", line 53, in <module>
    state = siamese_init(im, target_pos, target_sz, siammask, cfg['hp'], device=device)  # init tracker
  File "/home/pwh/SIAMMASK/SiamMask/tools/test.py", line 155, in siamese_init
    net.template(z.to(device))
  File "/home/pwh/SIAMMASK/SiamMask/experiments/siammask_sharp/custom.py", line 174, in template
    self.zf = self.features(template)
  File "/home/pwh/.conda/envs/siammask/lib/python3.6/site-packages/torch/nn/modules/module.py", line 477, in __call__
    result = self.forward(*input, **kwargs)
  File "/home/pwh/SIAMMASK/SiamMask/experiments/siammask_sharp/custom.py", line 59, in forward
    output = self.features(x)
  File "/home/pwh/.conda/envs/siammask/lib/python3.6/site-packages/torch/nn/modules/module.py", line 477, in __call__
    result = self.forward(*input, **kwargs)
  File "/home/pwh/SIAMMASK/SiamMask/experiments/siammask_sharp/resnet.py", line 218, in forward
    x = self.conv1(x)
  File "/home/pwh/.conda/envs/siammask/lib/python3.6/site-packages/torch/nn/modules/module.py", line 477, in __call__
    result = self.forward(*input, **kwargs)
  File "/home/pwh/.conda/envs/siammask/lib/python3.6/site-packages/torch/nn/modules/conv.py", line 301, in forward
    self.padding, self.dilation, self.groups)
RuntimeError: cuda runtime error (11) : invalid argument at /pytorch/aten/src/THC/THCGeneral.cpp:663

Solution:

La principale raison de ce problème est que la version de la torche ne lui correspond pas, la pip install -r requirment.txtversion de la torche a été téléchargée à l' origine 0.4.0
. Il peut donc pip install -U torchêtre mis à jour (mais il vaut mieux spécifier la version correspondant à la version cuda de votre propre système). Il faut noter ici que 2021年torch版本已经更新到1.8，si vous entrez directement la commande ci-dessus, torch sera mis à jour vers la version 1.8, donc j'ai rencontré l'erreur suivante:

Traceback (most recent call last):
  File "../../tools/demo.py", line 53, in <module>
    state = siamese_init(im, target_pos, target_sz, siammask, cfg['hp'], device=device)  # init tracker
  File "/home/pwh/SIAMMASK/SiamMask/tools/test.py", line 155, in siamese_init
    net.template(z.to(device))
  File "/home/pwh/SIAMMASK/SiamMask/experiments/siammask_sharp/custom.py", line 174, in template
    self.zf = self.features(template)
  File "/home/pwh/.conda/envs/siammask/lib/python3.6/site-packages/torch/nn/modules/module.py", line 889, in _call_impl
    result = self.forward(*input, **kwargs)
  File "/home/pwh/SIAMMASK/SiamMask/experiments/siammask_sharp/custom.py", line 59, in forward
    output = self.features(x)
  File "/home/pwh/.conda/envs/siammask/lib/python3.6/site-packages/torch/nn/modules/module.py", line 889, in _call_impl
    result = self.forward(*input, **kwargs)
  File "/home/pwh/SIAMMASK/SiamMask/experiments/siammask_sharp/resnet.py", line 218, in forward
    x = self.conv1(x)
  File "/home/pwh/.conda/envs/siammask/lib/python3.6/site-packages/torch/nn/modules/module.py", line 889, in _call_impl
    result = self.forward(*input, **kwargs)
  File "/home/pwh/.conda/envs/siammask/lib/python3.6/site-packages/torch/nn/modules/conv.py", line 399, in forward
    return self._conv_forward(input, self.weight, self.bias)
  File "/home/pwh/.conda/envs/siammask/lib/python3.6/site-packages/torch/nn/modules/conv.py", line 396, in _conv_forward
    self.padding, self.dilation, self.groups)
RuntimeError: cuDNN error: CUDNN_STATUS_NOT_INITIALIZED

Cela est dû cuda、cudnn、pytorchà la version incompatible, j'ai donc désinstallé la version 1.8 de torch et choisi la version 1.7 de torch. La commande est la suivante :,
pip install -i https://pypi.douban.com/simple/ torch==1.7le problème est résolu avec succès après la mise à jour.