Я только что получил это сообщение при попытке запустить прямую подачу torch.nn.Conv2d, получая следующую трассировку стека:
---------------------------------------------------------------------------
RuntimeError Traceback (most recent call last)
<ipython-input-26-04bd4a00565d> in <module>
3
4 # call training function
----> 5 losses = train(D, G, n_epochs=n_epochs)
<ipython-input-24-b539315e0aa0> in train(D, G, n_epochs, print_every)
46 real_images = real_images.cuda()
47
---> 48 D_real = D(real_images)
49 d_real_loss = real_loss(D_real, True) # smoothing label 1 => 0.9
50
~/anaconda3/lib/python3.7/site-packages/torch/nn/modules/module.py in __call__(self, *input, **kwargs)
548 result = self._slow_forward(*input, **kwargs)
549 else:
--> 550 result = self.forward(*input, **kwargs)
551 for hook in self._forward_hooks.values():
552 hook_result = hook(self, input, result)
<ipython-input-14-bf68e57c25ff> in forward(self, x)
48 """
49
---> 50 x = self.leaky_relu(self.conv1(x))
51 x = self.leaky_relu(self.conv2(x))
52 x = self.leaky_relu(self.conv3(x))
~/anaconda3/lib/python3.7/site-packages/torch/nn/modules/module.py in __call__(self, *input, **kwargs)
548 result = self._slow_forward(*input, **kwargs)
549 else:
--> 550 result = self.forward(*input, **kwargs)
551 for hook in self._forward_hooks.values():
552 hook_result = hook(self, input, result)
~/anaconda3/lib/python3.7/site-packages/torch/nn/modules/container.py in forward(self, input)
98 def forward(self, input):
99 for module in self:
--> 100 input = module(input)
101 return input
102
~/anaconda3/lib/python3.7/site-packages/torch/nn/modules/module.py in __call__(self, *input, **kwargs)
548 result = self._slow_forward(*input, **kwargs)
549 else:
--> 550 result = self.forward(*input, **kwargs)
551 for hook in self._forward_hooks.values():
552 hook_result = hook(self, input, result)
~/anaconda3/lib/python3.7/site-packages/torch/nn/modules/conv.py in forward(self, input)
347
348 def forward(self, input):
--> 349 return self._conv_forward(input, self.weight)
350
351 class Conv3d(_ConvNd):
~/anaconda3/lib/python3.7/site-packages/torch/nn/modules/conv.py in _conv_forward(self, input, weight)
344 _pair(0), self.dilation, self.groups)
345 return F.conv2d(input, weight, self.bias, self.stride,
--> 346 self.padding, self.dilation, self.groups)
347
348 def forward(self, input):
RuntimeError: Unable to find a valid cuDNN algorithm to run convolution
Запуск показа nvidia-smi:
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 440.33.01 Driver Version: 440.33.01 CUDA Version: 10.2 |
|-------------------------------+----------------------+----------------------+
| GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. |
|===============================+======================+======================|
| 0 GeForce GTX 770 On | 00000000:01:00.0 N/A | N/A |
| 38% 50C P8 N/A / N/A | 624MiB / 4034MiB | N/A Default |
+-------------------------------+----------------------+----------------------+
+-----------------------------------------------------------------------------+
| Processes: GPU Memory |
| GPU PID Type Process name Usage |
|=============================================================================|
| 0 Not Supported |
+-----------------------------------------------------------------------------+
Я использую Python 3.7, Pytorch 1.5, а графический процессор - Nvidia GeForce GTX 770, работающий на Ubuntu 18.04.2. Я не нашел это сообщение об ошибке нигде. Звонит ли он в колокол?
1008 * Большое спасибо заранее.