The code breakdown at the xdxd_inferer(inf_df) step with RuntimeError: CUDA error: no kernel image is available for execution on the device, the image that inference is being run on is from the solaris tutorial.
Buggy behavior and/or error message
Error traceback pasted below
---------------------------------------------------------------------------
RuntimeError Traceback (most recent call last)
<ipython-input-8-ac434f9ac605> in <module>()
5 print('dataset loaded. Running inference on the image.')
6 start_time = time.time()
----> 7 xdxd_inferer(inf_df)
8 end_time = time.time()
9 print('running inference on one image took {} seconds'.format(end_time-start_time))
/home/user_name/miniconda3/envs/solaris_cpu/lib/python3.7/site-packages/solaris/nets/infer.py in __call__(self, infer_df)
99 infer_df[i].iloc[idx].to(device))
100
--> 101 subarr_preds = self.model(inf_input)
102 subarr_preds = subarr_preds.cpu().data.numpy()
103 stitched_result = stitch_images(subarr_preds,
/home/user_name/miniconda3/envs/solaris_cpu/lib/python3.7/site-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs)
725 result = self._slow_forward(*input, **kwargs)
726 else:
--> 727 result = self.forward(*input, **kwargs)
728 for hook in itertools.chain(
729 _global_forward_hooks.values(),
/home/user_name/miniconda3/envs/solaris_cpu/lib/python3.7/site-packages/solaris/nets/zoo/xdxd_sn4.py in forward(self, x)
40
41 def forward(self, x):
---> 42 conv1 = self.conv1(x)
43 conv2 = self.conv2(self.pool(conv1))
44 conv3 = self.conv3(self.pool(conv2))
/home/user_name/miniconda3/envs/solaris_cpu/lib/python3.7/site-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs)
725 result = self._slow_forward(*input, **kwargs)
726 else:
--> 727 result = self.forward(*input, **kwargs)
728 for hook in itertools.chain(
729 _global_forward_hooks.values(),
/home/user_name/miniconda3/envs/solaris_cpu/lib/python3.7/site-packages/torch/nn/modules/container.py in forward(self, input)
115 def forward(self, input):
116 for module in self:
--> 117 input = module(input)
118 return input
119
/home/user_name/miniconda3/envs/solaris_cpu/lib/python3.7/site-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs)
725 result = self._slow_forward(*input, **kwargs)
726 else:
--> 727 result = self.forward(*input, **kwargs)
728 for hook in itertools.chain(
729 _global_forward_hooks.values(),
/home/user_name/miniconda3/envs/solaris_cpu/lib/python3.7/site-packages/torch/nn/modules/conv.py in forward(self, input)
421
422 def forward(self, input: Tensor) -> Tensor:
--> 423 return self._conv_forward(input, self.weight)
424
425 class Conv3d(_ConvNd):
/home/user_name/miniconda3/envs/solaris_cpu/lib/python3.7/site-packages/torch/nn/modules/conv.py in _conv_forward(self, input, weight)
418 _pair(0), self.dilation, self.groups)
419 return F.conv2d(input, weight, self.bias, self.stride,
--> 420 self.padding, self.dilation, self.groups)
421
422 def forward(self, input: Tensor) -> Tensor:
RuntimeError: CUDA error: no kernel image is available for execution on the device
Expected behavior
To run inference on the image specified in inf_df
Environment information
OS: CentOS Linux Version 7
environment generated using environment.yml in solaris repo
Thank you for helping us improve
solaris
!Summary of the bug
Gets a CUDA error when running xdxd_inferer from solaris_tutorials
Steps to reproduce the bug
Please either paste sample code used to generate the buggy behavior below, or provide step-by-step instructions to reproduce the problem.
The code breakdown at the xdxd_inferer(inf_df) step with RuntimeError: CUDA error: no kernel image is available for execution on the device, the image that inference is being run on is from the solaris tutorial.
Buggy behavior and/or error message
Error traceback pasted below
Expected behavior
To run inference on the image specified in inf_df
Environment information