You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hello,
I'm running the software on CPU by modifying _config.yaml as you documented in another issue.
After drawing a mask and processing some projections, I want to edit facial features and in order to do that I create a new attribute with the down-pointing arrows and then I click on "S Edit" but as soon as I do that I receive the following error message:
File "...\Chunkmogrify-master\torch_utils\ops\conv2d_gradfix.py", line 43, in conv_transpose2d
return torch.nn.functional.conv_transpose2d(input=input, weight=weight, bias=bias, stride=stride, padding=padding, output_padding=output_padding, groups=groups, dilation=dilation)
RuntimeError: "slow_conv_transpose2d_out_cpu" not implemented for 'Half'
The text was updated successfully, but these errors were encountered:
Fixed by forcing fp32 for running on cpu. I've tested running on cpu and didn't find any more issues after commit 16d2ce6. Let me know if you find any other problems!
Hello,
I'm running the software on CPU by modifying _config.yaml as you documented in another issue.
After drawing a mask and processing some projections, I want to edit facial features and in order to do that I create a new attribute with the down-pointing arrows and then I click on "S Edit" but as soon as I do that I receive the following error message:
The text was updated successfully, but these errors were encountered: