Configuration issues
frogM opened this issue · 0 comments
frogM commented
We have some issues when training FCN8s:
- The error "Torch.floattensor: object does not support indexing" occurs when the code runs to "writer.add_image(snapshot_name, val_visual)" in line 190, file "train.py". Our configuration is python 2.7, pytorch 0.2.0.
- According to your setup instructions, we should install tensorboardX, however, your source code uses tensorboard. Which one should I use?
- We want to know if the code can run on GPU.
Thank you very much!