CascadeTabNet
CascadeTabNet copied to clipboard
DevashishPrasad
Error when run main.py in Table Structure Recognition
environment: ubuntu 18.04 python==3.6 pytorch==1.4.0 torchvision==0.5.0 cudatoolkit=10.1 Config: cascade_mask_rcnn_hrnetv2p_w32_20e.py checkpoint: epoch_24.pth
When I run 'python main.py', folloing error pops up.
/home/vesper/anaconda3/envs/py36/lib/python3.6/site-packages/torch/nn/functional.py:2506: UserWarning: Default upsampling behavior when mode=bilinear is changed to align_corners=False since 0.4.0. Please specify align_corners=True if the old behavior is desired. See the documentation of nn.Upsample for details. "See the documentation of nn.Upsample for details.".format(mode))
I have a similar issue:
/usr/local/lib/python3.6/dist-packages/torch/nn/functional.py:2506: UserWarning: Default upsampling behavior when mode=bilinear is changed to align_corners=False since 0.4.0. Please specify align_corners=True if the old behavior is desired. See the documentation of nn.Upsample for details.
"See the documentation of nn.Upsample for details.".format(mode))
Did you get a chance to solve it?
I have a similar issue:
/usr/local/lib/python3.6/dist-packages/torch/nn/functional.py:2506: UserWarning: Default upsampling behavior when mode=bilinear is changed to align_corners=False since 0.4.0. Please specify align_corners=True if the old behavior is desired. See the documentation of nn.Upsample for details.
"See the documentation of nn.Upsample for details.".format(mode))
Did you get a chance to solve it?
No :( Please let me know if you figured out how to fix it.
Replace all cv2.imshow with cv2_imshow but with only one arg which is the image, don't forget to import "from google.colab.patches import cv2_imshow" .
delete all cv2.waitKey(0).
Hopefully, it will work.
But unfortunately, the results don't match what represented in the repo.
Replace all cv2.imshow with cv2_imshow but with only one arg which is the image, don't forget to import "from google.colab.patches import cv2_imshow" .
delete all cv2.waitKey(0).
Hopefully, it will work.
But unfortunately, the results don't match what represented in the repo.
But I'm not using colab. I'm using PC.