New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Invalid Argument error for train_shapes.ipynb #265
Comments
I'm also running into this issue. I'll try and debug it tonight/tomorrow. |
I think its related to #211 |
Somehow we're getting more Scores than we are anchors. ... which seems to be impossible, so there may be a mismatch in combining some things somehow. |
Are you using the default ResNet-101 with FPN structure? If so, you have a mismatch in the number of elements between RPN_ANCHOR_SCALES and BACKBONE_STRIDES. Also, you have RPN_ANCHOR_SCALES defined twice. In general, if you are using ResNet-101 with FPN and taking the C4 backbone, there are 5 levels in the FPN. Thus, you should have 5 elements in RPN_ANCHOR_SCALES and 5 elements in BACKBONE_STRIDES. |
When i run the train_shapes.ipynb, I met the result is that FileNotFoundError: [Errno 2] Could not find weight files in /home/ubuntu66/logs/shapes20181007T1338. How can i solve this problem? |
did anybody fix this issue? |
running train_shapes with the following config on a machine with
CPU
only:and and training with
layers='heads'
:generates the following
InvalidArgumentError
:The text was updated successfully, but these errors were encountered: