-
Notifications
You must be signed in to change notification settings - Fork 114
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
KeyError: 'roi_fmap.0.weight' in train_models_sgcls.sh #60
Comments
I think the problem is that you have a checkpoint for the sgcls model that you're treating like a detector checkpoint. If you download the provided detector checkpoint that should work! |
@rowanz |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Hey there,
I came across a problem similar to this #41 ,when I did the command
bash train_models_sgcls.sh
, I got the error message listed later.I renamed the downloaded file
vgrel-motifnet-sgcls.tar
tovg-24.tar
, and put it in the correct folder. Its size is1.7 GB (1,676,245,156 bytes).
Besides, both
pretrain_detector
andrefine_for_detection
run well.I guess the main problem lies in ckpt , but I have no idea what to do later.
Error Message
(neural_motifs) nopanic@ghostInSh3ll:/media/nopanic/DATA/AnExperiment/NeuralMotifs/neural-motifs-master/scripts$ bash train_models_sgcls.sh
TRAINING THE BASELINE
The text was updated successfully, but these errors were encountered: