-
Notifications
You must be signed in to change notification settings - Fork 34
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
How to print the output of the wrong prediction of validation dataset? #19
Comments
You may refer to the code here to compare the output (prediction) and the target (ground truth). Lines 238 to 242 in 09bb641
|
And if I want to get the dir with the prediction , ? |
To get the path of the images, you may refer to TokenLabeling/generate_label.py Lines 110 to 128 in 09bb641
|
Is there no test.py to inference? |
You can use this colab notebook for inference. It uses VOLO model, but you can simply change the model by |
~/.local/lib/python3.7/site-packages/tlt/utils/utils.py in load_pretrained_weights(model, checkpoint_path, use_ema, strict, num_classes) ~/.local/lib/python3.7/site-packages/torch/nn/modules/module.py in load_state_dict(self, state_dict, strict) RuntimeError: Error(s) in loading state_dict for LV_ViT: |
Please use the latest version of our repo. (pip install tlt==0.2.0) |
|
If the number of classes is not 1000, you should also pass |
It does work, thank you |
No description provided.
The text was updated successfully, but these errors were encountered: