-
Notifications
You must be signed in to change notification settings - Fork 10
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
Run evaluation only? #37
Comments
Please refer to this issue for the evaluation script #2. |
Thank you very much for your response. I am having some difficulty determining which data were used for the query/test images during meta-learning and meta-testing on the VOC dataset (i.e., the results reported in the top part of table 5 in the paper). I have performed the data preparation steps as instructed in the README file. I see files in |
Thank you for your interest in our work. You can find the dataset 'voc_2007_test_all1' here (https://github.com/GuangxingHan/Meta-Faster-R-CNN/blob/main/meta_faster_rcnn/data/datasets/builtin.py#L79) |
Thank you very much for your response. After preparing the data following the instructions, there seem to be files that contain the necessary information about the few-shot training examples. For example, the file |
Is there a way to run the model in evaluation mode only using the meta-trained model provided in the 'Model Zoo' section? The instructions in the readme only describe how to train the model from scratch. I am specifically interested in performing the evaluation for the VOC dataset.
The text was updated successfully, but these errors were encountered: