-
Notifications
You must be signed in to change notification settings - Fork 36
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
Saved Checkpoint Error #8
Comments
I have the same problem. I got how to run the trainer.py, checking some mistakes due to python version. However, I am not able to find where is the file 'models/MultiObjDetTracker-CHKPNT-03-0.55.hdf5'. Can you help me? |
I think that we have to train it from scratch by setting LOAD_MODEL in MultiObjDetTracker to False. |
When I got the hdf5 files saved, I tried to predict on 4 images using the prdict() in MultiObjDetTracker. The classes predicted were found to be empty and as well as the bounding boxes. When I tried to view the hdf5 files stored using pandas, they were found to be empty as well. May I know what might be casuing this issue? |
Did you train the model? |
I assumed that the model was already trained. Do you know how to perform the training with this files? |
I did what you mentioned above, but now I have other issues. In MultiObjTrack.py I am not able to find the .pickle files required to train the model. They are expected to belong to MOT dataset. Did you find them? |
I cannot find this file: data/MultiObjDetTracker_MOT17_TrainAnn.pickle |
Where can I find the 'models/MultiObjDetTracker-CHKPNT-03-0.55.hdf5'??
The text was updated successfully, but these errors were encountered: