Closed leonel11 closed 4 years ago
This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.
Did you find any solution, i also got same error
Unfortunately, not. This problem was given when I tried to fit the model with flag keep_images_without_gt=True. But everything was OK with flag keep_images_without_gt=False
Yes I also have make the flag False,seems like the codes will not work if there are no bounding box(ground truth) in images
This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.
Hello! Thank you very much for the code. When I tried to train SSD300 detector based on VGG16 I got the error
TypeError: __call__() missing 1 required positional argument: 'labels'
. It happened on the stage of callingfit_generator
when I wanted to fit the model. How can I solve it? May this problem be caused by possible errors in datasets? The fact is that I tried to fit the model on my own data.