Hi all,
I tried to use the model trained from pascal multi notebook to predict my images (learn.predict(is_test=True)), but I am not sure why I only got the first output of classes but not the second output for bounding box. I am not sure if I miss something here. Any help would be appreciated. Thanks a lot!
('output_shape', [[-1, 189, 21], [-1, 189, 4]])