Ginbor
Results
2
comments of
Ginbor
you can switch off the "get_different_scale" function in dataset.py line 63 OR you can set the the input image size (608, 416 ... ) before starting a new epoch, line...
in my case, the problem disappeared when I didn't use savemodel() function. I suppose that the problem appears after cur_model.save_weights(). also in my case i have train dataset that len(train_dataset)%batch_size...