Prediction and ground truth boxes bound whole image? about ssd_keras HOT 3 CLOSED

10 epochs is not remotely enough. The reason why decode_y2() with the default parameters is giving you an empty prediction list is because there simply aren't any good predictions yet. As mentioned in the README, you need to train for at least 20,000 steps (something in that ballpark) until the model starts to make any half-decent predictions. Try to relax the early stopping parameters so the model doesn't stop training so quickly.

I don't quite understand what you mean by "I get the image with both ground truth and prediction boxes bounding the whole images".

from ssd_keras.

Thanks for the quick response!I am training it now and I think it should solve the box issue

from ssd_keras.

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.

from ssd_keras.