Marco Boaretto

I was able to fix this. by using image = tf.to_float(image)

Well, does you dataset has images of the whole field while the camera is not near to the player? It might be because your object size will change depending on...

@hkhaledmohamed Yes, you can do that as is suggested in [here](https://github.com/experiencor/keras-yolo2/issues/246) for the racoon problem. The model must learn what is and what is not the object that it will...

Yes, However [there](https://github.com/rodrigo2019/keras_yolo2) is a version of this code that is already compatible with python3.

@wizephen @guysoft I think what you guys are looking for, can be found in here: https://github.com/rodrigo2019/keras_yolo2/releases/tag/pre-trained-weights

@zenetio I think all images are already normalized according to its respective feature extractor as can be seen in the frontend.py [here](https://github.com/experiencor/keras-yolo2/blob/4e8c85ce02435f136d4f4cfe930b4ccb759fbaf8/frontend.py#L286). @dr-askar have you tried raising the values of...