rodrigo2019
commented
3 years ago it is because in the older versions of the repo, we aplied some tf.print() lines in the loss function method. I will fix that, thank you
Closed 459below closed 3 years ago
rodrigo2019
commented
3 years ago it is because in the older versions of the repo, we aplied some tf.print() lines in the loss function method. I will fix that, thank you
https://github.com/rodrigo2019/keras_yolo2/blob/3ed7a365ceb2b8e473e0865cd7e4023325b5c360/keras_yolov2/frontend.py#L216
To my knowledge the verbose parameter in Keras is pretty confusing since it does not behave as one is used to. Higher doesn't seem to mean "more verbose" in this case. If debugging I'm quite sure that it should be verbose=1 instead of verbose=2.
According to documentation
verbose | 0, 1, or 2. Verbosity mode. 0 = silent, 1 = progress bar, 2 = one line per epoch. Note that the progress bar is not particularly useful when logged to a file, so verbose=2 is recommended when not running interactively (eg, in a production environment).