Xingyi Yang

It seems that you do not have the validation dataset. Is it right?

yes

one drawback of this implementation is that the loss can not reach 0 due to l2 regularization. You should check your threshold and the data format.

you should try a smaller score_threshold(0.1 or 0.01 for example) to see if there is any result

what's your learning rate,batch size,input size?

do you train when some layers are freezing？You should unfreeze all the layers when training.

You should train without frozen layers, so the change the code to 'False' in the frozen part ` **if False:** model.compile(optimizer=Adam(lr=1e-3), loss={ # use custom yolo_loss Lambda layer. 'yolo_loss': lambda...

I am not pretty sure about the reason about the bad performance, but keras implementation has such fault that the loss cannot be as low as darknet implementation. A higher...

2 times faster than darknet53. On a keras-yolov3 416x416 image,40+ frames per second.

i did not met this question.Did you use the correct format of anchor.txt?