YOLOv3_TensorFlow icon indicating copy to clipboard operation
YOLOv3_TensorFlow copied to clipboard

something wrong with gradient cliping

Open bitgs opened this issue 5 years ago • 0 comments

This gradient cliping sentence seems wrong. clip_grad_var = [gv if gv[0] is None else [tf.clip_by_norm(gv[0], 100.), gv[1]] for gv in gvs]

when gv[0]==0, gv[0] should be clipped. But here, you will do nothing.

bitgs avatar Dec 23 '19 02:12 bitgs