wizyoung / YOLOv3_TensorFlow

Complete YOLO v3 TensorFlow implementation. Support training on your own dataset.
MIT License
1.55k stars 580 forks source link

something wrong with gradient cliping #197

Open bitgs opened 4 years ago

bitgs commented 4 years ago

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.