Hi:
你好,python train.py 时会报梯度出错的问题; "File "train.py", line 171, in
callbacks = [checkpoint, earlystop, changelr, tensorboard])
" " raise ValueError('An operation has None for gradient. '
ValueError: An operation has None for gradient. Please make sure that all of your ops have a gradient defined (i.e. are differentiable). Common ops without gradient: K.argmax, K.round, K.eval. 我的tensorflow1.13.1版本 数据用的你提供的
Hi: 你好,python train.py 时会报梯度出错的问题; "File "train.py", line 171, in
callbacks = [checkpoint, earlystop, changelr, tensorboard])
" " raise ValueError('An operation has
None
for gradient. ' ValueError: An operation hasNone
for gradient. Please make sure that all of your ops have a gradient defined (i.e. are differentiable). Common ops without gradient: K.argmax, K.round, K.eval. 我的tensorflow1.13.1版本 数据用的你提供的