facenet 用自己的数据和预训练模型重新训练train

用自己的数据和预训练模型重新训练train_softmax.py出错

Open Galaxy-yyyyy opened this issue 5 years ago • 4 comments

TypeError: Cannot create initializer for non-floating point type.

Apr 23 '19 08:04 Galaxy-yyyyy

need more info ..when are you getting this error..please post the whole error or screenshot

Apr 25 '19 07:04 thelastfunction

hello, have u resolved this problem? i am facing the same issue

Mar 20 '20 06:03 StonePanda

你现在解决这个问题了嘛？我也遇到了同样的问题 @yuanlisha

Mar 20 '20 06:03 StonePanda

you can use image = tf.to_float(image) to solve this problem.

Jul 26 '21 08:07 qqqsd