linux运行keras程序报错

[JLANGLU]

安装了keras，运行一个实例，报错TypeError: sigmoid_cross_entropy_with_logits() got an unexpected keyword argument 'labels'
，求大神指导帮忙


Traceback (most recent call last):
File "Predict.py", line 19, in <module>
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
File "/home/jl/.local/lib/python2.7/site-packages/keras/models.py", line 766, in compile
**kwargs)
File "/home/jl/.local/lib/python2.7/site-packages/keras/engine/training.py", line 899, in compile
sample_weight, mask)
File "/home/jl/.local/lib/python2.7/site-packages/keras/engine/training.py", line 430, in weighted
score_array = fn(y_true, y_pred)
File "/home/jl/.local/lib/python2.7/site-packages/keras/losses.py", line 45, in binary_crossentropy
return K.mean(K.binary_crossentropy(y_pred, y_true), axis=-1)
File "/home/jl/.local/lib/python2.7/site-packages/keras/backend/tensorflow_backend.py", line 2615, in binary_crossentropy
logits=output)
TypeError: sigmoid_cross_entropy_with_logits() got an unexpected keyword argument 'labels'

[lingsongtianzi]

tensorflow版本的问题，将tensorflow版本升级到1.0以上即可

[lingsongtianzi]

tensorflow0.12里面用的是targets，而不是labels。

[zyq_go]

TypeError: sigmoid_cross_entropy_with_logits() got an unexpected keyword argument 'targets' 那如果是出来的是这个报错该怎么改呢