theo- / sentiment-analysis-keras-conv Goto Github PK

Hi! First of all, thanks for sharing this keras nn!

I was trying to run this code as is and I got this error right after running the model.compile(). Would you know what is it?

TypeError: sigmoid_cross_entropy_with_logits() got an unexpected keyword argument 'labels'_

Full Error Transcription:

`### In [21]: model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])

TypeError Traceback (most recent call last)
in ()
----> 1 model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])

//anaconda/lib/python2.7/site-packages/keras/models.pyc in compile(self, optimizer, loss, metrics, sample_weight_mode, **kwargs)
764 metrics=metrics,
765 sample_weight_mode=sample_weight_mode,
--> 766 **kwargs)
767 self.optimizer = self.model.optimizer
768 self.loss = self.model.loss

//anaconda/lib/python2.7/site-packages/keras/engine/training.pyc in compile(self, optimizer, loss, metrics, loss_weights, sample_weight_mode, **kwargs)
897 loss_weight = loss_weights_list[i]
898 output_loss = weighted_loss(y_true, y_pred,
--> 899 sample_weight, mask)
900 if len(self.outputs) > 1:
901 self.metrics_tensors.append(output_loss)

//anaconda/lib/python2.7/site-packages/keras/engine/training.pyc in weighted(y_true, y_pred, weights, mask)
428 """
429 # score_array has ndim >= 2
--> 430 score_array = fn(y_true, y_pred)
431 if mask is not None:
432 # Cast the mask to floatX to avoid float64 upcasting in theano

//anaconda/lib/python2.7/site-packages/keras/losses.pyc in binary_crossentropy(y_true, y_pred)
43
44 def binary_crossentropy(y_true, y_pred):
---> 45 return K.mean(K.binary_crossentropy(y_pred, y_true), axis=-1)
46
47

//anaconda/lib/python2.7/site-packages/keras/backend/tensorflow_backend.pyc in binary_crossentropy(output, target, from_logits)
2615
2616 return tf.nn.sigmoid_cross_entropy_with_logits(labels=target,
-> 2617 logits=output)
2618
2619

TypeError: sigmoid_cross_entropy_with_logits() got an unexpected keyword argument 'labels'
`

hi, thank you for the code and the blog post.
how can I use this code for multi_class classification?