Error when checking model input about cnn-for-sentence-classification-in-keras HOT 7 CLOSED

Hi. Thanks for the interest. I will check it later. So far please try to temporally change in ~/.keras/keras.json located in your user directory:

"image_dim_ordering": "tf",
to
"image_dim_ordering": "th",

and let me know whether it helps

or more likely something is wrong with embedding_weights you get from your trained word2vec. I've uploaded pretrained word2vec model, try with it.
use default:

embedding_dim = 20          
min_word_count = 1  # Minimum word count                        
context = 10        # Context window size  

from cnn-for-sentence-classification-in-keras.

Thank you for your answer.
Same error :

ValueError: Error when checking model input: expected dropout_input_2 to have 3 dimensions, but got array with shape (10662L, 56L).

I'll then try with Tensor Flow backend and tell you my comments.

I also tried withthe updated pretrained word2vec and same error.

I'll continue working on this issue.

from cnn-for-sentence-classification-in-keras.

Hello again, after a lot of problems with TensorFlow, everything is working... although I'd like to know if there's a chance to use Theano instead of TensorFlow.

from cnn-for-sentence-classification-in-keras.

It was originally for Theano. I'll let you know when I have a moment to run it with recent Keras. Version conflict is another possible reason

from cnn-for-sentence-classification-in-keras.

Thank you for your time. Could you please tell me, which version of Theano and Keras are you using?

from cnn-for-sentence-classification-in-keras.

I have verified it, and it works as intended. My versions are Theano v0.8.2, Keras v1.2.0 and it's not too much behind the current 1.2.2. Also, added minor changes, they don't affect overall behavior.

from cnn-for-sentence-classification-in-keras.

After changes on my configuration files and your updates, it is running well on Theano.
Thank you for your time.

from cnn-for-sentence-classification-in-keras.