error when retraining word vector

[wailoktam]

Hi, I have reverted to an earlier commit: https://github.com/alexander-rakhlin/CNN-for-Sentence-Classification-in-Keras/tree/0a10445fbd0a1c783e6231cd1accb1e1a4e2252f

The codes run fine with the provided embeddings. But when I delete the embeddings in the models directory and retrain it. I get the following errors:

trainGraph.py:127: UserWarning: Update your Conv1D call to the Keras 2 API: Conv1D(activation="relu", padding="valid", strides=1, filters=3, kernel_size=3)
subsample_length=1)(graph_in)
trainGraph.py:128: UserWarning: Update your MaxPooling1D call to the Keras 2 API: MaxPooling1D(pool_size=2)
pool = MaxPooling1D(pool_length=2)(conv)
trainGraph.py:127: UserWarning: Update your Conv1D call to the Keras 2 API: Conv1D(activation="relu", padding="valid", strides=1, filters=3, kernel_size=4)
subsample_length=1)(graph_in)
trainGraph.py:133: UserWarning: The Merge layer is deprecated and will be removed after 08/2017. Use instead layers from keras.layers.merge, e.g. add, concatenate, etc.
out = Merge(mode='concat')(convs)
trainGraph.py:137: UserWarning: Update your Model call to the Keras 2 API: Model(outputs=Join.0, inputs=/input_1)
graph = Model(input=graph_in, output=out)
/root/anaconda/lib/python2.7/site-packages/keras/models.py:849: UserWarning: The nb_epoch argument in fit has been renamed epochs.
warnings.warn('The nb_epoch argument in fit '
Traceback (most recent call last):
File "trainGraph.py", line 158, in
model.fit(x_shuffled, y_shuffled, batch_size=batch_size, nb_epoch=num_epochs, validation_split=val_split, verbose=2)
File "/root/anaconda/lib/python2.7/site-packages/keras/models.py", line 868, in fit
initial_epoch=initial_epoch)
File "/root/anaconda/lib/python2.7/site-packages/keras/engine/training.py", line 1434, in fit
batch_size=batch_size)
File "/root/anaconda/lib/python2.7/site-packages/keras/engine/training.py", line 1310, in _standardize_user_data
exception_prefix='input')
File "/root/anaconda/lib/python2.7/site-packages/keras/engine/training.py", line 139, in _standardize_input_data
str(array.shape))
ValueError: Error when checking input: expected embedding_1_input to have shape (None, 56) but got array with shape (481625, 629)

Any idea to fix it? Thanks.

[alexander-rakhlin]

Hi,

I am short of time these days. Current recommendation is to update old code for recent Keras and verify array dimensionality it produces to match the provided embeddings. The error here:

ValueError: Error when checking input: expected embedding_1_input to have shape (None, 56) but got array with shape (481625, 629)

[wailoktam]

Hi, I have rewritten the code for keras 2 but I am stuck at this line:

conv = Conv1D(filters=num_filters, kernerl_size=fsz, padding='valid', activation='relu', strides=1)(graph_in)

I am getting this error: File "trainGraph.py", line 131, in
conv = Conv1D(filters=num_filters, kernerl_size=fsz, padding='valid', activation='relu', strides=1)(graph_in)
TypeError: init() takes at least 3 arguments (2 given)

Any idea? Thanks in advance

[alexander-rakhlin]

Please see updated version