Python (Keras): Value Error: Error when checking input

Question

I'm trying to train a CNN on word vectors generated using the gensim library. After I have generated all of my data in numeric form, I try to pass it on to a CNN model using Keras when I get the following error:

ValueError: Error when checking input: expected conv2d_1_input to have 4 dimensions, but got array with shape (20000, 250, 50)

I've searched on this problem for hours, and all of the solutions posted for similar/same issues haven't been able to solve this error for me. Can anyone see where I'm going wrong with the input dimensions? I've generated some random numpy data that recreates the error:

import numpy as np
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import Convolution2D, Flatten, Dropout
from keras.layers.embeddings import Embedding
from keras.preprocessing import sequence
from keras.callbacks import TensorBoard

t = np.random.rand(20000,250,50)
l = np.random.rand(20000,1)

embedding_vecor_length = 50
net = Sequential()
net.add(Convolution2D(64, 3,input_shape=(1,250,50), 
data_format='channels_first'))
# Convolutional model (3x conv, flatten, 2x dense)
net.add(Convolution2D(32,(3), padding='same'))
net.add(Convolution2D(16,(3), padding='same'))
net.add(Convolution2D(8,(3), padding='same'))
net.add(Flatten())
net.add(Dropout(0.2))
net.add(Dense(180,activation='sigmoid'))
net.add(Dropout(0.2))
net.add(Dense(1,activation='sigmoid'))
net.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])

tensorBoardCallback = TensorBoard(log_dir='./logs', write_graph=True)
net.summary()

net.fit(t, l, epochs=3, callbacks=[tensorBoardCallback], batch_size=64)

Daniel Möller · Accepted Answer · 2018-12-05 15:53:10Z

1

Convolutions use 4 dimensions. Considering you're using "channels_first":

Images
Channels
Side 1
Side 2

Your input is missing the channels.

t = np.random.rand(20000,1,250,50)

answered Dec 5, 2018 at 15:53

Daniel Möller

86.8k24 gold badges202 silver badges222 bronze badges

Sign up to request clarification or add additional context in comments.

4 Comments

CPerkins Over a year ago

Thanks for the quick response! I'm not sure how I should add the channels to the shape of my array. Right now the shape of my data is (20000,250,50), so I would I add the channel dimension to the numpy array?

Daniel Möller Over a year ago

array = array.reshape((20000,1,250,50))

Daniel Möller Over a year ago

I suggest to use the channels last, as usual in Keras. Then array = array.reshape((20000,250,50,1))

CPerkins Over a year ago

Right on. Thanks that did the trick. Now I have another issue(nested np arrays) but is unrelated to this one.

Collectives™ on Stack Overflow

Python (Keras): Value Error: Error when checking input

1 Answer 1

4 Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

4 Comments

Your Answer

Sign up or log in

Post as a guest

Related