Error when checking model input: expected conv1d_1_input to have shape (None, 441, 216) but got array with shape (1, 441, 216)

Question

My input is simply a matrix with 441 rows and 216 columns :

The 216 feature values

The 441 trials

Total class label 6

I am trying to train my data on a CNN model:

model = Sequential()

model.add(Conv1D(128, 5, input_shape=(441, 216)))
model.add(Activation('relu'))
model.add(Conv1D(128, 5,padding='same'))
model.add(Activation('relu'))
model.add(Dropout(0.1))
model.add(MaxPooling1D(pool_size=(8)))
model.add(Conv1D(128, 5,padding='same',))
model.add(Activation('relu'))
model.add(Conv1D(128, 5,padding='same',))
model.add(Activation('relu'))
model.add(Conv1D(128, 5,padding='same',))
model.add(Activation('relu'))
model.add(Dropout(0.2))
model.add(Conv1D(128, 5,padding='same',))
model.add(Activation('relu'))
model.add(Flatten())
model.add(Dense(10))
model.add(Activation('softmax'))
opt = keras.optimizers.rmsprop(lr=0.00001, decay=1e-6)

model.compile(loss='categorical_crossentropy', 
           optimizer=opt,metrics=['accuracy'])

This throws the error: ValueError: Error when checking model input: expected conv1d_1_input to have shape (None, 441, 216) but got array with shape (1, 441, 216)

How can I feed in my input to the CNN ?

Simon Caby · Accepted Answer · 2019-03-29 20:01:42Z

1

You need to add a coma at the end of the first conv1d call: input_shape = (416, 234,) BTW, using "dropouts" between conv layers is less efficient than BatchNormalisation to avoid overfitting.

answered Mar 29, 2019 at 20:01

Simon Caby

1916 bronze badges

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

Collectives™ on Stack Overflow

Error when checking model input: expected conv1d_1_input to have shape (None, 441, 216) but got array with shape (1, 441, 216)

1 Answer 1

Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

Comments

Your Answer

Sign up or log in

Post as a guest

Related