ValueError: Input 0 is incompatible with layer lstm_13: expected ndim = 3, found ndim = 4
I am trying to categorize multiple classes, and here are the details of my training input and output:
train_input.shape = (1, 95000, 360) (length of array of length 95000 with each element is an array of length 360)
train_output.shape = (1, 95000, 22) (there are 22 classes)
model = Sequential()
model.add(LSTM(22, input_shape=(1, 95000,360)))
model.add(Dense(22, activation='softmax'))
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
print(model.summary())
model.fit(train_input, train_output, epochs=2, batch_size=500)
Mistake:
ValueError: Input 0 is incompatible with layer lstm_13: expected ndim = 3, found ndim = 4 in queue: model.add (LSTM (22, input_shape = (1, 95000,360)))
Please help me, I cannot solve this via other answers.
+3
source to share
2 answers
I solved the problem by doing
input size: (95000,360,1) and output size: (95000.22)
and changed the input form to (360,1) in the code where the model is defined:
model = Sequential()
model.add(LSTM(22, input_shape=(360,1)))
model.add(Dense(22, activation='softmax'))
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
print(model.summary())
model.fit(ml2_train_input, ml2_train_output_enc, epochs=2, batch_size=500)
+3
source to share