ValueError: Input 0 of layer "sequential_21" is incompatible with the layer: expected shape=(None, 4, 1), found shape=(None, 7, 7, 12)

Question

I am trying to run a CNN-LSTM model on a series of images with dimensions (9219, 7, 7, 12) but I get the following error :

model = Sequential()

model.add(Conv1D(32, 4, activation='relu', padding='same', input_shape=(train_x.shape[1], train_x.shape[2], train_x.shape[3])))
model.add(LSTM(32, return_sequences=True))
model.add(MaxPooling1D(2))
model.add(Conv1D(16, 8, activation="relu", padding='same'))
model.add(LSTM(64, return_sequences=True))
model.add(MaxPooling1D(2))
model.add(Conv1D(16, 8, activation="relu", padding='same'))
model.add(LSTM(128))
model.add(Dense(3, activation='sigmoid'))

And I get this error

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-117-d8b5365ec22e> in <cell line: 4>()
      2 
      3 model.add(Conv1D(32, 4, activation='relu', padding='same', input_shape=(train_x.shape[1], train_x.shape[2], train_x.shape[3])))
----> 4 model.add(LSTM(32, return_sequences=True))
      5 model.add(MaxPooling1D(2))
      6 model.add(Conv1D(16, 8, activation="relu", padding='same'))

2 frames
/usr/local/lib/python3.10/dist-packages/keras/engine/input_spec.py in assert_input_compatibility(input_spec, inputs, layer_name)
    233             ndim = shape.rank
    234             if ndim != spec.ndim:
--> 235                 raise ValueError(
    236                     f'Input {input_index} of layer "{layer_name}" '
    237                     "is incompatible with the layer: "

ValueError: Input 0 of layer "lstm_32" is incompatible with the layer: expected ndim=3, found ndim=4. Full shape received: (None, 7, 7, 32)

Try with input_shape=(train_x.shape[1], train_x.shape[2])? — shaik moeed
– shaik moeed, Commented Aug 24, 2023 at 5:17
No, that would just be leaving a dimension of his data. It should be input_shape=(train_x.shape[1], train_x.shape[2] * train_x.shape[3]) — Musabbir Arrafi
– Musabbir Arrafi, Commented Aug 24, 2023 at 5:24

Musabbir Arrafi · Accepted Answer · 2023-08-24 05:16:41Z

In your input shape, you're providing 3D input shape, whereas you're supposed to provide a 2D input shape like this input_shape=(train_x.shape[1], train_x.shape[2] * train_x.shape[3]). That's why the second hidden layer throws a input shape error. Here's how your code should look like:

Corrected model

model = Sequential()
model.add(Conv1D(32, 4, activation='relu', padding='same', input_shape=(train_x.shape[1], train_x.shape[2] * train_x.shape[3])))
model.add(LSTM(32, return_sequences=True))
model.add(MaxPooling1D(2))
model.add(Conv1D(16, 8, activation="relu", padding='same'))
model.add(LSTM(64, return_sequences=True))
model.add(MaxPooling1D(2))
model.add(Conv1D(16, 8, activation="relu", padding='same'))
model.add(LSTM(128))
model.add(Dense(3, activation='sigmoid'))

Model Summary

from keras.optimizers import Adam

# change the optimizer,loss function
# and metrics according to your need

model.compile(optimizer=Adam(learning_rate=0.001),
              loss='binary_crossentropy',
              metrics=['accuracy'])
print(model.summary())

Output:

Model: "sequential"
_________________________________________________________________
 Layer (type)                Output Shape              Param #   
=================================================================
 conv1d (Conv1D)             (None, 10, 32)            672       
                                                                 
 lstm (LSTM)                 (None, 10, 32)            8320      
                                                                 
 max_pooling1d (MaxPooling1  (None, 5, 32)             0         
 D)                                                              
                                                                 
 conv1d_1 (Conv1D)           (None, 5, 16)             4112      
                                                                 
 lstm_1 (LSTM)               (None, 5, 64)             20736     
                                                                 
 max_pooling1d_1 (MaxPoolin  (None, 2, 64)             0         
 g1D)                                                            
                                                                 
 conv1d_2 (Conv1D)           (None, 2, 16)             8208      
                                                                 
 lstm_2 (LSTM)               (None, 128)               74240     
                                                                 
 dense (Dense)               (None, 3)                 387       
                                                                 
=================================================================
Total params: 116675 (455.76 KB)
Trainable params: 116675 (455.76 KB)
Non-trainable params: 0 (0.00 Byte)

Collectives™ on Stack Overflow

ValueError: Input 0 of layer "sequential_21" is incompatible with the layer: expected shape=(None, 4, 1), found shape=(None, 7, 7, 12)

1 Answer 1

Corrected model

Model Summary

Output:

Hope it helps!

Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

Corrected model

Model Summary

Output:

Hope it helps!

Comments

Your Answer

Sign up or log in

Post as a guest

Related