I am trying to use a sequence of 22 images as input into a VGG16 network by concatenating the 22 inputs into a list and adding a Conv2D layer, I plan to use the imagenet weights but when I do such, it keeps returning the error
<ipython-input-51-3ae60b594d39> in <module>
1 for layer in model.layers:
2 layer.trainable = False
----> 3 vgg = VGG16(include_top = False, weights = 'imagenet', input_tensor = input)
2 frames
/usr/local/lib/python3.8/dist-packages/keras/saving/hdf5_format.py in load_weights_from_hdf5_group(f, model)
726 layer_names = filtered_layer_names
727 if len(layer_names) != len(filtered_layers):
--> 728 raise ValueError(
729 f'Layer count mismatch when loading weights from file. '
730 f'Model expected {len(filtered_layers)} layers, found '
ValueError: Layer count mismatch when loading weights from file. Model expected 14 layers, found 13 saved layers.```
Here is my code for the section and I really don't understand what went wrong.
inputs = []
for i in range(train_images.shape[0]):
inputs.append(tf.keras.Input(shape = (128,128,3)))
concate_input = tf.keras.layers.Concatenate()(inputs)
input = tf.keras.layers.Conv2D(3, (3, 3),
padding=‘same’, activation=“relu”)(concate_input)
vgg = VGG16(include_top = False, weights = ‘imagenet’, input_tensor = input)