Removing then Inserting a New Middle Layer in a Keras Model

by

Assuming that you have a model vgg16_model, initialized either by your function above or by keras.applications.VGG16(weights="imagenet"). Now, you need to insert a new layer in the middle in such a way that the weights of other layers will be saved.

The idea is to disassemble the whole network to separate layers, then assemble it back. Here is the code specifically for your task:

vgg_model = applications.VGG16(include_top=True, weights="imagenet")

# Disassemble layers
layers = [l for l in vgg_model.layers]

# Defining new convolutional layer.
# Important: the number of filters should be the same!
# Note: the receiptive field of two 3x3 convolutions is 5x5.
new_conv = Conv2D(filters=64, 
                  kernel_size=(5, 5),
                  name="new_conv",
                  padding='same')(layers[0].output)

# Now stack everything back
# Note: If you are going to fine tune the model, do not forget to
#       mark other layers as un-trainable

x = new_conv
for i in range(3, len(layers)):
    layers[i].trainable = False
    x = layers[i](x)

# Final touch
result_model = Model(input=layer[0].input, output=x)
result_model.summary()

And the output of the above code is: 

_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
input_50 (InputLayer)        (None, 224, 224, 3)       0         
_________________________________________________________________
new_conv (Conv2D)            (None, 224, 224, 64)      1792      
_________________________________________________________________
block1_pool (MaxPooling2D)   (None, 112, 112, 64)      0         
_________________________________________________________________
block2_conv1 (Conv2D)        (None, 112, 112, 128)     73856     
_________________________________________________________________
block2_conv2 (Conv2D)        (None, 112, 112, 128)     147584    
_________________________________________________________________
block2_pool (MaxPooling2D)   (None, 56, 56, 128)       0         
_________________________________________________________________
block3_conv1 (Conv2D)        (None, 56, 56, 256)       295168    
_________________________________________________________________
block3_conv2 (Conv2D)        (None, 56, 56, 256)       590080    
_________________________________________________________________
block3_conv3 (Conv2D)        (None, 56, 56, 256)       590080    
_________________________________________________________________
block3_pool (MaxPooling2D)   (None, 28, 28, 256)       0         
_________________________________________________________________
block4_conv1 (Conv2D)        (None, 28, 28, 512)       1180160   
_________________________________________________________________
block4_conv2 (Conv2D)        (None, 28, 28, 512)       2359808   
_________________________________________________________________
block4_conv3 (Conv2D)        (None, 28, 28, 512)       2359808   
_________________________________________________________________
block4_pool (MaxPooling2D)   (None, 14, 14, 512)       0         
_________________________________________________________________
block5_conv1 (Conv2D)        (None, 14, 14, 512)       2359808   
_________________________________________________________________
block5_conv2 (Conv2D)        (None, 14, 14, 512)       2359808   
_________________________________________________________________
block5_conv3 (Conv2D)        (None, 14, 14, 512)       2359808   
_________________________________________________________________
block5_pool (MaxPooling2D)   (None, 7, 7, 512)         0         
_________________________________________________________________
flatten (Flatten)            (None, 25088)             0         
_________________________________________________________________
fc1 (Dense)                  (None, 4096)              102764544 
_________________________________________________________________
fc2 (Dense)                  (None, 4096)              16781312  
_________________________________________________________________
predictions (Dense)          (None, 1000)              4097000   
=================================================================
Total params: 138,320,616
Trainable params: 1,792
Non-trainable params: 138,318,824
_________________________________________________________________

More Related Contents:

  1. How to apply gradient clipping in TensorFlow?
  2. Keras custom loss function: Accessing current input pattern
  3. How can I use a pre-trained neural network with grayscale images?
  4. How to fix “ResourceExhaustedError: OOM when allocating tensor”
  5. Keras, How to get the output of each layer?
  6. Make a custom loss function in keras
  7. Keras not training on entire dataset
  8. Deep-Learning Nan loss reasons
  9. Can Keras with Tensorflow backend be forced to use CPU or GPU at will?
  10. Proper way to feed time-series data to stateful LSTM?
  11. Keras replacing input layer
  12. How to get other metrics in Tensorflow 2.0 (not only accuracy)?
  13. How to understand the term `tensor` in TensorFlow?
  14. Dimension of shape in conv1D
  15. How to know if underfitting or overfitting is occuring?
  16. Custom loss function in Keras
  17. Save and load model optimizer state
  18. Unknown initializer: GlorotUniform when loading Keras model
  19. How do I get the weights of a layer in Keras?
  20. Multiple outputs in Keras
  21. How to handle non-determinism when training on a GPU?
  22. ValueError: Input 0 of layer sequential is incompatible with the layer: : expected min_ndim=4, found ndim=3. Full shape received: [8, 28, 28]
  23. How to implement Grad-CAM on a trained network
  24. keras: how to save the training history attribute of the history object
  25. ‘Tensor’ object has no attribute ‘lower’
  26. ValueError: Output tensors to a Model must be the output of a TensorFlow `Layer`
  27. How do I plot a Keras/Tensorflow subclassing API model?
  28. Strange behaviour of the loss function in keras model, with pretrained convolutional base
  29. How is the Keras Conv1D input specified? I seem to be lacking a dimension
  30. Multi-input Multi-output Model with Keras Functional API

Leave a Comment