Keras replacing input layer

by

When you saved your model using:

old_model.save('my_model.h5')

it will save following:

  1. The architecture of the model, allowing to create the model.
  2. The weights of the model.
  3. The training configuration of the model (loss, optimizer).
  4. The state of the optimizer, allowing training to resume from where you left before.

So then, when you load the model:

res50_model = load_model('my_model.h5')

you should get the same model back, you can verify the same using:

res50_model.summary()
res50_model.get_weights()

Now you can, pop the input layer and add your own using:

res50_model.layers.pop(0)
res50_model.summary()

add new input layer: 

newInput = Input(batch_shape=(0,299,299,3))    # let us say this new InputLayer
newOutputs = res50_model(newInput)
newModel = Model(newInput, newOutputs)

newModel.summary()
res50_model.summary()

More Related Contents:

  1. Keras, How to get the output of each layer?
  2. How to apply gradient clipping in TensorFlow?
  3. Keras custom loss function: Accessing current input pattern
  4. How can I use a pre-trained neural network with grayscale images?
  5. Dimension of shape in conv1D
  6. Removing then Inserting a New Middle Layer in a Keras Model
  7. Custom loss function in Keras
  8. How do I get the weights of a layer in Keras?
  9. Multiple outputs in Keras
  10. ValueError: Input 0 of layer sequential is incompatible with the layer: : expected min_ndim=4, found ndim=3. Full shape received: [8, 28, 28]
  11. Keras LSTM input dimension setting
  12. How to implement Grad-CAM on a trained network
  13. How to fix “ResourceExhaustedError: OOM when allocating tensor”
  14. How do I plot a Keras/Tensorflow subclassing API model?
  15. Strange behaviour of the loss function in keras model, with pretrained convolutional base
  16. Multi-input Multi-output Model with Keras Functional API
  17. Understanding Keras LSTMs
  18. Make a custom loss function in keras
  19. Keras not training on entire dataset
  20. Could not load dynamic library ‘cudart64_101.dll’ on tensorflow CPU-only installation
  21. Negative dimension size caused by subtracting 3 from 1 for ‘conv2d_2/convolution’
  22. This model has not yet been built error on model.summary()
  23. How to understand the term `tensor` in TensorFlow?
  24. TensorFlow ValueError: Cannot feed value of shape (64, 64, 3) for Tensor u’Placeholder:0′, which has shape ‘(?, 64, 64, 3)’
  25. Save and load model optimizer state
  26. Keras misinterprets training data shape
  27. How to handle non-determinism when training on a GPU?
  28. How to fix “AttributeError: module ‘tensorflow’ has no attribute ‘get_default_graph'”?
  29. What is right batch normalization function in Tensorflow?
  30. TensorFlow 2.0 Keras: How to write image summaries for TensorBoard

Leave a Comment