How to add and remove new layers in keras after loading weights?

by

You can take the output of the last model and create a new model. The lower layers remains the same.

model.summary()
model.layers.pop()
model.layers.pop()
model.summary()

x = MaxPooling2D()(model.layers[-1].output)
o = Activation('sigmoid', name="loss")(x)

model2 = Model(inputs=in_img, outputs=[o])
model2.summary()

Check How to use models from keras.applications for transfer learnig?

Update on Edit:

The new error is because you are trying to create the new model on global in_img which is actually not used in the previous model creation.. there you are actually defining a local in_img. So the global in_img is obviously not connected to the upper layers in the symbolic graph. And it has nothing to do with loading weights.

To better resolve this problem you should instead use model.input to reference to the input.

model3 = Model(input=model2.input, output=[o])

More Related Contents:

  1. Keras Dense layer’s input is not flattened
  2. Keras give input to intermediate layer and get final output
  3. How can I use a weight matrix created by a trained neural network to make predictions in another file?
  4. Make a custom loss function in keras
  5. How do you create a custom activation function with Keras?
  6. Deep-Learning Nan loss reasons
  7. Keras Sequential model input layer
  8. How to concatenate two layers in keras?
  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. Does Any one got “AttributeError: ‘str’ object has no attribute ‘decode’ ” , while Loading a Keras Saved Model
  12. ValueError at /image/ Tensor Tensor(“activation_5/Softmax:0”, shape=(?, 4), dtype=float32) is not an element of this graph
  13. ValueError: Error when checking target: expected model_2 to have shape (None, 252, 252, 1) but got array with shape (300, 128, 128, 3)
  14. Keras custom loss function: Accessing current input pattern
  15. Negative dimension size caused by subtracting 3 from 1 for ‘conv2d_2/convolution’
  16. How to get other metrics in Tensorflow 2.0 (not only accuracy)?
  17. How to know if underfitting or overfitting is occuring?
  18. memory issues when transforming np.array using to_categorical
  19. How to save final model using keras?
  20. What is the role of TimeDistributed layer in Keras?
  21. Unknown initializer: GlorotUniform when loading Keras model
  22. How to use fit_generator with multiple inputs
  23. How to create a keras layer with a custom gradient in TF2.0?
  24. keras: how to save the training history attribute of the history object
  25. How to fix “AttributeError: module ‘tensorflow’ has no attribute ‘get_default_graph'”?
  26. ‘Tensor’ object has no attribute ‘lower’
  27. ValueError: Output tensors to a Model must be the output of a TensorFlow `Layer`
  28. How to fix “ResourceExhaustedError: OOM when allocating tensor”
  29. Can I send callbacks to a KerasClassifier?
  30. How is the Keras Conv1D input specified? I seem to be lacking a dimension

Leave a Comment