Passing output of a CNN to BILSTM

by

The problem is the data passed to LSTM and it can be solved inside your network. The LSTM expects 3D data while Conv2D produces 4D. There are two possibilities you can adopt:

1) make a reshape (batch_size, H, W*channel);

2) make a reshape (batch_size, W, H*channel).

In these ways, you have 3D data to use inside your LSTM. below an example

def ReshapeLayer(x):
    
    shape = x.shape
    
    # 1 possibility: H,W*channel
    reshape = Reshape((shape[1],shape[2]*shape[3]))(x)
    
    # 2 possibility: W,H*channel
    # transpose = Permute((2,1,3))(x)
    # reshape = Reshape((shape[1],shape[2]*shape[3]))(transpose)
    
    return reshape

model = Sequential()
model.add(Conv2D(filters = 16, kernel_size = 3, input_shape = (32,32,3)))
model.add(Lambda(ReshapeLayer))  # <============
model.add(LSTM(16))
model.add(Dense(units=2, activation='softmax'))
model.compile(loss="categorical_crossentropy", optimizer="adam",)
model.summary()

More Related Contents:

  1. Tensorflow – ValueError: Failed to convert a NumPy array to a Tensor (Unsupported object type float)
  2. Proper way to feed time-series data to stateful LSTM?
  3. How does Keras 1d convolution layer work with word embeddings – text classification problem? (Filters, kernel size, and all hyperparameter)
  4. expected ndim=3, found ndim=2
  5. Dimension of shape in conv1D
  6. Keras LSTM input dimension setting
  7. How to implement Grad-CAM on a trained network
  8. ‘Tensor’ object has no attribute ‘lower’
  9. Keras Dense layer’s input is not flattened
  10. Keras + Tensorflow and Multiprocessing in Python
  11. How to use a Keras RNN model to forecast for future dates or events?
  12. TypeError: __array__() takes 1 positional argument but 2 were given (Image classification Keras)
  13. Tensorflow 2.0 – AttributeError: module ‘tensorflow’ has no attribute ‘Session’
  14. Neural Network LSTM input shape from dataframe
  15. What do I need K.clear_session() and del model for (Keras with Tensorflow-gpu)?
  16. How to get other metrics in Tensorflow 2.0 (not only accuracy)?
  17. Removing then Inserting a New Middle Layer in a Keras Model
  18. Why can’t I get reproducible results in Keras even though I set the random seeds?
  19. AttributeError: module ‘tensorflow.python.keras.utils.generic_utils’ has no attribute ‘populate_dict_with_module_objects’
  20. How do I check if keras is using gpu version of tensorflow?
  21. Tensorflow : logits and labels must have the same first dimension
  22. How to create a keras layer with a custom gradient in TF2.0?
  23. How to fix “AttributeError: module ‘tensorflow’ has no attribute ‘get_default_graph'”?
  24. ValueError: Input 0 is incompatible with layer lstm_13: expected ndim=3, found ndim=4
  25. How to fix “ResourceExhaustedError: OOM when allocating tensor”
  26. How do I plot a Keras/Tensorflow subclassing API model?
  27. Strange behaviour of the loss function in keras model, with pretrained convolutional base
  28. TensorFlow 2.0 Keras: How to write image summaries for TensorBoard
  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