Setting timesteps = 1 (since, I want one timestep for each instance) and reshaping the X_train and X_test as: import numpy as np X_train = np.reshape(X_train, (X_train.shape[0], 1, X_train.shape[1])) X_test = np.reshape(X_test, (X_test.shape[0], 1, X_test.shape[1])) This worked!
keras.backend.clear_session() should clear the previous model. From https://keras.io/backend/: Destroys the current TF graph and creates a new one. Useful to avoid clutter from old models / layers.
What is keras_layer in your code? You can set weights these ways: model.layers[i].set_weights(listOfNumpyArrays) model.get_layer(layerName).set_weights(…) model.set_weights(listOfNumpyArrays) Where model is an instance of an existing model. You can see the expected length of the list and its array shapes using the method get_weights() from the same instances above.
Keras does this by default. In Keras dropout is disabled in test mode. You can look at the code here and see that they use the dropped input in training and the actual input while testing. As far as I know you have to build your own training function from the layers and specify the … Read more
Keras does this by default. In Keras dropout is disabled in test mode. You can look at the code here and see that they use the dropped input in training and the actual input while testing. As far as I know you have to build your own training function from the layers and specify the … Read more
After looking at keras sources (this place): Start up your python-binary and do the following import os print(os.path.expanduser(‘~’)) # >>> C:\\Users\\Sascha’ # will look different for different OS This should be the base-directory Keras will build an folder .keras there where keras.json resides (if it was already created). If it’s not there, create it there … Read more
Those methods are roughly the same. It is correct to subclass Sequence when your dataset doesn’t fit in memory. But you shouldn’t run any preprocessing in any of the class’ methods because that will be reexecuted once per epoch wasting lots of computing resources. It is probably also easier to shuffle the samples rather than … Read more
tf.keras (formerly tf.contrib.keras) is an implementation of keras 2 implemented exclusively with/for tensorflow. It is hosted on the tensorflow repo and has a distinct code base than the official repo (the last commit there in the tf-keras branch dates back from May 2017). As a rule of thumb, if your code use any tensorflow-specific code, … Read more
When you use fit_generator, the number of samples processed for each epoch is batch_size * steps_per_epochs. From the Keras documentation for fit_generator: https://keras.io/models/sequential/ steps_per_epoch: Total number of steps (batches of samples) to yield from generator before declaring one epoch finished and starting the next epoch. It should typically be equal to the number of unique … Read more