Train the model for a fixed number of epochs. Returns a history object. Its `history` attribute is a record of training loss values a

Configure the learning process. # Arguments optimizer: str (name of optimizer) or optimizer object. See [optimize

Compute the loss on some input data, batch by batch. Arguments: see `fit` method.

Generate output predictions for the input samples batch by batch. # Arguments X: the input data, as a numpy array.

Generate output predictions for the input samples batch by batch. Arguments: see `fit` method.

Train the model for a fixed number of epochs. Returns a history object. Its `history` attribute is a record of training loss values a

Generate class probability predictions for the input samples batch by batch. # Arguments X: the input data, as a numpy ar

Add a node in the graph. It can be connected to multiple inputs, which will first be merged into one tensor according to the mode spec

Sum of the values in a tensor, alongside the specified axis.

Return the parameters of the layer, as a dictionary.

Generate class predictions for the input samples batch by batch. # Arguments X: the input data, as a numpy array.

Configure the learning process. # Arguments optimizer: str (name of optimizer) or optimizer object. See [optimize

Add an input to the graph. # Arguments: name: string. The name of the new input. Must be unique in the graph. input_s

Add an output to the graph. This output can merge several node outputs into a single output. # Arguments name: name of t

Compute the loss on some input data, batch by batch. # Arguments X: input data, as a numpy array. y: labels, as a num

Set the weights of the layer. weights: a list of numpy arrays. The number of arrays and their shape must match number

Generate output predictions for the input samples batch by batch. # Arguments X: the input data, as a numpy array.

Generate class predictions for the input samples batch by batch. # Arguments X: the input data, as a numpy array.

classification=True overrides output_shape (i.e. output_shape is set to (1,)) and the output consists in integers in [0, nb_c

@param current: index of current step @param values: list of tuples (name, value_for_last_step). The progress bar

Return the configuration of the model as a dictionary. To load a model from its configuration, use `keras.models.model_from_c

Single gradient update on a batch of samples. Arguments: see `fit` method.

Function for making predictions with the Bayesian neural network. @param X_test The matrix of features for the test data

Compute the loss on a single batch of samples. Arguments: see `fit` method.

Pad each sequence to the same length: the length of the longest sequence. If maxlen is provided, any sequence longer

Convert class vector (integers from 0 to nb_classes) to binary class matrix, for use with categorical_crossentropy.

Load all layer weights from a HDF5 save file.

Dump all layer weights to a HDF5 file.

Used to share a same layer across multiple nodes. Supposed, for instance, that you want to apply one same `Dense` layer after to the

These are just a set of floats used for testing the activation functions, and are useful in multiple tests. The values should all be non

Return the weights of the layer, as a list of numpy arrays.

For some models (such as RNNs) you want a way of being able to mark some output data-points as "masked", so they are not used in futur

These are just a set of floats used for testing the activation functions, and are useful in multiple tests.

Single gradient update over one batch of samples. Returns the loss over the data, or a tuple `(loss, accuracy)` if `accuracy=True`.

Return the total number of floats (or ints) composing the weights of the layer.

Connect a layer to its parent in the computational graph.

Use this function to add a shared layer across multiple Sequential models without merging the outputs.

Instantiation of layer weights. Called after `set_previous`, or after `set_input_shape`, once the layer has a defined input shape.