qkeras.qconv2d_batchnorm

Fold batchnormalization with previous QConv2D layers.

Classes

QConv2DBatchnorm(*args, **kwargs)

Fold batchnormalization with a previous qconv2d layer.

class qkeras.qconv2d_batchnorm.QConv2DBatchnorm(*args, **kwargs)

Bases: QConv2D

Fold batchnormalization with a previous qconv2d layer.

build(input_shape)

call(inputs, training=False)

get_config()

Returns the config of the object.

An object config is a Python dictionary (serializable) containing the information needed to re-instantiate it.

get_folded_weights()

Function to get the batchnorm folded weights.

This function converts the weights by folding batchnorm parameters into the weight of QConv2D. The high-level equation:

W_fold = gamma * W / sqrt(variance + epsilon) bias_fold = gamma * (bias - moving_mean) / sqrt(variance + epsilon) + beta

get_quantization_config()

get_quantizers()

load_own_variables(store)

Loads the state of the layer.

You can override this method to take full control of how the state of the layer is loaded upon calling keras.models.load_model().

Parameters:

store – Dict from which the state of the model will be loaded.

save_own_variables(store)

Saves the state of the layer.

You can override this method to take full control of how the state of the layer is saved upon calling model.save().

Parameters:

store – Dict where the state of the model will be saved.