qkeras.qnormalization

Definition of normalization quantization package.

Classes

QBatchNormalization(*args, **kwargs)

Quantized Batch Normalization layer.

class qkeras.qnormalization.QBatchNormalization(*args, **kwargs)

Bases: BatchNormalization

Quantized Batch Normalization layer. For training, mean and variance are not quantized. For inference, the quantized moving mean and moving variance are used.

output = (x - mean) / sqrt(var + epsilon) * quantized_gamma + quantized_beta

call(inputs, training=False)

compute_output_shape(input_shape)

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_prunable_weights()

get_quantizers()