quantize_preprocess

Function Usage

Preprocesses the quantization of a graph based on the quantization configuration file (currently, only balanced quantization is supported), inserts the balanced quantization operator, and generates a balance factor record file record_file that is to be read in the subsequent quantize_model phase.

Prototype

quantized_preprocess(graph, config_file, record_file, outputs=None)

Command-Line Options

Option	Input/Return	Meaning	Restriction
graph	Input	A tf.Graph of the model to be quantized.	A tf.Graph.
config_file	Input	User-defined quantization configuration file, which specifies the configuration of each layer to be quantized in the tf.Graph.	A string
record_file	Input	Directory of the balance factor record file, including the file name.	A string
outputs	Input	List of output nodes of the graph. When the output nodes change due to graph modification, this list is updated accordingly.	A list. Default: None

Outputs

None.

Examples

import amct_tensorflow as amct
# Build a network to be quantized.
network = build_network()

# Insert the quantization API.
amct.quantized_preprocess(
      graph=tf.get_default_graph(),
      config_file="./configs/config.json",
      record_file="./record_scale_offset.txt")

Parent topic: PTQ APIs