save_compressed_retrain_model

Function Usage

Generates the final static compression combination model based on the retrained model.

Constraints

None

Prototype

save_compressed_retrain_model(pb_model, outputs, record_file, save_path)

Command-Line Options

Option	Input/Return	Meaning	Restriction
pb_model	Input	PB model with sparsity and quantization operators for inference.	A string
outputs	Input	List of output operators of the graph.	A list of strings.
record_file	Input	Directory of the quantization factor record file, including the file name.	A string
save_path	Input	Path for storing the compressed model. Must include the prefix of the model name, for example, *./quantized_model/model**.	A string

Returns

None

Outputs

The compressed model that serves for both accuracy simulation in the TensorFlow environment and inference deployment on Ascend AI Processor.

Calling Example

import amct_tensorflow as amct
amct.save_compressed_retrain_model(masked_pb_path, [operation_name_1, operation_name_2], './tmp/record.txt', './pb_model/final_model')

Parent topic: Compression Combination APIs