save_quant_retrain_model

Applicability

Product	Supported
Atlas A3 training series products/Atlas A3 inference series products	INT8 quantization: √
Atlas A2 training products/Atlas A2 inference products	INT8 quantization: √
Atlas 200I/500 A2 inference product	INT8 quantization: √
Atlas inference series products	INT8 quantization: √
Atlas training products	INT8 quantization: √

Description

Inserts operators such as AscendQuant and AscendDequant into the retrained model and generates a model that can be used for both accuracy simulation and inference deployment.

Prototype

save_quant_retrain_model(pb_model, outputs, record_file, save_path)

Parameters

Parameter	Input/Output	Description
pb_model	Input	.pb model saved after retraining. A string.
outputs	Input	Output of the user model A list of strings, for example, [output1,output2,...].
record_file	Input	File for storing quantization factors. A quantized model file is generated based on the record file and original .pb model file. A string.
save_path	Input	Model save path. Must include the prefix of the model name, for example, *./quantized_model/model**. A string.

Returns

None

Example

amct.save_quant_retrain_model(FLAGS.checkpoint_path+'/output_graph.pb',output_node_names, record_file, FLAGS.checkpoint_path+'/resnet50')

The quantized .pb model file can be used for accuracy simulation in the TensorFlow environment or inference on the Ascend AI Processor.

When QAT is performed again, the preceding files output by the API will be overwritten.

Parent topic: QAT APIs