Simplified Configuration File for Auto Channel Pruning Search

The basic_info.proto file describes configurations for auto channel pruning search. Find the file in /amct_tensorflow/proto/basic_info.proto under the AMCT installation directory. The content of the file is as follows.

Parameter	Required/Optional	Type	Field	Description
AutoMixedPrecisionConfig	-	-	-	AMCT simplified configuration for automatic mixed precision search. The current version does not support this feature.
	Optional	Float	compress_ratio	Compression ratio. The computation amount of all quantizable layers is used as a reference compression multiple.
	Repeated	QuantBitLimit	quant_bit_limit	Quantization bit width search range of specified layers.
	Optional	String	ptq_cfg	Simplified PTQ configuration file, which is used to obtain the quantization factors under the quantization bit widths of INT4 and INT8 during calibration. If it is not set, uses the default PTQ configuration.
	Optional	Int64	test_iteration	Number of batches to dump. The dump data is used to measure the quantization impact and computation amount. The data size should be large enough to be representative.
	Optional	String	override_qat_cfg	Simplified QAT configuration file. The output of automatic mixed precision search will overwrite the bit width of involved layers, and other parameters remain unchanged. If it is not set, uses the simplified QAT configuration file (.proto) to generate a .cfg configuration file with quantization bit width.
AutoChannelPruneConfig	-	-	-	AMCT simplified configuration for auto channel pruning search
	Required	Float	compress_ratio	Compression ratio. The computation amount of all quantizable layers is used as a reference compression multiple.
	Optional	Boolean	ascend_optimized	Whether to perform adaptation to Ascend platforms. If the sparsified model is to be deployed on the AI processor, you are advised to set this parameter to true.
	Optional	Float	max_prune_ratio	Maximum sparsity ratio of a single layer. Defaults to 1.
	Optional	Int64	test_iteration	Batch number of the input test data.
	Optional	String	override_prune_cfg	Simplified configuration file for channel pruning set by the user. It can contain only the skip and override configurations. The configured layers use the specified configuration and will not be rewritten by the auto channel pruning search APIs.
QuantBitLimit	-	-	-	Quantization bit width search range of specified layers.
	Optional	String	layer_name	Layer name.
	Repeated	DataType	data_range	Quantization bit width range.
DataType	-	-	-	Quantization bit width range. Enumeration.
	-	-	FLOAT	Float. Not quantized. The current version supports only INT8 quantization.
	-	-	INT8	INT8 quantization.
	-	-	INT4	INT4 quantization.

The following is an example of the simplified configuration file (amc.cfg) for auto channel pruning search:

compress_ratio: 1.5
ascend_optimized: true
max_prune_ratio: 0.8
test_iteration: 1
override_prune_cfg: 'your/path/to/override_channel_prune.cfg'

Parent topic: Reference