AMCT_LOG_FILE_LEVEL

Description

Sets the log level of framework-specific log files (amct_pytorch.log for PyTorch; amct_caffe.log for Caffe; amct_onnx.log for ONNX), as well as the log level of logs output by each quantization layer during precision simulation model generation.

Possible values are:

• DEBUG: Prints logs of DEBUG, INFO, WARNING, and ERROR levels, including process details, quantizable layer, and corresponding processing phase (fusion, parameter quantization, or activation quantization).
• INFO (default): Prints logs of INFO, WARNING, and ERROR levels, including brief quantization processing information such as the quantization phase.
• WARNING: Prints logs of WARNING and ERROR levels, including warnings generated during quantization.
• ERROR: Prints logs of the ERROR level, including error messages generated during quantization.

Example

export AMCT_LOG_FILE_LEVEL=INFO

Constraints

None

Applicability

Atlas 350 Accelerator Card

Atlas A2 training product/Atlas A2 inference product

Atlas A3 training product/Atlas A3 inference product

Atlas 200I/500 A2 inference product

Atlas training product

Atlas inference product