AMCT_LOG_FILE_LEVEL

Description

Sets the level of messages in the amct_pytorch.log file for the PyTorch framework, amct_caffe.log for the Caffe framework, and amct_onnx.log for the ONNX framework, and sets the level of messages in the log file generated by the corresponding quantization layer when the model for accuracy simulation is generated.

Possible values are:

• DEBUG: DEBUG, INFO, WARNING, and ERROR logs. Detailed process messages, quantizable layer, and corresponding processing phase (fusion, parameter quantization, or activation quantization)
• INFO (default): INFO, WARNING, and ERROR logs. Brief quantization processing messages, including the quantization phase.
• WARNING: WARNING and ERROR logs. Warning messages during quantization.
• ERROR: ERROR logs. Error messages during quantization.

Example

export AMCT_LOG_FILE_LEVEL=INFO

Restrictions

None

Applicability

Atlas A2 training products/Atlas A2 inference products

Atlas A3 training products/Atlas A3 inference products

Atlas 200I/500 A2 inference products

Atlas training products

Atlas inference products