onnxruntime/onnxruntime/python/tools/quantization
Justin Chu 938e2136c6
Enable pylint and numpy rules (#15218)
### Description

Enable pylint and numpy rules

### Motivation and Context

Modernize numpy usage and enable more quality checks
2023-03-27 20:37:53 -07:00
..
CalTableFlatBuffers Adopt linrtunner as the linting tool - take 2 (#15085) 2023-03-24 15:29:03 -07:00
operators Adopt linrtunner as the linting tool - take 2 (#15085) 2023-03-24 15:29:03 -07:00
__init__.py Adopt linrtunner as the linting tool - take 2 (#15085) 2023-03-24 15:29:03 -07:00
calibrate.py Enable pylint and numpy rules (#15218) 2023-03-27 20:37:53 -07:00
onnx_model.py Enable pylint and numpy rules (#15218) 2023-03-27 20:37:53 -07:00
onnx_quantizer.py Enable pylint and numpy rules (#15218) 2023-03-27 20:37:53 -07:00
preprocess.py fix python import sequence warning (#12864) 2022-09-07 09:53:39 -07:00
qdq_loss_debug.py Adopt linrtunner as the linting tool - take 2 (#15085) 2023-03-24 15:29:03 -07:00
qdq_quantizer.py Adopt linrtunner as the linting tool - take 2 (#15085) 2023-03-24 15:29:03 -07:00
quant_utils.py Adopt linrtunner as the linting tool - take 2 (#15085) 2023-03-24 15:29:03 -07:00
quantize.py Add InstanceNormalization operator to QNN EP (#14867) 2023-03-10 14:42:41 -08:00
README.md
registry.py Adopt linrtunner as the linting tool - take 2 (#15085) 2023-03-24 15:29:03 -07:00
shape_inference.py Adopt linrtunner as the linting tool - take 2 (#15085) 2023-03-24 15:29:03 -07:00

Quantization Tool

This tool can be used to quantize select ONNX models. Support is based on operators in the model. Please refer to https://onnxruntime.ai/docs/performance/quantization.html for usage details and https://github.com/microsoft/onnxruntime-inference-examples/tree/main/quantization for examples.