A automatic pipeline for SnapML quantization
Project description
# SnapML Automatic Quantization Pipeline
## Installation:
pip install git+ssh://git@github.sc-corp.net/Snapchat/snapml_auto_quantization.git –upgrade
## Uninstallation:
pip uninstall snapml_auto_quantization
## Exporting ONNX Models:
- torch.onnx.export(net, inputs, onnx_path, verbose=verbose,
input_names=input_names, output_names=output_names, keep_initializers_as_inputs=True, operator_export_type= torch.onnx.OperatorExportTypes.ONNX_ATEN_FALLBACK, opset_version=None)
## API Documenation
[Documentation](https://github.sc-corp.net/pages/Snapchat/snapml_auto_quantization/)
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
File details
Details for the file snapml_auto_quantization-0.0.5.tar.gz.
File metadata
- Download URL: snapml_auto_quantization-0.0.5.tar.gz
- Upload date:
- Size: 16.5 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.1 CPython/3.9.1
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 6909749ef3f2d56766f03b7398f8e1b996825e8bb957e3f2b6b82feab7b3f384 |
|
| MD5 | 0fde615b3e9b3fad7683cc84a7eef5bf |
|
| BLAKE2b-256 | a2e83c7b3fe10ae1dee32229c383e2e5723070009a0ed95a0cf289608253a5f7 |
