训练量化QAT 常用参考链接

3.参考文档

pytorch-quantization master documentation

https://developer.nvidia.com/zh-cn/blog/chieving-fp32-accuracy-for-int8-inference-using-quantization-aware-training-with-tensorrt/

https://docs.nvidia.com/deeplearning/frameworks/tf-trt-user-guide/index.html#profiling-tools

pytorch onnx onnxruntime tensorrt踩坑 各种问题 - 简书

TensorRT/tools/pytorch-quantization/examples at master · NVIDIA/TensorRT · GitHub

TensorRT/tools/pytorch-quantization/docs/source/tutorials/quant_resnet50.rst at master · NVIDIA/TensorRT · GitHub

https://medium.com/@DeeperAndCheaper/quantization-achieve-accuracy-drop-to-near-zero-yolov8-qat-x2-speed-up-on-your-jetson-orin-nano-e178c4d8a5e3

4.参考代码

Tensorrt: TensorRT/samples/python at release/10.1 · NVIDIA/TensorRT · GitHub

Pytorch: TensorRT/examples/int8/training/vgg16 at main · pytorch/TensorRT · GitHub

pytorch文档解释：Deploying Quantization Aware Trained models in INT8 using Torch-TensorRT — Torch-TensorRT v1.3.0 documentation

GitHub - NVIDIA-AI-IOT/yolo_deepstream: yolo model qat and deploy with deepstream&tensorrt