jnulzl / PyTorch-QATLinks
PyTorch Quantization Aware Training(QAT,量化感知训练)
☆39Updated 2 years ago
Alternatives and similar repositories for PyTorch-QAT
Users that are interested in PyTorch-QAT are comparing it to the libraries listed below
Sorting:
- TensorRT 2022 亚军方案,tensorrt加速mobilevit模型☆68Updated 3 years ago
- base quantization methods including: QAT, PTQ, per_channel, per_tensor, dorefa, lsq, adaround, omse, Histogram, bias_correction.etc☆50Updated 3 years ago
- TensorRT 2022复赛方案: 首个基于Transformer的图像重建模型MST++的TensorRT模型推断优化☆143Updated 3 years ago
- A simple tutorial of SNPE.☆178Updated 2 years ago
- A set of examples around MegEngine☆31Updated last year
- Offline Quantization Tools for Deploy.☆141Updated last year
- ☆43Updated 3 years ago
- Quantize,Pytorch,Vgg16,MobileNet☆43Updated 4 years ago
- This is 8-bit quantization sample for yolov5. Both PTQ, QAT and Partial Quantization have been implemented, and present the results based…☆109Updated 3 years ago
- 该代码与B站上的视频 https://www.bilibili.com/video/BV18L41197Uz/?spm_id_from=333.788&vd_source=eefa4b6e337f16d87d87c2c357db8ca7 相关联。☆70Updated 2 years ago
- Make RepVGG Greater Again: A Quantization-aware Approach☆28Updated last year
- 该项目实现了图像超分辨率算法ELAN的TensorRT版本。☆31Updated 3 years ago
- algorithm-cpp projects☆80Updated 3 years ago
- ☆150Updated last year
- a simple pipline of int8 quantization based on tensorrt.☆69Updated 3 years ago
- OpenPose uses Pytorch for static quantization, saving, and loading of models☆87Updated 4 years ago
- An onnx-based quantitation tool.☆71Updated last year
- PyTorch Quantization Aware Training Example☆144Updated last year
- Speed up image preprocess with cuda when handle image or tensorrt inference☆79Updated last week
- ☆26Updated 2 years ago
- ☆47Updated 2 years ago
- 高效部署:YOLO X, V3, V4, V5, V6, V7, V8, EdgeYOLO TRT推理 ™️ ,前后处理均由CUDA核函数实现 CPP/CUDA🚀☆52Updated 2 years ago
- MegEngine到其他框架的转换器☆70Updated 2 years ago
- ☆37Updated 2 years ago
- A large number of cuda/tensorrt cases . 大量案例来学习cuda/tensorrt☆157Updated 3 years ago
- This project aims to explore the deployment of Swin-Transformer based on TensorRT, including the test results of FP16 and INT8.☆172Updated 2 years ago
- ONNX2Pytorch☆165Updated 4 years ago
- yolov5 tensorrt int8量化方法汇总☆83Updated last year
- An Improved One millisecond Mobile Backbone☆147Updated 3 years ago
- Based of paper "Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference"☆64Updated 4 years ago