tangchen2 / Model-Compression
Model Compression 1. Pruning(BN Pruning) 2. Knowledge Distillation (Hinton) 3. Quantization (MNN) 4. Deployment (MNN)
☆79Updated 4 years ago
Alternatives and similar repositories for Model-Compression:
Users that are interested in Model-Compression are comparing it to the libraries listed below
- Pytorch-->onnx-->TensorRT; CUDA11, CUDNN8, TensorRT8☆208Updated last year
- www.giantpandacv.com☆147Updated 9 months ago
- YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite☆67Updated 3 years ago
- 比ResNet更强的RepVGG，结构重参数化，推理部署一路3x3卷积到底，详细的代码讲解，欢迎star☆46Updated 3 years ago
- model compression based on pytorch (1、quantization: 8/4/2bits(dorefa)、ternary/binary value(twn/bnn/xnor-net)；2、 pruning: normal、regular a…☆170Updated 4 years ago
- TensorRT 2022 亚军方案，tensorrt加速mobilevit模型☆62Updated 2 years ago
- 模型压缩demo（剪枝、量化、知识蒸馏）☆71Updated 4 years ago
- RM Operation can equivalently convert ResNet to VGG, which is better for pruning; and can help RepVGG perform better when the depth is la…☆212Updated last year
- 针对pytorch模型的自动化模型结构分析和修改工具集，包含自动分析模型结构的模型压缩算法库☆250Updated last year
- An Object Detection Knowledge Distillation framework powered by pytorch, now having SSD and yolov5.☆222Updated 3 years ago
- Official repo of RepOptimizers and RepOpt-VGG☆261Updated 2 years ago
- pytorch AutoSlim tools，支持三行代码对pytorch模型进行剪枝压缩☆38Updated 3 years ago
- An Improved One millisecond Mobile Backbone☆144Updated 2 years ago
- yolov5 5.0 version distillation || yolov5 5.0版本知识蒸馏，yolov5l >> yolov5s☆157Updated 3 years ago
- ☆32Updated 4 years ago
- ☆91Updated 3 years ago
- simplest implementation of yolo v1 via pytorch☆43Updated 4 years ago
- ResRep: Lossless CNN Pruning via Decoupling Remembering and Forgetting (ICCV 2021)☆294Updated 2 years ago
- [T-PAMI'23] PAGCP for the compression of YOLOv5☆117Updated last year
- Yolov5 distillation training | Yolov5知识蒸馏训练，支持训练自己的数据☆212Updated 2 years ago
- tensorrt int8 量化yolov5 onnx模型☆181Updated 3 years ago
- Focal and Global Knowledge Distillation for Detectors (CVPR 2022)☆367Updated 2 years ago
- ☆170Updated 2 years ago
- RepGhost: A Hardware-Efficient Ghost Module via Re-parameterization☆175Updated last year
- OpenPose uses Pytorch for static quantization, saving, and loading of models☆85Updated 3 years ago
- yolov5目标检测模型的知识蒸馏（基于响应的蒸馏）☆97Updated 3 years ago
- ☆132Updated last year
- 基于NanoDet项目进行小裁剪，专门用来实现PyTorch 版本的代码，下载直接能使用，支持图片、视频文件、摄像头实时目标检测。☆149Updated 4 years ago
- algorithm-cpp projects☆79Updated 2 years ago
- Using model pruning method to obtain compact models Pruned-YOLOv5 based on YOLOv5.☆58Updated 3 years ago