THU-MIG / torch-model-compression
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
☆251Updated 2 years ago
Alternatives and similar repositories for torch-model-compression:
Users that are interested in torch-model-compression are comparing it to the libraries listed below
- 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
- Pytorch-->onnx-->TensorRT; CUDA11, CUDNN8, TensorRT8☆208Updated last year
- pytorch AutoSlim tools，支持三行代码对pytorch模型进行剪枝压缩☆38Updated 4 years ago
- www.giantpandacv.com☆148Updated 10 months ago
- Model Compression 1. Pruning(BN Pruning) 2. Knowledge Distillation (Hinton) 3. Quantization (MNN) 4. Deployment (MNN)☆79Updated 4 years ago
- An Object Detection Knowledge Distillation framework powered by pytorch, now having SSD and yolov5.☆223Updated 3 years ago
- ONNX2Pytorch☆161Updated 4 years ago
- A simple network quantization demo using pytorch from scratch.☆528Updated last year
- An Improved One millisecond Mobile Backbone☆145Updated 2 years ago
- ResRep: Lossless CNN Pruning via Decoupling Remembering and Forgetting (ICCV 2021)☆294Updated 2 years ago
- Model Quantization Benchmark☆801Updated 2 weeks 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…☆211Updated last year
- A nnie quantization aware training tool on pytorch.☆239Updated 4 years ago
- 模型压缩demo（剪枝、量化、知识蒸馏）☆74Updated 5 years ago
- ☆99Updated 3 years ago
- tensorrt int8 量化yolov5 onnx模型☆183Updated 4 years ago
- Everything in Torch Fx☆341Updated 10 months ago
- Pytorch and ncnn implementation of PPYOLOE、YOLOX、PPYOLO、PPYOLOv2、PicoDet and so on.☆296Updated last year
- OpenPose uses Pytorch for static quantization, saving, and loading of models☆87Updated 3 years ago
- Neural Network Blocks - Collect all kinds of fancy model blocks for you to build more powerful neural network model.☆240Updated 2 years ago
- mobilev2-yolov5s剪枝、蒸馏，支持ncnn，tensorRT部署。ultra-light but better performence！☆844Updated 2 years ago
- EasyQuant(EQ) is an efficient and simple post-training quantization method via effectively optimizing the scales of weights and activatio…☆399Updated 2 years ago
- B站Efficient-Neural-Network学习分享的配套代码☆298Updated 3 years ago
- Offline Quantization Tools for Deploy.☆127Updated last year
- yolov5 prune，Support V2, V3, V4 and V6 versions of yolov5☆575Updated 3 years ago
- Network reproduction and expansion based on Learning Efficient Convolutional Networks Through Network Slimming (ICCV 2017).☆24Updated 3 years ago
- Official repo of RepOptimizers and RepOpt-VGG☆263Updated 2 years ago
- 服务侧深度学习部署案例☆451Updated 5 years ago
- yolov5 5.0 version distillation || yolov5 5.0版本知识蒸馏，yolov5l >> yolov5s☆160Updated 3 years ago
- pytorch -> onnx -> caffe, pytorch to caffe, or other deep learning framework to onnx and onnx to caffe.☆161Updated 4 years ago