Culturenotes / Network-Slimming
Network reproduction and expansion based on Learning Efficient Convolutional Networks Through Network Slimming (ICCV 2017).
☆23Updated 2 years ago
Related projects: ⓘ
- 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
- RM Operation can equivalently convert ResNet to VGG, which is better for pruning; and can help RepVGG perform better when the depth is la…☆209Updated last year
- ResRep: Lossless CNN Pruning via Decoupling Remembering and Forgetting (ICCV 2021)☆287Updated last year
- 模型压缩demo（剪枝、量化、知识蒸馏）☆62Updated 4 years ago
- Try out different pruning-approaches on lightweight Backbones.☆142Updated 4 years ago
- An extension version of our paper accepted by CVPR 2020, Oral -- HRank: Filter Pruning using High-Rank Feature Map☆146Updated 3 years ago
- An Object Detection Knowledge Distillation framework powered by pytorch, now having SSD and yolov5.☆214Updated 2 years ago
- ☆32Updated 3 years ago
- 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☆234Updated last year
- Official Repsoitory for "Activate or Not: Learning Customized Activation." [CVPR 2021]☆203Updated 3 years ago
- ghostnet_cifar10☆116Updated 3 years ago
- Pytorch implementation of our paper accepted by CVPR 2020 (Oral) -- HRank: Filter Pruning using High-Rank Feature Map☆250Updated 3 years ago
- A compression tool based on distiller☆15Updated 3 years ago
- An Improved One millisecond Mobile Backbone☆140Updated 2 years ago
- ☆134Updated last year
- 对 YOLOv3 做模型剪枝（network slimming），对于 oxford hand 数据集（因项目需要），模型剪枝后的参数量减少 80%，Infer 的速度达到原来 2 倍，mAP 基本不变☆12Updated 5 years ago
- MobileNetV3 based SSD-lite implementation in Pytorch☆97Updated 5 years ago
- ☆14Updated 3 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
- Learning both Weights and Connections for Efficient Neural Networks https://arxiv.org/abs/1506.02626☆18Updated 3 years ago
- Pytorch Implementationg of “Learning Efficient Convolutional Networks through Network Slimming”☆76Updated 5 years ago
- Base to channel pruned to ResNet18 model☆143Updated last year
- Diverse Branch Block: Building a Convolution as an Inception-like Unit☆317Updated last year
- network slimming with pytorch☆24Updated 4 years ago
- RepVGG TensorRT int8 量化，实测推理不到1ms一帧！☆61Updated 3 years ago
- Personal Pytorch toy script.☆66Updated 2 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☆45Updated 3 years ago
- A PyTorch implementation of SSDLite on COCO☆84Updated 3 years ago
- ☆330Updated 2 years ago
- [ IJCAI-20 ] Split to Be Slim: An Overlooked Redundancy in Vanilla Convolution☆129Updated 4 years ago