Make Structured Pruning Methods Smooth and Adaptive: Decay Pruning Method (DPM) is a novel smooth and dynamic pruning approach, that can be seemingly integrated with various existing structured pruning methods, providing significant improvement.

Code for paper "Channel Pruning Guided by Spatial and Channel Attention for DNNs in Intelligent Edge Computing"

🌠 Enhanced Network Compression Through Tensor Decompositions and Pruning

Channel Pruning for Accelerating Very Deep Neural Networks (ICCV'17)

[ECCV 2018] AMC: AutoML for Model Compression and Acceleration on Mobile Devices

对人像抠图模型MODNet进行滤波器级别的剪枝，结合自适应与固定比例策略。

Compact image style transfer with channel and xor losses

GNN-RL Compression: Topology-Aware Network Pruning using Multi-stage Graph Embedding and Reinforcement Learning

Official PyTorch implementation of "Lightweight Alpha Matting Network Using Distillation-Based Channel Pruning" (Asian Conference on Computer Vision 2022)

在 oxford hand 数据集上对 YOLOv3 做模型剪枝（network slimming）

[NIPS 2016] Learning Structured Sparsity in Deep Neural Networks

[ICCV 2017] Learning Efficient Convolutional Networks through Network Slimming

Official repository for the research article "Pruning vs XNOR-Net: A ComprehensiveStudy on Deep Learning for AudioClassification in Microcontrollers"

This repo shows some code about the pruning strategy in the paper "A Channel-level Pruning Strategy for Convolutional Neural Networks". https://teacher.bupt.edu.cn/zhuchuang/en/index.htm

Cheng-Hao Tu, Jia-Hong Lee, Yi-Ming Chan and Chu-Song Chen, "Pruning Depthwise Separable Convolutions for MobileNet Compression," International Joint Conference on Neural Networks, IJCNN 2020, July 2020.

Network Slimming (Pytorch) (ICCV 2017)

A PyTorch Implementation of Feature Boosting and Suppression

pruning with optimal thresholding or network slimming for pytorch models, support user defined models with Linear/Conv(groups=1)/BN

An implementation of Channel Pruning on face recognition algorithm Sphereface.

Code for the NuerIPS'19 paper "Gate Decorator: Global Filter Pruning Method for Accelerating Deep Convolutional Neural Networks"