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

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

Network Slimming (Pytorch) (ICCV 2017)

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

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

Mayo: Auto-generation of hardware-friendly deep neural networks. Dynamic Channel Pruning: Feature Boosting and Suppression.

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

An implementation of Channel Pruning on face recognition algorithm Sphereface.

No description provided.

ChainerPruner: Channel Pruning framework for Chainer

[NIPS 2016] Learning Structured Sparsity in Deep Neural Networks

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

A PyTorch Implementation of Feature Boosting and Suppression

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.

:stars: Enhanced Network Compression Through Tensor Decompositions and Pruning

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

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

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。

Single shot object detection in PyTorch

[ICCV 2017] Learning Efficient Convolutional Networks through Network Slimming

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.

渠道获取

An re-implementation of resnet18 network slimming

Code for "Characterising Across Stack Optimisations for Deep Convolutional Neural Networks"

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

Compact image style transfer with channel and xor losses