YOLOv5 Series Multi-backbone(TPH-YOLOv5, Ghostnet, ShuffleNetv2, Mobilenetv3Small, EfficientNetLite, PP-LCNet, SwinTransformer YOLO), Module(CBAM, DCN), Pruning (EagleEye, Network Slimming) and Qua…

D2Go is a toolkit for efficient deep learning

YOLOv5 in PyTorch > ONNX > CoreML > iOS

ncnn is a high-performance neural network inference framework optimized for the mobile platform

The pytorch re-implement of the official efficientdet with SOTA performance in real time and pretrained weights.

Examples for using ONNX Runtime for machine learning inferencing.

TensorFlow examples

Pytorch implementation of RetinaNet object detection.

mobilev2-yolov5s剪枝、蒸馏，支持ncnn，tensorRT部署。ultra-light but better performence！

Implementation EfficientDet: Scalable and Efficient Object Detection in PyTorch

Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Acceleration (CVPR 2019 Oral)

Pruning Filter in Filter(NeurIPS2020)

PyTorch android examples of usage in applications

Examples of Tensorflow Lite on Android

Data Science Using Python

Testing ONNX Runtime with android NNAPI

yolov3 yolov4 channel and layer pruning, Knowledge Distillation 层剪枝，通道剪枝，知识蒸馏

(Pretrained weights provided) EfficientDet: Scalable and Efficient Object Detection implementation by Signatrix GmbH

For the paper of 'Real-time mango detection on CPU using pruned YOLO network'

提供对YOLOv3及Tiny的多种剪枝版本，以适应不同的需求。

Soft Filter Pruning for Accelerating Deep Convolutional Neural Networks