[yolov5 v7.0][WIDER FACE][ECCV 2022]YOLO5Face: Why Reinventing a Face Detector

A multi task neural network implemented from scratch, performing object detection with SSD and semantic segmentation with DeeplabV3+ simultaneosly!

This repository contains the source code of our work on designing efficient CNNs for computer vision

Optimizing DNN Operators on Mobile GPUs

🍅🍅🍅YOLOv5-Lite: Evolved from yolov5 and the size of model is only 900+kb (int8) and 1.7M (fp16). Reach 15 FPS on the Raspberry Pi 4B~

This is a project focused on identifying the presence of pneumonia in chest X-ray images. Each image can be classified into one of three categories: Bacterial Pneumonia, Viral Pneumonia, or Normal.

Various codes and scripts used during AI research, all neatly organised

Light-weight Single Person Pose Estimator

A notebook to learn the use of CNNs and ShuffleNet

Build AI model to classify beverages for blind individuals

face image illumination quality assessment implement by pytorch

Leaf Disease multi-class image classification using deep learning architectures implemented in PyTorch

Project Land Cover Classification using ShuffleNetV2

Implement deep learning model used pytorch for serving

A PyTorch Implementation of ShuffleFaceNet.

Implement deep learning model used pytorch for serving

PyTorch implementation for 3D CNN models for medical image data (1 channel gray scale images).

Multi-backbone, Prune, Quantization, KD

Implementation of ShuffleNetV2 for pytorch

ShuffleNet_V2 for ncnn framework