🍅🍅🍅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~

Light-weight Single Person Pose Estimator

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

face image illumination quality assessment implement by pytorch

LightNet++: Boosted Light-weighted Networks for Real-time Semantic Segmentation

Implementation of ShuffleNetV2 for pytorch

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

Multi-backbone, Prune, Quantization, KD

QuarkDet lightweight object detection in PyTorch .Real-Time Object Detection on Mobile Devices.

Tensorflow ShuffleNet v2 implementation

Real-time fire detection in image/video/webcam using a convolutional neural network (deep learning) - from our ICMLA 2020 paper (Thomson / Bhowmik / Breckon)

Train/Eval the popular network by TF-Slim,include mobilenet/shufflenet/squeezenet/resnet/inception/vgg/alexnet

VoVNet, MobileNet, ShuffleNet, HarDNet, GhostNet, EfficientNet backbone networks and SKU-110K dataset for detectron2

A PyTorch Implementation of ShuffleFaceNet.

implement the shufflenetv2, and test the performance

ShuffleNetV2 by Pytorch and NCNN

ShuffleNet_V2 for ncnn framework

a tensorflow based implementation of ShuffleNetV2 on the Tiny ImageNet dataset

Implementation of MobileNet, MobileNetv2, ShuffleNet, ShuffleNetv2, EfficientNet in Pytorch.

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

Tensorrt implementation of face key points

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

Build AI model to classify beverages for blind individuals

Lightweight deep learning approach for IoT malware detection achieving 95.15% F1-score. Compares CNN, MobileNetV3, and ShuffleNetV2 on network traffic visualization with SMOTE-balanced dataset (9 malware classes + benign).

A replication of "Global Perception-Based Robust Parking Space Detection Using a Low-Cost Camera"

Implement deep learning model used pytorch for serving

Image Classification with On-Device Inference, built with Flutter, AI model runs on mobile cpu

AI Track's Exercise to create a basic CNN to recognize different animals from the Chinese Zodiac

Optimizing DNN Operators on Mobile GPUs

Dự án Trafic-Monitoring nhận diện phương tiện, phân loại hãng xe và OCR biển số bằng C++ với ONNX Runtime + OpenCV.