yolo3 tensorflowyolo3 implement by tensorflow, including mobilenet_v1, mobilenet_v2
hand detectionA Light CNN based Method for Hand Detection and Orientation Estimation
LightNetLightNet: Light-weight Networks for Semantic Image Segmentation (Cityscapes and Mapillary Vistas Dataset)
ModelZoo.pytorchHands on Imagenet training. Unofficial ModelZoo project on Pytorch. MobileNetV3 Top1 75.64🌟 GhostNet1.3x 75.78🌟
MobileNetV3-TFTensorflow implementation for two new MobileNetV3 models!
pedestrian recognitionA simple human recognition api for re-ID usage, power by paper https://arxiv.org/abs/1703.07737
YOLOv5-Lite🍅🍅🍅YOLOv5-Lite: lighter, faster and easier to deploy. Evolved from yolov5 and the size of model is only 930+kb (int8) and 1.7M (fp16). It can reach 10+ FPS on the Raspberry Pi 4B when the input size is 320×320~
awesome lightweight networksThe implementation of various lightweight networks by using PyTorch. such as:MobileNetV2,MobileNeXt,GhostNet,ParNet,MobileViT、AdderNet,ShuffleNetV1-V2,LCNet,ConvNeXt,etc. ⭐⭐⭐⭐⭐
sparsezooNeural network model repository for highly sparse and sparse-quantized models with matching sparsification recipes
Maix-LogoClassifierA simple logo classifier developed using Maixduino framework and PlatfomIO, to run on K210 MCU on Sipeed's Maix dev board.
CRNN-OCR-liteLightweight CRNN for OCR (including handwritten text) with depthwise separable convolutions and spatial transformer module [keras+tf]
RFBNetReceptive Field Block Net for Accurate and Fast Object Detection, ECCV 2018
Voice-MLMobileNet trained with VoxCeleb dataset and used for voice verification
mobilenextnon-official PyTorch implementation of MobileNeXt from paper [Rethinking Bottleneck Structure for Efficient Mobile Network Design]