The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more

Implementation of popular deep learning networks with TensorRT network definition API

Robust realtime face and facial landmark tracking on CPU with Unity integration

This is a pytorch repository of YOLOv4, attentive YOLOv4 and mobilenet YOLOv4 with PASCAL VOC and COCO

Pretrained EfficientNet, EfficientNet-Lite, MixNet, MobileNetV3 / V2, MNASNet A1 and B1, FBNet, Single-Path NAS

🍅 Deploy ncnn on mobile phones. Support Android and iOS. 移动端ncnn部署，支持Android与iOS。

High level network definitions with pre-trained weights in TensorFlow

MobileNetV3 in pytorch and ImageNet pretrained models

MEAL V2: Boosting Vanilla ResNet-50 to 80%+ Top-1 Accuracy on ImageNet without Tricks. In NeurIPS 2020 workshop.

74.3% MobileNetV3-Large and 67.2% MobileNetV3-Small model on ImageNet

[CVPR2020] GhostNet: More Features from Cheap Operations

YOLO ModelCompression MultidatasetTraining

📸 PyTorch implementation of MobileNetV3 for real-time semantic segmentation, with pretrained weights & state-of-the-art performance

This repository aims at providing efficient CNNs for Audio Tagging. We provide AudioSet pre-trained models ready for downstream training and extraction of audio embeddings.

GameAssist是一个AI游戏助手，结合OpenCv、OpenCvSharp4、ssd_mobilenet_v3等技术，对游戏对象进行识别，支持自动瞄准/自动开枪等功能，提升玩家的游戏体验

Implementing Searching for MobileNetV3 paper using Pytorch

Yolov5/Yolov4/ Yolov3/ Yolo_tiny in tensorflow

MobileNetV3-SSD for object detection and implementation in PyTorch

Human action classification system with pose-based (MediaPipe) and video-based (3D CNN) models. Features 100+ architectures for real-time pose classification and temporal models pretrained on UCF-101/HMDB51.

A Keras implementation of MobileNetV3.