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

This project uses PyTorch to classify bone fractures. As well as fine-tuning some famous CNN architectures (like VGG 19, MobileNetV3, RegNet,...), we designed our own architecture. Additionally, we used Transformer architectures (such as Vision Transformer and Swin Transformer). This dataset is Bone Fracture Multi-Region X-ray, available on Kaggle.

Implementation of popular deep learning networks with TensorRT network definition API

MobileNetV3 SSD的简洁版本

Image Captioning With MobileNet-LLaMA 3

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

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.

Click the link below to checkout the website

Recipely is an Android Application simplify all the use case of a chef. Build with Modern Android development tool (Kotlin , Jetpack Compose, Coroutine, Hilt/Dagger 2, Room, MVVM, Clean Architecture, Material Component. Intergrated with ML using MobilenetV3

Repository containing Code and other materials for the Research Project on Rock Type Classification

6DOF机械臂上，自然语言指令控制，MobileNetV3识别定位，视觉伺服PID抓取

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

How AI enhances parking management. In a team of four, we leveraged deep CNNs to create a system that detects (YOLO) and classifies (ensemble of SqueezeNet and ResNet) parking spots as free or occupied from images obtained by common surveillance cameras. It is able to employ pre-installed cameras, optimizing space utilization and reducing costs.

Classification models with pretrained backbones. PyTorch. Easy to use baseline to train your models

Habiba Omran Thesis

EfficientNet, MobileNetV3, MobileNetV2, MixNet, etc in JAX w/ Flax Linen and Objax

A sustainable living app that turns trash into treasure.

GUI testing automation and testing tools automation attempt

By comparing the performance of 24 custom trained models with various configurations, I aim to identify the most effective model architecture and configuration for accurate gel electrophoresis image classification.