#Image Classification

Logo of DenseNet
DenseNet
DenseNet is a network architecture that efficiently connects layers within dense blocks, optimizing learning and reducing parameters. It excels in accuracy on CIFAR10/100 and ImageNet using fewer resources. Versatile implementations in PyTorch and TensorFlow, coupled with memory-efficient features, make it ideal for various applications. Comprehensive documentation and pre-trained models are available for developers seeking adaptable solutions in image classification.
Logo of ml-fastvit
ml-fastvit
This repository features FastViT, a rapid hybrid vision transformer utilizing structural reparameterization to boost image classification accuracy. Models have been trained on ImageNet-1K and benchmarked for latency on an iPhone 12 Pro via the ModelBench app. The repository includes setup guides for configuring environments, training, and evaluating models, along with scripts for implementation. It provides a varied collection of pre-trained models tailored for classification tasks, including the option for knowledge distillation. Comprehensive dataset preparation and model export instructions are available, making this a versatile tool for tasks ranging from training to fine-tuning in machine learning.
Logo of Windows-Machine-Learning
Windows-Machine-Learning
Discover a machine learning inference API optimized for real-time use with ONNX Runtime and DirectML. Windows Machine Learning offers resources and samples to incorporate ML features into Windows applications, catering to frameworks and real-time gaming needs. Leverage Windows SDK or a NuGet package for inferencing, enhance models, and verify with tools such as WinMLRunner and WinML Dashboard. Explore extensive model samples, tutorials, and advanced use-cases for ML integration in UWP and desktop apps.
Logo of techniques
techniques
Discover deep learning techniques structured for satellite and aerial image analysis, covering classification, segmentation, and object detection among others. This resource details architectures, models, and algorithms devised to tackle the unique challenges posed by large image sizes and varied object classes. Uncover methods such as regression, cloud and change detection, time series analysis, and crop classification, emphasizing practical applications in remote sensing.
Logo of MIC
MIC
Masked Image Consistency (MIC) advances unsupervised domain adaptation by focusing on spatial context relations in target domains. Through consistency between masked image predictions and pseudo-labels, MIC enhances visual recognition performance in tasks like image classification, semantic segmentation, and object detection. Suitable for various UDA challenges, including synthetic-to-real and clear-to-adverse-weather scenarios, MIC achieves high performance in benchmarks such as GTA to Cityscapes and VisDA-2017, contributing significantly to domain adaptation research.
Logo of computervision-recipes
computervision-recipes
This repository provides comprehensive examples and best practices for building computer vision systems, utilizing cutting-edge algorithms and neural network architectures. It includes tools to improve, assess, and scale models by incorporating advanced libraries, thus aiding data scientists and machine learning engineers in expediting real-world projects. The focus is on efficient time-to-market strategies, supporting various tasks such as image classification and action recognition with deployment capabilities on cloud services like Azure, using Jupyter notebooks and PyTorch for demonstration.
Logo of Awesome-Backbones
Awesome-Backbones
This open-source project provides a wide range of image classification backbones compatible with Python 3.6+ and PyTorch 1.7.1+. Explore models like MobileViT and EfficientNetV2, featuring pre-trained weights for seamless integration. Tutorials on setup, data handling, and evaluation assist in enhancing training efficacy and stability. Suitable for developers aiming for adaptable and strong frameworks in AI-powered image assessment.
Logo of Awesome-Geospatial
Awesome-Geospatial
Discover a diverse assortment of geospatial tools, including database extensions and GIS systems, featuring technologies like PostGIS, ArcGIS, Leaflet, and CesiumJS. These resources aid in geographic data management and analysis for academic, commercial, or personal projects across multiple platforms and languages.
Logo of Vision-RWKV
Vision-RWKV
Vision-RWKV is an AI project offering efficient and scalable solutions for visual perception through RWKV-like architectures. It excels in high-resolution image processing with a global receptive field, achieving superior performance and stability, especially after pre-training on large datasets. Outperforming window-based and global attention ViTs in classification tasks, it boasts lower flops and faster speeds. Recent support for RWKV6 further boosts classification performance. The project provides multiple pre-trained models on ImageNet, suited for object detection and semantic segmentation, with straightforward access to checkpoints and configuration files for customization.