Showing 1361-1380 of 2,275 projects
A self-supervised learning framework for learning general human representations from unlabeled images.
This is a Jupyter Notebook project focused on biological foundation modeling from molecular to genome scale.
Adapts Meta AI's Segment Anything model to downstream tasks using adapters and prompts.
ChainerCV is a Python library for deep learning in computer vision tasks such as object detection and segmentation.
Non-official implementation of the CBAM paper, a convolutional block attention module for neural networks.
CCNet is a semantic segmentation library that uses Criss-Cross Attention to improve scene parsing performance.
This PyTorch-based repository provides tools for developing image captioning models.
A Python library for benchmarking multiple object trackers (MOT) that can be used in computer vision applications.
Real-time AI assistant for Ray-Ban smart glasses using vision, voice, and agentic actions via Gemini Live.
A next-gen fast plotting library for scientific visualization running on WGPU and the pygfx rendering engine.
A PyTorch library that provides Vision Transformer (ViT) adapters for dense prediction tasks like object detection and semantic segmentation.
A flexible Python library for optical character recognition (OCR) using the CRAFT text detector and Keras CRNN recognition model.
An open-source tool for annotating Chinese text corpus, useful for NLP and text analysis projects.
Open-source RPA framework for Python and Robot Framework, focused on automation and AI-powered document processing.
An open-source library for training and running state-of-the-art diffusion models in Python.
Lightweight, tightly coupled lidar-inertial odometry using parallel sparse incremental voxels.
A Python library that provides native multimodal models for building world-learning AI systems.
Bottom-up attention model for image captioning and visual question answering, built on Faster R-CNN and Visual Genome.
PixelNeRF is a Python library for training and using NeRF models for neural volumetric rendering.
An open-source image annotation tool for computer vision tasks.
Get weekly updates on trending AI coding tools and projects.