Search Results for "vision" - Page 6
Sort By:
Showing 271 open source projects for "vision"
View related business solutions-
$300 Free Credits to Build on Google CloudPut your $300 in credit toward real workloads, then keep building with free monthly usage for 20+ products. No commitment and no charge until you upgrade.
-
Save Up to 91% on Cloud Compute With Spot VMsRun batch jobs at 60-91% off with Spot VMs. Long-running workloads get automatic discounts with sustained use.
-
1
Uncertainty Baselines
High-quality implementations of standard and SOTA methods
Uncertainty Baselines is a collection of strong, well-documented training pipelines that make it straightforward to evaluate predictive uncertainty in modern machine learning models. Rather than offering toy scripts, it provides end-to-end recipes—data input, model architectures, training loops, evaluation metrics, and logging—so results are comparable across runs and research groups. The library spans canonical modalities and tasks, from image classification and NLP to tabular problems,... -
2
CoreNet
CoreNet: A library for training deep neural networks
...Its distributed runtime manages synchronization, load balancing, and mixed-precision computation to maximize throughput while minimizing communication bottlenecks. CoreNet integrates tightly with Apple’s proprietary ML stack and hardware, serving as the foundation for research in computer vision, language models, and multimodal systems within Apple AI. The framework includes monitoring tools, fault tolerance mechanisms, and efficient checkpointing for massive training runs. -
3
PaddleSpeech
Easy-to-use Speech Toolkit including Self-Supervised Learning model
PaddleSpeech is an open-source toolkit on PaddlePaddle platform for a variety of critical tasks in speech and audio, with state-of-art and influential models. Via the easy-to-use, efficient, flexible and scalable implementation, our vision is to empower both industrial application and academic research, including training, inference & testing modules, and deployment process. Low barriers to install, CLI, Server, and Streaming Server is available to quick-start your journey. We provide high-speed and ultra-lightweight models, and also cutting-edge technology. We provide production ready streaming asr and streaming tts system. ... -
4
CogVLM2
GPT4V-level open-source multi-modal model based on Llama3-8B
CogVLM2 is the second generation of the CogVLM vision-language model series, developed by ZhipuAI and released in 2024. Built on Meta-Llama-3-8B-Instruct, CogVLM2 significantly improves over its predecessor by providing stronger performance across multimodal benchmarks such as TextVQA, DocVQA, and ChartQA, while introducing extended context length support of up to 8K tokens and high-resolution image input up to 1344×1344. -
Build Agents and Models on One PlatformGemini Enterprise Agent Platform is Google Cloud's comprehensive platform for developers to build, scale, govern, and optimize agents and models. Choose from Google's most advanced models and third-party models like Anthropic's Claude Model Family.
-
5
CogAgent
An open sourced end-to-end VLM-based GUI Agent
CogAgent is a 9B-parameter bilingual vision-language GUI agent model based on GLM-4V-9B, trained with staged data curation, optimization, and strategy upgrades to improve perception, action prediction, and generalization across tasks. It focuses on operating real user interfaces from screenshots plus text, and follows a strict input–output format that returns structured actions, grounded operations, and optional sensitivity annotations. -
6
Lyra 2
Project Lyra: Open Generative 3D World Models
...The system evolves across versions, with newer iterations introducing long-horizon generation and improved 3D consistency across frames. It combines elements of computer vision, generative modeling, and spatial intelligence to produce dynamic and navigable virtual worlds. The architecture is designed to handle both 3D and 4D scene generation, making it suitable for applications such as simulation, gaming, and virtual environments. By emphasizing open implementations, the project provides researchers and developers with access to cutting-edge generative modeling techniques. -
7
face.evoLVe
High-Performance Face Recognition Library on PaddlePaddle & PyTorch
face.evoLVe is a high-performance face recognition library designed for research and real-world applications in computer vision. The project provides a comprehensive framework for building and training modern face recognition models using deep learning architectures. It includes components for face alignment, landmark localization, data preprocessing, and model training pipelines that allow developers to construct end-to-end facial recognition systems. The repository supports multiple neural network backbones such as ResNet, DenseNet, MobileNet, and ShuffleNet, enabling experimentation with different architectures depending on performance requirements. ... -
8
HuixiangDou
Overcoming Group Chat Scenarios with LLM-based Technical Assistance
...This design allows the system to participate in group discussions without flooding the chat with unnecessary messages. The assistant uses retrieval and ranking methods along with language model reasoning to produce accurate answers for technical topics such as computer vision and machine learning projects. It can be integrated into messaging platforms such as WeChat or other team collaboration tools to assist developer communities. -
9
AppAgent
Multimodal Agents as Smartphone Users, an LLM-based multimodal agent
...Instead of requiring backend access to application APIs, the framework interacts with apps the same way a human user would, making it compatible with a wide variety of mobile applications. AppAgent combines vision capabilities with language reasoning to understand interface elements and determine which actions are required to accomplish a task. The system also includes mechanisms for exploration and learning, allowing the agent to analyze user interface layouts and build structured knowledge about how different apps function. -
Host LLMs in Production With On-Demand GPUsDeploy your model, get an endpoint, pay only for compute time. No GPU provisioning or infrastructure management required.
-
10
Lingvo
Framework for building neural networks
Lingvo is a TensorFlow based framework focused on building and training sequence models, especially for language and speech tasks. It was originally developed for internal research and later open sourced to support reproducible experiments and shared model implementations. The framework provides a structured way to define models, input pipelines, and training configurations using a common interface for layers, which encourages reuse across different tasks. It has been used to implement state... -
11
screenshot-to-code
Drop in a screenshot and convert it to clean code
screenshot-to-code converts UI screenshots or design images into working front-end code, accelerating the path from concept to prototype. It uses modern vision-capable or code-generating models to infer layout structure, typography, and components, then outputs clean HTML/CSS (often Tailwind) or framework code. A web interface lets you upload images, tune options, and preview generated results, while a backend service orchestrates the model calls and post-processing. The tool focuses on practical developer outputs—semantic markup, reusable components, and readable classes—so the result is a starting point you can refine, not a throwaway demo. ... -
12
ML Ferret
Refer and Ground Anything Anywhere at Any Granularity
...The core idea is a hybrid region representation that mixes discrete coordinates with continuous visual features, so the model can fluidly handle “any-form” referring while maintaining precise spatial localization. The repo presents the vision-language pipeline, model assets, and paper resources that show how Ferret answers questions, follows instructions, and returns grounded outputs rather than just text. In practice, this enables tasks like “find that small red icon next to the chart and describe it” where both the linguistic reference and the visual region are ambiguous without fine spatial reasoning. -
13
Multimodal
TorchMultimodal is a PyTorch library
This project, also known as TorchMultimodal, is a PyTorch library for building, training, and experimenting with multimodal, multi-task models at scale. The library provides modular building blocks such as encoders, fusion modules, loss functions, and transformations that support combining modalities (vision, text, audio, etc.) in unified architectures. It includes a collection of ready model classes—like ALBEF, CLIP, BLIP-2, COCA, FLAVA, MDETR, and Omnivore—that serve as reference implementations you can adopt or adapt. The design emphasizes composability: you can mix and match encoder, fusion, and decoder components rather than starting from monolithic models. ... -
14
OmniParser
A simple screen parsing tool towards pure vision based GUI agent
OmniParser is a comprehensive method for parsing user interface screenshots into structured elements, significantly enhancing the ability of multimodal models like GPT-4 to generate actions accurately grounded in corresponding regions of the interface. It reliably identifies interactable icons within user interfaces and understands the semantics of various elements in a screenshot, associating intended actions with the correct screen regions. To achieve this, OmniParser curates an... -
15
tvm
Open deep learning compiler stack for cpu, gpu, etc.
Apache TVM is an open source machine learning compiler framework for CPUs, GPUs, and machine learning accelerators. It aims to enable machine learning engineers to optimize and run computations efficiently on any hardware backend. The vision of the Apache TVM Project is to host a diverse community of experts and practitioners in machine learning, compilers, and systems architecture to build an accessible, extensible, and automated open-source framework that optimizes current and emerging machine learning models for any hardware platform. Compilation of deep learning models in Keras, MXNet, PyTorch, Tensorflow, CoreML, DarkNet and more. ... -
16
Mesh R-CNN
code for Mesh R-CNN, ICCV 2019
Mesh R-CNN is a 3D reconstruction and object understanding framework developed by Facebook Research that extends Mask R-CNN into the 3D domain. Built on top of Detectron2 and PyTorch3D, Mesh R-CNN enables end-to-end 3D mesh prediction directly from single RGB images. The model learns to detect, segment, and reconstruct detailed 3D mesh representations of objects in natural images, bridging the gap between 2D perception and 3D understanding. Unlike voxel-based or point-based approaches, Mesh... -
17
UCO3D
Uncommon Objects in 3D dataset
uCO3D is a large-scale 3D vision dataset and toolkit centered on turn-table videos of everyday objects drawn from the LVIS taxonomy. It provides about 170,000 full videos per object instance rather than still frames, along with per-video annotations including object masks, calibrated camera poses, and multiple flavors of point clouds. Each sequence also ships with a precomputed 3D Gaussian Splat reconstruction, enabling fast, differentiable rendering workflows and modern implicit/point-based modeling experiments. ... -
18
fvcore
Collection of common code shared among different research projects
fvcore is a lightweight utility library that factors out common performance-minded components used across Facebook/Meta computer-vision codebases. It provides numerics and loss layers (e.g., focal loss, smooth-L1, IoU/GIoU) implemented for speed and clarity, along with initialization helpers and normalization layers for building PyTorch models. Its common modules include timers, logging, checkpoints, registry patterns, and configuration helpers that reduce boilerplate in research code. ... -
19
NVIDIA NeMo Framework
Scalable generative AI framework built for researchers and developers
NVIDIA NeMo is a scalable, cloud-native generative AI framework aimed at researchers and PyTorch developers working on large language models, multimodal models, and speech AI (ASR and TTS), with growing support for computer vision. It provides collections of domain-specific modules and reference implementations that make it easier to pre-train, fine-tune, and deploy very large models on multi-GPU and multi-node infrastructure. NeMo 2.0 introduces a Python-based configuration system, replacing YAML with more flexible, programmable configs that can be versioned and composed for different experiments. ... -
20
Qwen2.5-Omni
Capable of understanding text, audio, vision, video
Qwen2.5-Omni is an end-to-end multimodal flagship model in the Qwen series by Alibaba Cloud, designed to process multiple modalities (text, images, audio, video) and generate responses both as text and natural speech in streaming real-time. It supports “Thinker-Talker” architecture, and introduces innovations for aligning modalities over time (for example synchronizing video/audio), robust speech generation, and low-VRAM/quantized versions to make usage more accessible. It holds... -
21
OAGI Python SDK
Python SDK for the Computer Use model Lux, developed by OpenAGI
OAGI Python SDK is a Python client library for the Lux computer-use model that turns Lux into a programmable automation layer for operating human-facing software via vision and actions. It exposes the OAGI API in an ergonomic way, letting you trigger Lux in three main modes: Tasker for precise scripted sequences, Actor for fast one-shot tasks, and Thinker for open-ended, multi-step objectives. The SDK is designed around “computer use” as a paradigm, where the AI actually navigates interfaces, clicks, types, scrolls, and reads the screen through screenshots instead of only calling APIs. ... -
22
Sa2VA
Official Repo For "Sa2VA: Marrying SAM2 with LLaVA
Sa2VA is a cutting-edge open-source multi-modal large language model (MLLM) developed by ByteDance that unifies dense segmentation, visual understanding, and language-based reasoning across both images and videos. It merges the segmentation power of a state-of-the-art video segmentation model (based on SAM‑2) with the vision-language reasoning capabilities of a strong LLM backbone (derived from models like InternVL2.5 / Qwen-VL series), yielding a system that can answer questions about visual content, perform referring segmentation, and maintain temporal consistency across frames in video. With minimal instruction tuning (often one-shot), Sa2VA can handle tasks such as “segment the main subject,” “what are the objects in this scene?”... -
23
Vidi2
Large Multimodal Models for Video Understanding and Editing
Vidi is a family of large multimodal models developed for deep video understanding and editing tasks, integrating vision, audio, and language to allow sophisticated querying and manipulation of video content. It’s designed to process long-form, real-world videos and answer complex queries such as “when in this clip does X happen?” or “where in the frame is object Y during that moment?” — offering temporal retrieval, spatio-temporal grounding (i.e. locating objects over time + space), and even video question answering. ... -
24
YOLOv9
Learning What You Want to Learn Using Programmable Gradient Info
...YOLOv9 is designed for real-time detection scenarios where both accuracy and efficiency matter. It is especially relevant for researchers and engineers comparing next-generation YOLO architectures or building production computer vision systems. -
25
Grounded-Segment-Anything
Marrying Grounding DINO with Segment Anything & Stable Diffusion
Grounded-Segment-Anything is a research-oriented project that combines powerful open-set object detection with pixel-level segmentation and subsequent creative workflows, effectively enabling detection, segmentation, and high-level vision tasks guided by free-form text prompts. The core idea behind the project is to pair Grounding DINO — a zero-shot object detector that can locate objects described by natural language — with Segment Anything Model (SAM), which can produce detailed masks for objects once they are localized. This fusion lets users provide arbitrary text descriptions (e.g., “a cat, a bicycle, or a coffee mug”), have the detection model find relevant bounding boxes, and then use SAM to generate precise segmentation masks that isolate each object in the scene.
