Search Results for "performance"
Sort By:
Showing 29 open source projects for "performance"
View related business solutions-
Ship Agents FasterGemini Enterprise Agent Platform lets you rapidly build, scale, govern and optimize production-ready agents grounded in your organization's data. The platform enables developers to build custom or pre-built agents for virtually any use case. New customers get $300 in free credits.
-
$300 Free Credits to Build on Google CloudStart your next project with $300 in free Google Cloud credit. Spin up VMs, run containers, query petabytes in BigQuery, or build agents with Gemini Enterprise Agent Platform. Once your credits are used, keep building with 20+ always-free tier products including Compute Engine, Cloud Storage, GKE, and Cloud Run functions. No commitment required—just sign up and start building.
-
1
OpenVINO
OpenVINO™ Toolkit repository
OpenVINO™ is an open-source toolkit for optimizing and deploying AI inference. Boost deep learning performance in computer vision, automatic speech recognition, natural language processing and other common tasks. Use models trained with popular frameworks like TensorFlow, PyTorch and more. Reduce resource demands and efficiently deploy on a range of Intel® platforms from edge to cloud. This open-source version includes several components: namely Model Optimizer, OpenVINO™ Runtime, Post-Training Optimization Tool, as well as CPU, GPU, MYRIAD, multi device and heterogeneous plugins to accelerate deep learning inferencing on Intel® CPUs and Intel® Processor Graphics. ... -
2
Albumentations
Fast image augmentation library and an easy-to-use wrapper
Albumentations is a computer vision tool that boosts the performance of deep convolutional neural networks. Albumentations is a Python library for fast and flexible image augmentations. Albumentations efficiently implements a rich variety of image transform operations that are optimized for performance, and does so while providing a concise, yet powerful image augmentation interface for different computer vision tasks, including object classification, segmentation, and detection. ... -
3
ArrayFire
ArrayFire, a general purpose GPU library
...The library serves users in every technical computing market. Data structures in ArrayFire are smartly managed to avoid costly memory transfers and to take advantage of each performance feature provided by the underlying hardware. The community of ArrayFire developers invites you to build with us if you're interested and able to write top performing tensor functions. Together we can fulfill The ArrayFire Mission under an excellent Code of Conduct that promotes a respectful and friendly building experience. Rigorous benchmarks and tests ensuring top performance and numerical accuracy. ... -
4
SAM 2
The repository provides code for running inference with SAM 2
SAM2 is a next-generation version of the Segment Anything Model (SAM), designed to improve performance, generalization, and efficiency in promptable image segmentation tasks. It retains the core promptable interface—accepting points, boxes, or masks—but incorporates architectural and training enhancements to produce higher-fidelity masks, better boundary adherence, and robustness to complex scenes. The updated model is optimized for faster inference and lower memory use, enabling real-time interactivity even on larger images or constrained hardware. ... -
AI-powered service management for IT and enterprise teamsGive your IT, operations, and business teams the ability to deliver exceptional services—without the complexity. Maximize operational efficiency with refreshingly simple, AI-powered Freshservice.
-
5
Colossal-AI
Making large AI models cheaper, faster and more accessible
The Transformer architecture has improved the performance of deep learning models in domains such as Computer Vision and Natural Language Processing. Together with better performance come larger model sizes. This imposes challenges to the memory wall of the current accelerator hardware such as GPU. It is never ideal to train large models such as Vision Transformer, BERT, and GPT on a single GPU or a single machine. -
6
Image Fusion
Deep Learning-based Image Fusion: A Survey
...The repository includes a “General Evaluation Metric” subfolder containing objective fusion metrics. It is not a single monolithic tool, but rather a curated reference and aggregation of methods, code and performance comparisons in the domain of image fusion. Survey style description of method taxonomy, architectures, loss types. Compilation of many state-of-the-art image fusion methods (infrared + visible, multi-focus, multi-exposure). Survey style description of method taxonomy, architectures, loss types. -
7
FiftyOne
The open-source tool for building high-quality datasets
...FiftyOne supercharges your machine learning workflows by enabling you to visualize datasets and interpret models faster and more effectively. Improving data quality and understanding your model’s failure modes are the most impactful ways to boost the performance of your model. FiftyOne provides the building blocks for optimizing your dataset analysis pipeline. Use it to get hands-on with your data, including visualizing complex labels, evaluating your models, exploring scenarios of interest, identifying failure modes, finding annotation mistakes, and much more! Surveys show that machine learning engineers spend over half of their time wrangling data, but it doesn't have to be that way. -
8
fastai
Deep learning library
fastai is a deep learning library which provides practitioners with high-level components that can quickly and easily provide state-of-the-art results in standard deep learning domains, and provides researchers with low-level components that can be mixed and matched to build new approaches. It aims to do both things without substantial compromises in ease of use, flexibility, or performance. This is possible thanks to a carefully layered architecture, which expresses common underlying patterns of many deep learning and data processing techniques in terms of decoupled abstractions. These abstractions can be expressed concisely and clearly by leveraging the dynamism of the underlying Python language and the flexibility of the PyTorch library. fastai is organized around two main design goals: to be approachable and rapidly productive, while also being deeply hackable and configurable. ... -
9
OpenNN - Open Neural Networks Library
Machine learning algorithms for advanced analytics
...Some typical applications of OpenNN are business intelligence (customer segmentation, churn prevention…), health care (early diagnosis, microarray analysis…) and engineering (performance optimization, predictive maitenance…). OpenNN does not deal with computer vision or natural language processing. The main advantage of OpenNN is its high performance. This library outstands in terms of execution speed and memory allocation. It is constantly optimized and parallelized in order to maximize its efficiency. ... -
99.99% Uptime for MySQL and PostgreSQL DatabasesCloud SQL Enterprise Plus delivers near-zero downtime with 35 days of point-in-time recovery. Supports MySQL, PostgreSQL, and SQL Server.
-
10
Blazeface
Blazeface is a lightweight model that detects faces in images
Blazeface is a lightweight, high-performance face detection model designed for mobile and embedded devices, developed by TensorFlow. It is optimized for real-time face detection tasks and runs efficiently on mobile CPUs, ensuring minimal latency and power consumption. Blazeface is based on a fast architecture and uses deep learning techniques to detect faces with high accuracy, even in challenging conditions. -
11
BoofCV
BoofCV is an open source Java library for real-time computer vision.
BoofCV is an open source Java library for real-time computer vision and robotics applications. Written from scratch for ease of use and high performance, it provides both basic and advanced features needed for creating a computer vision system. Functionality include optimized low level image processing routines (e.g. convolution, interpolation, gradient) to high level functionality such as image stabilization. Released under an Apache 2.0 license for both academic and commercial use. -
12
pipeless
A computer vision framework to create and deploy apps in minutes
...You can easily use industry-standard models, such as YOLO, or load your custom model in one of the supported inference runtimes. Pipeless ships some of the most popular inference runtimes, such as the ONNX Runtime, allowing you to run inference with high performance on CPU or GPU out-of-the-box. You can deploy your Pipeless application with a single command to edge and IoT devices or the cloud. -
13
T81 558
Applications of Deep Neural Networks
...This course will introduce the student to classic neural network structures, Convolution Neural Networks (CNN), Long Short-Term Memory (LSTM), Gated Recurrent Neural Networks (GRU), General Adversarial Networks (GAN) and reinforcement learning. Application of these architectures to computer vision, time series, security, natural language processing (NLP), and data generation will be covered. High-Performance Computing (HPC) aspects will demonstrate how deep learning can be leveraged both on graphical processing units (GPUs), as well as grids. -
14
ConvNeXt
Code release for ConvNeXt model
...The repository provides pretrained models, training recipes, and ablation studies demonstrating how incremental design choices collectively yield state-of-the-art performance. -
15
Tiny
Tiny Face Detector, CVPR 2017
...It provides training/testing scripts, a demo (tiny_face_detector.m), model loading, evaluation on WIDER FACE, and supporting utilities (e.g. cnn_widerface_eval.m). The code depends on MatConvNet, which must be compiled (with GPU / CUDA / cuDNN support) for full performance. Pretrained model provided (ResNet101-based, plus alternatives). Demo and evaluation scripts for benchmark datasets. Use of “foveal descriptors” to incorporate context for low-resolution faces. Pretrained model provided (ResNet101-based, plus alternatives). -
16
OpenFace
A state-of-the-art facial behavior analysis toolkit
...OpenFace is able to deliver state-of-the-art results in all of these mentioned tasks. OpenFace is available for Windows, Ubuntu and macOS installations. It is capable of real-time performance and does not need to run on any specialist hardware, a simple webcam will suffice. -
17
maskrcnn-benchmark
Fast, modular reference implementation of Instance Segmentation
Mask R-CNN Benchmark is a PyTorch-based framework that provides high-performance implementations of object detection, instance segmentation, and keypoint detection models. Originally built to benchmark Mask R-CNN and related models, it offers a clean, modular design to train and evaluate detection systems efficiently on standard datasets like COCO. The framework integrates critical components—region proposal networks (RPNs), RoIAlign layers, mask heads, and backbone architectures such as ResNet and FPN—optimized for both accuracy and speed. ... -
18
Mexopencv
Collection and a development kit of matlab mex functions for OpenCV
mexopencv is a collection of MEX functions that provide MATLAB bindings for OpenCV, the popular computer vision library. It enables MATLAB users to access nearly the full range of OpenCV’s C++ API directly from MATLAB, combining the ease of MATLAB scripting with the performance of OpenCV. -
19
ECO
Matlab implementation of the ECO tracker
ECO (Efficient Convolution Operators for Tracking) is a high-performance object tracking algorithm developed by Martin Danelljan and collaborators. It is based on discriminative correlation filters and designed to handle appearance changes, occlusions, and scale variations in visual object tracking tasks. The code provides a MATLAB implementation of the ECO and ECO-HC (high-speed) variants and was one of the top performers on multiple visual tracking benchmarks. -
20
R-FCN
R-FCN: Object Detection via Region-based Fully Convolutional Networks
...R-FCN is efficient (low per-region overhead) and competitive in accuracy (e.g. with ResNet backbones). Position-sensitive score maps for per-region classification without expensive per-region convs. Optional “deformable R-FCN” extension for improved performance. -
21
HashingBaselineForImageRetrieval
Various hashing methods for image retrieval and serves as the baseline
This repository provides baseline implementations of deep supervised hashing methods for image retrieval tasks using PyTorch. It includes clean, minimal code for several hashing algorithms designed to map images into compact binary codes while preserving similarity in feature space, enabling fast and scalable retrieval from large image datasets. -
22
Edges
Structured Edge Detection Toolbox
...The toolbox also includes the Edge Boxes object proposal method, fast superpixel generation, and utilities for training, evaluation, and integration with vision pipelines. High performance (frames per second performance depending on settings). Integration with MATLAB and compatibility with external vision pipelines. Fast edge detection using structured forests (predict structured edge maps). -
23
Netvlad
NetVLAD: CNN architecture for weakly supervised place recognition
NetVLAD is a deep learning-based image descriptor framework developed by Relja Arandjelović for place recognition and image retrieval. It extends standard CNNs with a trainable VLAD (Vector of Locally Aggregated Descriptors) layer to create compact, robust global descriptors from image features. This implementation includes training code and pretrained models using the Pittsburgh and Tokyo datasets. -
24
Rcnn
R-CNN: Regions with Convolutional Neural Network Features
...Developed by Ross Girshick, R-CNN combines region proposals with convolutional neural networks to detect objects in images. It was one of the first approaches to significantly improve performance on object detection benchmarks like PASCAL VOC. -
25
OpenTLD
OpenTLD is an open source library for real-time 2D tracking
...In terms of usage, one typically initializes the tracker by providing a bounding box on the first frame, then calls a function like run_TLD to process a video and obtain bounding boxes over time. The system updates its internal models as frames are processed, and can re-detect the target when tracking fails. The algorithm’s performance is known to improve over time due to its online adaptation behavior. Because of its age and MATLAB dependencies, adopting it in modern C++ / real-time pipelines may require effort (e.g. rewriting or porting) or using more recent tracking libraries.
