Search Results for "compute" - Page 4
Sort By:
Showing 114 open source projects for "compute"
View related business solutions-
Secure File Transfer for Windows with Cerberus by RedwoodCerberus supports unlimited users and connections on a single IP, with built-in encryption, 2FA, and a browser-based web client — all deployable in under 15 minutes with a 25-day free trial.
-
Full-stack observability with actually useful AI | Grafana CloudBuilt on open standards like Prometheus and OpenTelemetry, Grafana Cloud includes Kubernetes Monitoring, Application Observability, Incident Response, plus the AI-powered Grafana Assistant. Get started with our generous free tier today.
-
1
TensorHouse
A collection of reference Jupyter notebooks and demo AI/ML application
TensorHouse is a scalable reinforcement learning (RL) platform that focuses on high-throughput experience generation and distributed training. It is designed to efficiently train agents across multiple environments and compute resources. TensorHouse enables flexible experiment management, making it suitable for large-scale RL experiments in both research and applied settings. -
2
FastViT
This repository contains the official implementation of research
...The codebase provides reference implementations and checkpoints that make it easy to evaluate or fine-tune on downstream datasets. In practice, FastViT offers drop-in backbones that reduce compute and memory pressure without exotic training tricks. -
3
llm
An ecosystem of Rust libraries for working with large language models
...Text generation can be done as a one-off based on a prompt, or interactively, through REPL or chat modes. The CLI can also be used to serialize (print) decoded models, quantize GGML files, or compute the perplexity of a model. It can be downloaded from the latest GitHub release or by installing it from crates.io. -
4
Fairseq
Facebook AI Research Sequence-to-Sequence Toolkit written in Python
...These ideas are encapsulated in the new FullyShardedDataParallel (FSDP) wrapper provided by fairscale. Fairseq can be extended through user-supplied plug-ins. Models define the neural network architecture and encapsulate all of the learnable parameters. Criterions compute the loss function given the model outputs and targets. Tasks store dictionaries and provide helpers for loading/iterating over Datasets, initializing the Model/Criterion and calculating the loss. -
Our Free Plans just got better! | Auth0You asked, we delivered! Auth0 is excited to expand our Free and Paid plans to include more options so you can focus on building, deploying, and scaling applications without having to worry about your security. Auth0 now, thank yourself later.
-
5
Procgen
Procedurally-Generated Game-Like Gym-Environments
Procgen (short for Procedural Generation Benchmark) is a suite of 16 procedurally generated, game-like reinforcement learning environments designed to evaluate generalization and sample efficiency in RL agents. Unlike fixed, deterministic environments, Procgen generates new levels (layouts, obstacles, visual variation) each episode, making it impossible for an agent to simply memorize trajectories. The environments are designed to run very quickly (thousands of steps per second on a single... -
6
MACE
Deep learning inference framework optimized for mobile platforms
Mobile AI Compute Engine (or MACE for short) is a deep learning inference framework optimized for mobile heterogeneous computing on Android, iOS, Linux and Windows devices. Runtime is optimized with NEON, OpenCL and Hexagon, and Winograd algorithm is introduced to speed up convolution operations. The initialization is also optimized to be faster. -
7
Trax
Deep learning with clear code and speed
Trax is an end-to-end library for deep learning that focuses on clear code and speed. It is actively used and maintained in the Google Brain team. Run a pre-trained Transformer, create a translator in a few lines of code. Features and resources, API docs, where to talk to us, how to open an issue and more. Walkthrough, how Trax works, how to make new models and train on your own data. Trax includes basic models (like ResNet, LSTM, Transformer) and RL algorithms (like REINFORCE, A2C, PPO). It... -
8
gpt-2-simple
Python package to easily retrain OpenAI's GPT-2 text-generating model
...For finetuning, it is strongly recommended to use a GPU, although you can generate using a CPU (albeit much more slowly). If you are training in the cloud, using a Colaboratory notebook or a Google Compute Engine VM w/ the TensorFlow Deep Learning image is strongly recommended. (as the GPT-2 model is hosted on GCP) You can use gpt-2-simple to retrain a model using a GPU for free in this Colaboratory notebook, which also demos additional features of the package. Note: Development on gpt-2-simple has mostly been superceded by aitextgen, which has similar AI text generation capabilities with more efficient training time. -
9
TimeSformer
The official pytorch implementation of our paper
...TimeSformer was influential in showing that pure transformer architectures—without convolutional backbones—can perform strongly on video classification tasks. Its flexible attention design allows experimenting with different factoring (spatial-then-temporal, joint, etc.) to trade off compute, memory, and accuracy. -
Try Google Cloud Risk-Free With $300 in CreditUse your credit across every product. Compute, storage, AI, analytics. When it runs out, 20+ products stay free. You only pay when you choose to.
-
10
XLM (Cross-lingual Language Model)
PyTorch original implementation of Cross-lingual Language Model
...The repository provides preprocessing pipelines, training code, and fine-tuning scripts so you can reproduce benchmark results or adapt models to your own multilingual corpora. Pretrained checkpoints cover dozens of languages and multiple model sizes, balancing quality and compute needs. -
11
Swift for TensorFlow
Swift for TensorFlow
...By embedding machine learning functionality into the Swift compiler and language design, the project enables developers to write high-performance machine learning models while maintaining the readability and safety of modern programming practices. Swift for TensorFlow also introduces tools that allow developers to compute gradients automatically, which is essential for training neural networks through gradient-based optimization. -
12
TTS
Deep learning for text to speech
...Notebooks for extensive model benchmarking. Modular (but not too much) code base enabling easy testing for new ideas. Text2Spec models (Tacotron, Tacotron2, Glow-TTS, SpeedySpeech). Speaker Encoder to compute speaker embeddings efficiently. Vocoder models (MelGAN, Multiband-MelGAN, GAN-TTS, ParallelWaveGAN, WaveGrad, WaveRNN). If you are only interested in synthesizing speech with the released TTS models, installing from PyPI is the easiest option. -
13
Amazon SageMaker Examples
Jupyter notebooks that demonstrate how to build models using SageMaker
...If you’re new to SageMaker we recommend starting with more feature-rich SageMaker Studio. It uses the familiar JupyterLab interface and has seamless integration with a variety of deep learning and data science environments and scalable compute resources for training, inference, and other ML operations. Studio offers teams and companies easy on-boarding for their team members, freeing them up from complex systems admin and security processes. Administrators control data access and resource provisioning for their users. Notebook Instances are another option. They have the familiar Jupyter and JuypterLab interfaces that work well for single users, or small teams where users are also administrators. ... -
14
AdaNet
Fast and flexible AutoML with learning guarantees
AdaNet is a TensorFlow framework for fast and flexible AutoML with learning guarantees. AdaNet is a lightweight TensorFlow-based framework for automatically learning high-quality models with minimal expert intervention. AdaNet builds on recent AutoML efforts to be fast and flexible while providing learning guarantees. Importantly, AdaNet provides a general framework for not only learning a neural network architecture but also for learning to the ensemble to obtain even better models. At each... -
15
uTensor
TinyML AI inference library
uTensor is an embedded machine learning inference framework designed to run neural network models on resource-constrained devices such as microcontrollers and Internet-of-Things hardware. The project focuses on enabling TinyML deployments by translating trained machine learning models into efficient C++ code that can execute directly on embedded systems. Instead of training models on-device, the framework uses an offline workflow that converts trained TensorFlow graphs into optimized... -
16
PyTorch-BigGraph
Generate embeddings from large-scale graph-structured data
PyTorch-BigGraph (PBG) is a system for learning embeddings on massive graphs—think billions of nodes and edges—using partitioning and distributed training to keep memory and compute tractable. It shards entities into partitions and buckets edges so that each training pass only touches a small slice of parameters, which drastically reduces peak RAM and enables horizontal scaling across machines. PBG supports multi-relation graphs (knowledge graphs) with relation-specific scoring functions, negative sampling strategies, and typed entities, making it suitable for link prediction and retrieval. ... -
17
Azure Machine Learning Python SDK
Python notebooks with ML and deep learning examples
Azure Machine Learning Python SDK is a curated repository of Python-based Jupyter notebooks that demonstrate how to develop, train, evaluate, and deploy machine learning and deep learning models using the Azure Machine Learning Python SDK. The content spans a wide range of real-world tasks — from foundational quickstarts that teach users how to configure an Azure ML workspace and connect to compute resources, to advanced tutorials on using pipelines, automated machine learning, and dataset handling. Because it is designed to work with Azure Machine Learning compute instances, many notebooks can be executed directly in the cloud without additional setup, but they can also run locally with the appropriate SDK and packages installed. ... -
18
ELI5
A library for debugging/inspecting machine learning classifiers
...It supports several popular machine learning frameworks including scikit-learn, XGBoost, LightGBM, CatBoost, and Keras. The library allows users to inspect model weights, analyze decision trees, and compute permutation feature importance for black-box models. It also provides specialized tools such as TextExplainer, which can highlight important words in text classification tasks to explain why a model produced a particular prediction. Additionally, the library integrates explanation algorithms such as LIME to interpret predictions from arbitrary machine learning models. -
19
FID score for PyTorch
Compute FID scores with PyTorch
This is a port of the official implementation of Fréchet Inception Distance to PyTorch. FID is a measure of similarity between two datasets of images. It was shown to correlate well with human judgement of visual quality and is most often used to evaluate the quality of samples of Generative Adversarial Networks. FID is calculated by computing the Fréchet distance between two Gaussians fitted to feature representations of the Inception network. The weights and the model are exactly the same... -
20
ConvNet Burden
Memory consumption and FLOP count estimates for convnets
convnet-burden is a MATLAB toolbox / script collection estimating computational cost (FLOPs) and memory consumption of various convolutional neural network architectures. It lets users compute approximate burdens (in FLOPs, memory) for standard image classification CNN models (e.g. ResNet, VGG) based on network definitions. The tool helps researchers compare the computational efficiency of architectures or quantify resource needs. Estimation of memory consumption (e.g. feature map sizes, parameter storage). Support for multiple network definitions/architectures. ... -
21
tracking.js
A modern approach for Computer Vision on the web
The tracking.js library brings different computer vision algorithms and techniques into the browser environment. By using modern HTML5 specifications, we enable you to do real-time color tracking, face detection and much more, all that with a lightweight core (~7 KB) and intuitive interface. To get started, download the project. This project includes all of the tracking.js examples, source code dependencies you'll need to get started. Unzip the project somewhere on your local drive. The... -
22
Density-ratio based clustering
Discovering clusters with varying densities
This site provides the source code of two approaches for density-ratio based clustering, used for discovering clusters with varying densities. One approach is to modify a density-based clustering algorithm to do density-ratio based clustering by using its density estimator to compute density-ratio. The other approach involves rescaling the given dataset only. An existing density-based clustering algorithm, which is applied to the rescaled dataset, can find all clusters with varying densities that would otherwise impossible had the same algorithm been applied to the unscaled dataset. Reference: Zhu, Y., Ting, K. ... -
23
JAABA
The Janelia Automated Animal Behavior Annotator
The Janelia Automatic Animal Behavior Annotator (JAABA) is a machine learning-based system that enables researchers to automatically compute interpretable, quantitative statistics describing video of behaving animals. Through our system, users encode their intuition about the structure of behavior by labeling the behavior of the animal, e.g. walking, grooming, or following, in a small set of video frames. JAABA uses machine learning techniques to convert these manual labels into behavior detectors that can then be used to automatically classify the behaviors of animals in large data sets with high throughput. ... -
24
Cpt Kirk
Obtain why and why-not justifications for answer set programs.
Since the method proposed in https://www.researchgate.net/publication/262599199_Unifying_Provenance_and_Debugging_for_Answer-Set_Programs?ev=prf_pub is based on meta-programming, it is possible to use existing state-of-the-art software systems that support well-founded and answer-set semantics, which allowed us to start developing this new tool by extending the one that exists related to a debugging approach: Spock, hence the name Cpt. Kirk. Furthermore and more importantly, one direction... -
25
SPINdle is a logic reasoner that can be used to compute the consequence of defeasible logic theories in an efficient manner. The current implementation covers both the basic defeasible logic and modal defeasible logic.
