Search Results for "model-builder" - Page 3
Sort By:
Showing 107 open source projects for "model-builder"
View related business solutions-
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.
-
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.
-
1
fastMRI
A large open dataset + tools to speed up MRI scans using ML
...The repository provides an open-source PyTorch framework with data loaders, subsampling utilities, reconstruction models, and evaluation metrics, supporting both research reproducibility and practical experimentation. It includes reference implementations for key MRI reconstruction architectures such as U-Net and Variational Networks (VarNet), along with example scripts for model training and evaluation using the PyTorch Lightning framework. The project also releases several fully anonymized public MRI datasets, including knee, brain, and prostate scans. -
2
MiniChain
A tiny library for coding with large language models
MiniChain is a small Python library for building applications that combine large language models, prompts, and executable tools. Developers annotate ordinary functions to define model calls while keeping prompt templates separate from application logic. Multiple functions can be chained so the output of one model or tool becomes the input to another. The library records calls as a graph, making intermediate steps easier to inspect, debug, and retry. It includes model abstractions for language models as well as tools such as Python execution. ... -
3
FairScale
PyTorch extensions for high performance and large scale training
FairScale is a collection of PyTorch performance and scaling primitives that pioneered many of the ideas now used for large-model training. It introduced Fully Sharded Data Parallel (FSDP) style techniques that shard model parameters, gradients, and optimizer states across ranks to fit bigger models into the same memory budget. The library also provides pipeline parallelism, activation checkpointing, mixed precision, optimizer state sharding (OSS), and auto-wrapping policies that reduce boilerplate in complex distributed setups. ... -
4
albert_zh
Implementation of A Lite Bert For Self-Supervised Learning Language
albert_zh is a Chinese ALBERT pretraining and model release repository. It implements ALBERT with TensorFlow and provides Chinese pretrained models designed to reduce parameter size while preserving strong language understanding performance. The project includes several model variants, such as tiny, small, base, large, and xlarge-style releases, giving users options for speed, size, and accuracy tradeoffs. -
$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.
-
5
Jraph
A Graph Neural Network Library in Jax
...The library includes a comprehensive set of utilities for batching, padding, masking, and partitioning graph data, making it ideal for distributed and large-scale GNN experiments. Jraph also comes with a model zoo—a collection of forkable reference implementations of common message-passing GNN architectures, such as Graph Networks, Graph Convolutional Networks, and Graph Attention Networks. -
6
YOLOV4 Pytorch
This is a source code for YoloV4-pytorch that can be used to train you
YOLOV4 Pytorch is a PyTorch implementation of the YOLOv4 object detection model for training and running custom detection systems. The repository is structured around practical workflows, including training, prediction, evaluation, anchor generation, model configuration, and dataset annotation utilities. It supports VOC-style datasets and includes scripts for prediction, mAP evaluation, FPS testing, video prediction, batch prediction, and heatmap generation. -
7
PyTorch Transfer-Learning-Library
Transfer Learning Library for Domain Adaptation, Task Adaptation, etc.
TLlib is an open-source and well-documented library for Transfer Learning. It is based on pure PyTorch with high performance and friendly API. Our code is pythonic, and the design is consistent with torchvision. You can easily develop new algorithms or readily apply existing algorithms. We appreciate all contributions. If you are planning to contribute back bug-fixes, please do so without any further discussion. If you plan to contribute new features, utility functions or extensions, please... -
8
YOLOV3 Pytorch
This is a source code for yolo3-pytorch
YOLOV3 Pytorch is a PyTorch implementation of the YOLOv3 object detection model built for training, prediction, and evaluation. The repository provides a complete workflow for users who want to train their own object detector with VOC-style data or use pretrained weights. It includes utilities for annotation conversion, anchor generation, image prediction, video prediction, batch prediction, FPS measurement, heatmap output, and mAP evaluation. -
9
Official YOLOv7
YOLOv7: Trainable bag-of-freebies sets new state-of-the-art
YOLOv7 is the official implementation of the paper “YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors.” It is a PyTorch-based object detection project focused on high speed and strong accuracy for real-time computer vision. The repository provides model definitions, training scripts, testing tools, inference examples, pretrained weights, and deployment-oriented materials. YOLOv7 introduced training-time improvements that raise accuracy without increasing inference cost, which is why the project became important in real-time detection research. It supports multiple model sizes and related tasks such as object detection and instance segmentation through associated branches or weights. ... -
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.
-
10
Fairseq
Facebook AI Research Sequence-to-Sequence Toolkit written in Python
...Tasks store dictionaries and provide helpers for loading/iterating over Datasets, initializing the Model/Criterion and calculating the loss. -
11
Faster-Rcnn
This is a pytorch implementation library of faster-rcnn
Faster-Rcnn is a PyTorch implementation of the Faster R-CNN two-stage object detection model. It is designed for training and evaluating detectors on VOC-format datasets, including VOC07+12 and custom datasets arranged with VOC-style annotations and images. The repository includes scripts for training, prediction, evaluation, annotation generation, and model summary inspection. It supports backbone options through pretrained VGG and ResNet weights, making it useful for comparing feature extractors. ... -
12
Unet
Source code for unet-pytorch, which can train its own model
...The repository is built around training, prediction, and mIoU evaluation for VOC-style segmentation data and medical-style datasets. It includes scripts for general training, medical dataset training, prediction, annotation handling, model summaries, and evaluation. The project supports multiple backbones, data processing utilities, extensive comments, and adjustable training parameters. Its README notes that U-Net is better suited to datasets with fewer features and shallow visual structures, such as medical image segmentation, rather than complex VOC-style scenes. ... -
13
DeepLabv3 Plus
Encoder-Decoder with Atrous Separable Convolution
...It implements the encoder-decoder architecture with atrous separable convolution and provides a practical workflow for training, prediction, and mIoU evaluation. The repository supports VOC-style segmentation datasets and includes utilities for annotation generation, JSON dataset conversion, model summary inspection, prediction, and metric calculation. It provides pretrained weight workflows for MobileNetV2 and Xception backbones and notes that the correct backbone should be selected during training and prediction. The project also supports multi-GPU training, multiple backbones, learning rate schedules with step and cosine options, optimizer selection, and adaptive learning rate behavior based on batch size. ... -
14
AugLy
A data augmentations library for audio, image, text, and video
...These sub-libraries include both function-based and class-based transforms, composition operators, and have the option to provide metadata about the transform applied, including its intensity. AugLy is a great library to utilize for augmenting your data in model training, or to evaluate the robustness gaps of your model! We designed AugLy to include many specific data augmentations that users perform in real life on internet platforms like Facebook's -- for example making an image into a meme, overlaying text/emojis on images/videos, reposting a screenshot from social media. While AugLy contains more generic data augmentations as well, it will be particularly useful to you if you're working on a problem like copy detection, hate speech detection, etc. -
15
Spyne
A transport agnostic sync/async RPC library
...Spyne aims to save the protocol implementers the hassle of implementing their own remote procedure call api and the application programmers the hassle of jumping through hoops just to expose their services using multiple protocols and transports. In other words, Spyne is a framework for building distributed solutions that strictly follow the MVC pattern, where Model = spyne.model, View = spyne.protocol and Controller = user code. Spyne comes with the implementations of popular transport, protocol and interface document standards along with a well-defined API that lets you build on existing functionality. -
16
SVoice (Speech Voice Separation)
We provide a PyTorch implementation of the paper Voice Separation
...This project presents a deep learning framework capable of separating mixed audio sequences where several people speak simultaneously, without prior knowledge of how many speakers are present. The model employs gated neural networks with recurrent processing blocks that disentangle voices over multiple computational steps, while maintaining speaker consistency across output channels. Separate models are trained for different speaker counts, and the largest-capacity model dynamically determines the actual number of speakers in a mixture. ... -
17
YOLOR
implementation of paper - You Only Learn One Representation
...It builds on the YOLO family and related PyTorch detection work, combining practical detector training with a research idea about unified representations. YOLOR includes model configurations, training code, evaluation scripts, inference tools, and pretrained weights. Its central contribution is the use of implicit knowledge to improve network performance without treating every task as fully separate. It is useful for computer vision researchers and developers studying YOLO-style detectors, representation learning, and high-performance detection systems. -
18
TensorNetwork
A library for easy and efficient manipulation of tensor networks
TensorNetwork is a high-level library for building and contracting tensor networks—graphical factorizations of large tensors that underpin many algorithms in physics and machine learning. It abstracts networks as nodes and edges, then compiles efficient contraction orders across multiple numeric backends so users can focus on model structure rather than index bookkeeping. Common network families (MPS/TT, PEPS, MERA, tree networks) are expressed with concise APIs that encourage experimentation and comparison. The library provides automatic path finding and cost estimation, exposing when contractions will explode in memory and suggesting better orders. Because it supports backends such as NumPy, TensorFlow, PyTorch, and JAX, the same model can run on CPUs, GPUs, or TPUs with minimal code changes. ... -
19
Spleeter
Deezer source separation library including pretrained models
Spleeter is the Deezer source separation library with pretrained models written in Python and using Tensorflow. It makes it easy to train music source separation models (assuming you have a dataset of isolated sources), and provides already trained state of the art models for performing various flavours of separation. 2 stems and 4 stems models have state of the art performances on the musdb dataset. Spleeter is also very fast as it can perform separation of audio files to 4 stems 100x... -
20
ReinventCommunity
Jupyter Notebook tutorials for REINVENT 3.2
This repository is a collection of useful jupyter notebooks, code snippets and example JSON files illustrating the use of Reinvent 3.2. -
21
Differentiable Neural Computer
A TensorFlow implementation of the Differentiable Neural Computer
...Published in Nature in 2016 under the paper “Hybrid computing using a neural network with dynamic external memory,” the DNC combines the pattern recognition power of neural networks with a memory module that can be written to and read from in a differentiable way. This allows the model to learn how to store and retrieve information across long time horizons, much like a traditional computer. The architecture consists of modular components including an access module for managing memory operations, a controller (often an LSTM or feedforward network) for issuing read/write commands, and submodules for temporal linkage and memory allocation tracking. -
22
Minkowski Engine
Auto-diff neural network library for high-dimensional sparse tensors
...To run the examples, please install the package and run the command in the package root directory. Compressing a neural network to speed up inference and minimize memory footprint has been studied widely. One of the popular techniques for model compression is pruning the weights in convnets, is also known as sparse convolutional networks. Such parameter-space sparsity used for model compression compresses networks that operate on dense tensors and all intermediate activations of these networks are also dense tensors. -
23
NLP Architect
A model library for exploring state-of-the-art deep learning
...NLP Architect is designed to be flexible for adding new models, neural network components, data handling methods, and for easy training and running models. NLP Architect is a model-oriented library designed to showcase novel and different neural network optimizations. The library contains NLP/NLU-related models per task, different neural network topologies (which are used in models), procedures for simplifying workflows in the library, pre-defined data processors and dataset loaders and misc utilities. The library is designed to be a tool for model development: data pre-processing, build model, train, validate, infer, save or load a model. -
24
fastNLP
fastNLP: A Modularized and Extensible NLP Framework
fastNLP is a lightweight framework for natural language processing (NLP), the goal is to quickly implement NLP tasks and build complex models. A unified Tabular data container simplifies the data preprocessing process. Built-in Loader and Pipe for multiple datasets, eliminating the need for preprocessing code. Various convenient NLP tools, such as Embedding loading (including ELMo and BERT), intermediate data cache, etc.. Provide a variety of neural network components and recurrence models... -
25
SentEval
A python tool for evaluating the quality of sentence embeddings
...Datasets are wrapped with unified preprocessing and metrics so results are comparable across papers and implementations. Because the interface is minimal, researchers can plug in encoders from any framework or language model and obtain a broad evaluation with little glue code. SentEval helped establish common baselines and reporting conventions in the sentence-representation community, reducing friction when comparing new methods.
