#PyTorch

CLIP employs contrastive language-image pre-training to achieve zero-shot prediction, matching performance with labeled data models. By integrating with PyTorch and TorchVision, CLIP facilitates diverse tasks like CIFAR-100 predictions and linear-probe evaluations through its image and text encoding capabilities.

LoRA employs low-rank matrix adaptations, reducing trainable parameters and optimizing task adaptation in large language models. This approach minimizes storage needs and avoids inference delays. The Python package integrates with PyTorch and the Hugging Face PEFT library, ensuring competitive performance alongside full fine-tuning in benchmarks like GLUE. LoRA adapts specific Transformer elements, like query and value projections, offering flexibility across models such as RoBERTa, DeBERTa, and GPT-2. The 'loralib' can be installed to apply these techniques efficiently.

Curated Transformers is a PyTorch library providing modular transformer models that ensure efficient feature reuse and easy scalability. It supports large language models such as Falcon, Llama, and Dolly v2 and works seamlessly within the PyTorch environment while maintaining minimal dependencies. With straightforward type annotations, it suits educational purposes and integrates well with type-checked codebases. Used by Explosion and set as the default in spaCy 3.7, it offers compatibility with diverse architectures like BERT and GPT variants through Huggingface Hub.

Discover a diverse set of machine learning notebooks covering applications from neural networks to computer vision. These resources on Codespaces offer clear setup guidance for straightforward learning in machine learning fields, including PyTorch and generative adversarial networks, ideal for expanding knowledge or efficiently prototyping.

Discover extensive deep learning applications and inference deployment frameworks in this updated resource. This tutorial builds upon the first edition, offering foundational concepts and guiding from basic knowledge to industry applications in computer vision, NLP, and large language models. It details PyTorch fundamentals and projects covering image processing, text generation, and model deployment with ONNX and TensorRT, allowing learners to apply theory in practice. Designed for AI learners, students, and professionals aiming to extend their understanding and practical skills in PyTorch.

This comprehensive guide covers the entire process of building a GPT-like large language model, starting from coding the basics. It provides step-by-step instructions with clear explanations and examples, making it a valuable resource for understanding model development, pretraining, and finetuning techniques. The guide parallels techniques used in technologies like ChatGPT and includes information on loading and refining larger pre-trained models. Access the official code repository for updates and additional resources.

Torchreid is an advanced library designed for deep-learning person re-identification, supporting multi-GPU use and both image and video analysis. It facilitates complete training, cross-dataset evaluation, and straightforward dataset setup while implementing leading-edge models. The library is highly adaptable, permitting easy integration of new models, datasets, and techniques, and includes pre-trained models and innovative training methods. Torchreid additionally offers support for ONNX, OpenVINO, and TFLite for model exportation, enhancing adaptability across diverse platforms. It serves as a valuable tool for researchers and developers focused on efficient person re-identification solutions.

This open-source resource is designed for beginners interested in leveraging PyTorch for deep learning projects and research. Regularly updated, it aligns with the latest PyTorch releases, providing timely and practical insights for users. Covering topics from basic tensors and autograd to advanced concepts like CNN, RNN, and multi-GPU training, this handbook spans a wide gamut of learning materials. It includes online guides, practical exercises, and community support to aid real-world application.

This tutorial provides a detailed guide on developing a machine learning pipeline with PyTorch. It involves creating custom datasets, exploring traditional algorithms, and transitioning to deep learning. Based on a Harvard graduate course project, it includes updated PyTorch code and clear setup instructions. Available in both HTML and IPython Notebook formats, it is designed for those aiming to expand their machine learning knowledge.

DeepPavlov 1.0 is an intuitive open-source NLP framework using PyTorch and transformers, designed to provide seamless model deployment for practitioners with little NLP background. It supports diverse applications with pre-trained models, simple installation, and various interfaces across platforms.

FasterTransformer offers highly optimized transformer-based encoders and decoders for GPU-driven inference. Utilizing CUDA and C++, it integrates seamlessly with TensorFlow, PyTorch, and Triton, providing practical examples. Key features include FP16 precision and INT8 quantization for substantial speedup in BERT, decoder, and GPT tasks, enhancing processing efficiency across NVIDIA GPU architectures.

Discover Rust bindings for the PyTorch C++ API using the tch crate, featuring integration with libtorch for tensor operations and neural network training. Supports both static and dynamic linking with Python compatibility, and includes examples for model training, optimization, and leveraging pre-trained weights, while adhering closely to the original PyTorch API.

This comprehensive list highlights popular open-source deep learning projects available on GitHub, including prominent tools such as TensorFlow, PyTorch, and OpenCV. These libraries and frameworks are vital for machine learning professionals, offering solutions tailored to applications in areas like neural networks and computer vision. With easy-to-use interfaces, strong community support, and robust functionalities, they cater to both beginners and advanced users focused on developing and enhancing machine learning skills and solutions.

NeuralProphet integrates neural networks with traditional algorithms on PyTorch, providing an accessible platform for high-frequency time series prediction. Designed for collaborative development, it supports rapid model customization, emphasizing clarity and adaptability. While initial predictions may require tuning, iterative refinement results in precise models. Optimized for datasets covering a minimum of two years, it includes features like autoregression and seasonality. Participate in community discussions on GitHub and Slack, and utilize comprehensive tutorials. A suitable choice for developers exploring open-source forecasting solutions.

The Differentiable Architecture Search method leverages continuous relaxation and gradient descent for efficient design of convolutional and recurrent architectures applicable in image classification and language modeling. Compatible with a single GPU setup, it targets datasets like CIFAR-10, ImageNet, PTB, and WikiText-2. Pretrained models facilitate swift evaluations, while 2nd-order approximations aid in searching for optimal architectures based on validation outcomes. Comprehensive training with full-sized models verifies their performance. Visualization tools further enhance understanding of architectural design, all within Python and PyTorch environments, providing a notable advancement for machine learning architecture optimization.

This repository provides a full PyTorch adaptation of the 'Dive Into Deep Learning' book, shifting from the original MXNet base. It spans key concepts in deep learning including data manipulation, linear regression, attention mechanisms, and computer vision, across various detailed chapters. The project welcomes contributions for continuous enhancement, serving as a valuable resource for developers aiming to advance their PyTorch deep learning skills. It is recommended to clone the repository or employ nbviewer for optimal notebook viewing.

Thinc simplifies deep learning with its lightweight, type-checked API. It seamlessly integrates with PyTorch, TensorFlow, and MXNet, allowing for flexible model composition and configuration. Ideal for use as an interface layer or standalone toolkit, Thinc supports Python 3.6+ and is valued for production reliability across platforms.

Whisper, a speech recognition solution by OpenAI, utilizes a Transformer sequence-to-sequence approach for multilingual transcription and language identification. With models ranging from 'tiny' to 'turbo', it balances speed with accuracy and is compatible with multiple Python versions, supporting comprehensive audio processing tasks in Python as well as via command-line, catering to developers in need of robust pre-trained models across multiple languages.

This guide delves into the core concepts and practical uses of deep learning with PyTorch, targeted towards developers. It covers essential theories and hands-on coding examples, though it omits topics like recurrent neural networks to center on helping readers navigate advanced subjects independently. Perfect for those versed in Python, it lays a robust foundation for developing deep learning skills.

Explore a detailed guide to PyTorch with tutorials, video lessons, and suggested readings. Discover practical applications in NLP and computer vision using a variety of PyTorch repositories. This resource caters to learners of all levels, providing comprehensive support from foundational neural network concepts to advanced model training techniques.

Explore Monodepth2's PyTorch-based reference implementation for advanced depth estimation. The project methodically outlines dependency setups, guides on predicting scaled disparities, and furnishes ready-to-use pretrained models. Detailed instructions for custom dataset training, model finetuning, and KITTI dataset evaluation are included, alongside support for multiple training modalities including monocular, stereo, and combined approaches, catering to diverse research requirements.

Explore state-of-the-art methods for AI explainability in computer vision, including advanced Pixel Attribution and benchmarking tools. Supports diverse CNNs and Vision Transformers across use cases like classification and segmentation, with methods like GradCAM for enhanced visualization and interpretability metrics.

This PyTorch-based implementation of the Single Shot MultiBox Detector offers a streamlined approach for efficient object detection. Compatible with popular datasets and offering straightforward processes for setup, training, and evaluation, this project supports NVIDIA GPU acceleration and real-time training performance enhancements via Visdom integration. Users can explore transfer learning with pre-trained model weights, supported by comprehensive instructions for both command-line and Jupyter notebook demos. Regular updates aim to expand capabilities, including support for SSD512 and custom dataset training.

The project ports RWKV language model architecture to ggml, supporting FP32, FP16, and various quantized inferences like INT4, INT5, and INT8. Primarily CPU-focused, it includes both a C library and a Python wrapper, with optional cuBLAS support. It supports RWKV versions 5 and 6, providing competitive alternatives to Transformer models, especially for extensive contexts, and accommodates LoRA checkpoint integration, offering detailed performance metrics for efficient computations.

An open-source library for scalable and flexible deep learning model training. Built on PyTorch, Composer simplifies distributed workflows for large clusters, supporting models like LLMs, CNNs, and transformers. Features include parallel data loading, efficient memory use, and customizable training loops, assisting in automating routine tasks to achieve flexibility and high performance. Designed for those with Python and PyTorch knowledge, it allows seamless integration with streaming datasets and experiment tracking tools for efficient training configurations.

The 12-week program offers an introduction to Artificial Intelligence, covering neural networks, deep learning, and practical experience with TensorFlow and PyTorch. It delves into different AI methodologies, including symbolic AI and genetic algorithms, while omitting business uses and deep mathematics. Ethical implications and additional opportunities for learning are available through resources like Microsoft Learn.

This project offers an implementation of OpenAI's DALL-E in Pytorch, providing text-to-image transformation capabilities with options for scalability and customization, including the use of pretrained VAE models and adjustable attention mechanisms. It includes CLIP integration for image generation ranking and supports training protocols like reversible networks and sparse attention.

x-transformers offers an efficient implementation of transformers with features like Flash Attention and memory augmentation. It is suitable for tasks in NLP and computer vision, optimizing performance and resource use, without over-promising results.

Explore an open-source toolkit for text detection, recognition, and information extraction, built on PyTorch and MMDetection. It supports a wide range of text processing tasks with state-of-the-art models and allows customization of core components like optimizers and preprocessors. Features include visualization tools, validation utilities, and data converters. Suitable for researchers and developers, it supports various datasets and includes robust version 1.0.0 updates with new datasets and enhanced documentation, ideal for developing strong text-focused applications.

This repository provides PyTorch implementations for both CycleGAN and pix2pix, supporting both unpaired and paired image-to-image translation. Ideal for research and experimentation, the codebase is compatible with the latest PyTorch releases and optimizes training with advanced models like img2img-turbo and contrastive-unpaired-translation. It includes resources such as training tips, FAQs, Docker support, and Colab notebooks for practical usage.

MONAI, built on PyTorch, is an open-source framework designed for deep learning in medical imaging. It offers state-of-the-art workflows with flexible pre-processing, compositional APIs, and domain-specific tools. Supporting multi-GPU environments, MONAI promotes collaboration among researchers. Its Model Zoo and extensive documentation streamline integration and use, making MONAI a valuable resource in healthcare.

The PyTorch implementation of the Transformer model uses self-attention for advanced translation, achieving leading results in the 2014 WMT English-German task. It supports training and translation with the model, with byte pair encoding features under development. The project is suitable for those interested in Transformer architecture without convolutional or recurrent layers. Contributions and suggestions are welcome.

This open-source guide provides a comprehensive introduction to PyTorch based on version 1.8, including basic usage, advanced extensions, and practical applications. It offers a hands-on approach with Jupyter Notebooks, covering topics like vectorization and distributed computing, and guides on projects such as GANs, NLP with Transformers, and Style Transfer. Accessible for those without the accompanying book, this resource includes full code and pre-trained models.

Explore DeepMoji, a model trained on a vast dataset of emoji-laden tweets to enhance emotion detection efficiency. With well-documented resources, it simplifies setup on Keras compatible with Theano or Tensorflow, also offering a PyTorch version by HuggingFace. It allows for converting text to emotion vectors and predicting emojis, boosting NLP project potential without exaggeration.

The fastai library offers high-level and low-level components to support both standard deep learning tasks and innovative model customization. Its architecture takes advantage of Python and PyTorch, ensuring usability and performance. Key features include a GPU-optimized vision library, dynamic callback system, and adaptable data block API. Suitable for various deployment needs, fastai also facilitates integration with existing libraries and efficient model training.

PyTorch provides tensor computation with GPU support and dynamic neural networks using an autograd system. It integrates with Python, allowing use of libraries like NumPy and SciPy for flexible scientific computations. Features include a dynamic network structure, memory-efficient usage, and simple extensibility. Suitable for researchers and developers exploring AI and machine learning.

Explore PyTorch's take on 'Dive into Deep Learning', transitioning from MXNet. This resource hosts detailed Jupyter notebooks and markdown documentation, tailored for beginners eager to explore deep learning with PyTorch. Providing various resource access methods, the project encourages user contributions without requiring deep learning expertise. Study advanced topics like CNNs, RNNs, and optimization algorithms through hands-on exercises.

The toolkit facilitates end-to-end speech recognition and text-to-speech using PyTorch and Kaldi-style data processing. It manages numerous tasks like speech recognition, translation, enhancement, and diarization efficiently. By providing detailed recipes for ASR and TTS, and integrating with neural vocoders, it supports offline and streaming functionalities, making it a valuable resource for speech technology research and development.

This PyTorch-based U-Net implementation enhances high-definition image segmentation, particularly for challenges like Kaggle's Carvana Image Masking. Featuring Docker for straightforward deployment and mixed precision optimization, the model boasts a Dice coefficient of 0.988423 across vast test sets. The project supports diverse segmentation applications, such as medical and portrait, and offers seamless training and inference with Weights & Biases for live training progress. Pretrained models are accessible for swift application.

Access extensive deep learning documentation with PyTorch Chinese translations, offering optimized use for both GPU and CPU. Engage with the community to explore translated PyTorch 2.0 resources, and visit official sites for continuous updates. This initiative promotes the open dissemination of knowledge and encourages collaborative participation to enhance resource quality. Join the conversation through various platforms for feedback and contributions.

YOLOX provides an efficient anchor-free object detection model, optimizing both accuracy and speed. Bridging research and practice, it supports PyTorch and MegEngine, includes JIT compile operations, and promises enhancements like YOLOX-P6. Explore the GitHub repository for demos and further insights.

This repository provides detailed PyTorch deep learning tutorials aligned with the Udacity Deep Learning Nanodegree, featuring projects such as bike-sharing predictions and dog breed classification. It also includes topics like CNNs, RNNs, GANs, as well as weight initialization and batch normalization. Additionally, learn to deploy models with AWS SageMaker for a comprehensive learning experience.

Discover a comprehensive course focusing on PyTorch for deep learning, including the latest PyTorch 2.0 tutorial. This hands-on course emphasizes practical coding with sections covering neural network classification, computer vision, transfer learning, custom datasets, and model deployment. Through milestone projects such as FoodVision, gain practical experience and develop a portfolio. This beginner-friendly course uses Google Colab notebooks and video content for understanding deep learning fundamentals.

OpenNMT-py is an open-source platform facilitating neural machine translation and language modeling. It supports various NLP tasks and is suitable for production environments. Features include model quantization, integration with PyTorch, and GPU-acceleration for large models. Comprehensive tutorials and documentation assist developers in implementing NLP solutions.

Informer significantly enhances long sequence time-series forecasting by optimizing transformer efficiency with ProbSparse Attention. This method focuses on active queries, resulting in superior predictions. The project includes thorough experiment reproducibility utilizing datasets like ETTh1 and ETTh2, and operates on PyTorch. Core features encompass model training commands, data integration, and optimization settings. Informer efficiently manages large data sequences, essential for AI-based predictions across diverse applications. Frequent updates ensure it remains at the forefront of AI research.

TorchServe provides mandatory token authorization and defaults to disabling model API control, enhancing security for PyTorch models in production environments. It is designed for flexible deployment across multiple platforms, such as CPUs, GPUs, AWS, and Google Cloud. TorchServe supports complex workflow deployments and advanced model management with various optimizations, offering high-performance AI solutions.

This repository provides concise tutorial codes for deep learning researchers to learn PyTorch efficiently, with models mostly under 30 lines of code. It presents a coherent learning trajectory from foundational topics like PyTorch basics, linear regression, to advanced subjects such as Generative Adversarial Networks and Neural Style Transfer. This guide serves as a practical supplement to the Official PyTorch Tutorial, offering vital resources for developing proficiency in PyTorch. The prerequisites include Python 2.7 or 3.5+ and PyTorch 0.4.0+.

GluonCV offers a comprehensive set of state-of-the-art deep learning models for a variety of computer vision tasks such as image classification and object detection. It facilitates quick prototyping for engineers, researchers, and students by supporting both PyTorch and MXNet frameworks. Key features include scripts for reproducing research results, an extensive collection of pre-trained models, and user-friendly APIs to ease implementation. Ideal for both research and production, GluonCV is well-supported by the community and integrates seamlessly with AutoGluon for enhanced model deployment.

Pyro, developed on PyTorch, is a universal probabilistic programming library that supports scaling with minimal overhead. Designed for both automation and expert control, it provides composable abstractions for generative and inference models. Originally an Uber AI project, Pyro now thrives under the Linux Foundation, maintained by community and Broad Institute contributors, fostering open-source collaboration.

This implementation utilizes PyTorch to improve human pose estimation by maintaining high-resolution images throughout. It starts with a high-resolution subnetwork, ensuring precise keypoint heatmap prediction. Proven effective on COCO and MPII datasets, this HRNet approach is valuable for tasks including segmentation, face alignment, and object detection.