#cplusplus #caffe #convolution #deep_learning #deep_neural_networks #diy #graph_algorithms #inference #inference_engine #maxpooling #ncnn #pnnx #pytorch #relu #resnet #sigmoid #yolo #yolov5

This course, "_动手自制大模型推理框架_" (Handcrafting Large Model Inference Framework), is a valuable resource for those interested in deep learning and model inference. It teaches you how to build a modern C++ project from scratch, focusing on designing and implementing a deep learning inference framework. The course supports latest models like LLama3.2 and Qwen2.5, and uses CUDA acceleration and Int8 quantization for better performance.

By taking this course, you will learn how to write efficient C++ code, manage projects with CMake and Git, design computational graphs, implement common operators like convolution and pooling, and optimize them for speed. This knowledge will be highly beneficial for job interviews and advancing your skills in deep learning. The course also includes practical demos on models like Unet and YoloV5, making it a hands-on learning experience.

https://github.com/zjhellofss/KuiperInfer

#python #baselines #gsde #gym #machine_learning #openai #python #pytorch #reinforcement_learning #reinforcement_learning_algorithms #robotics #sb3 #sde #stable_baselines #toolbox

Stable Baselines3 (SB3) is a tool that makes it easy to use reinforcement learning algorithms with PyTorch. It provides reliable and tested implementations of these algorithms, which helps researchers and developers build projects quickly. SB3 offers many features like custom environments, policies, and integration with other tools like Tensorboard and Hugging Face. It also has detailed documentation and examples to help beginners get started. This tool assumes you have some knowledge of reinforcement learning but provides resources to learn more. Using SB3 can save time and effort by providing a stable base for your projects, allowing you to focus on new ideas and improvements.

https://github.com/DLR-RM/stable-baselines3

#python #deep_learning #plate_recognition #pytorch #yolov5

This tool helps you detect and recognize car license plates from images and videos. It supports 12 different types of Chinese license plates, including blue, yellow, new energy, police, and more. You can use it with Python and PyTorch, and it provides demos for testing with images and videos. The benefit is that it makes it easy to automate the process of identifying car license plates accurately, which can be useful for various applications such as traffic management or security systems.

https://github.com/we0091234/Chinese_license_plate_detection_recognition

#jupyter_notebook #deep_learning #machine_learning #python #pytorch

This course, "深入浅出PyTorch" (Thorough PyTorch), is designed to help you learn PyTorch from basics to advanced levels. It covers everything from installing PyTorch, understanding tensors and automatic differentiation, to building and training models, and even deploying them. The course is divided into several chapters, each focusing on different aspects of PyTorch, such as data loading, model construction, loss functions, optimizers, and visualization.

The benefit to you is that you will gain a comprehensive understanding of PyTorch, which is a powerful tool for deep learning. You will learn through both theoretical explanations and practical exercises, including hands-on projects like fashion classification and fruit classification. This will help you develop your programming skills and ability to solve real-world problems using deep learning algorithms. Additionally, the course includes video tutorials and a community-driven approach to learning, making it easier and more engaging.

https://github.com/datawhalechina/thorough-pytorch

#python #annotation #annotation_tool #annotations #boundingbox #computer_vision #computer_vision_annotation #dataset #deep_learning #image_annotation #image_classification #image_labeling #image_labelling_tool #imagenet #labeling #labeling_tool #object_detection #pytorch #semantic_segmentation #tensorflow #video_annotation

CVAT is a powerful tool for annotating videos and images, especially useful for computer vision projects. It helps developers and companies annotate data quickly and efficiently. You can use CVAT online for free or subscribe for more features like unlimited data and integrations with other tools. It also offers a self-hosted option with enterprise support. CVAT supports many annotation formats and has automatic labeling options to speed up your work. It's widely used by many teams worldwide, making it a reliable choice for your data annotation needs.

https://github.com/cvat-ai/cvat

#python #deep_learning #geometric_deep_learning #graph_convolutional_networks #graph_neural_networks #pytorch

PyG (PyTorch Geometric) is a library that makes it easy to work with Graph Neural Networks (GNNs) using PyTorch. Here’s why it’s beneficial You can start training a GNN model with just 10-20 lines of code, especially if you're already familiar with PyTorch.
- **Comprehensive Models** The library supports large-scale graphs, dynamic graphs, and heterogeneous graphs, making it versatile for various applications.
- **Scalability** It provides extensive documentation, tutorials, and examples to help you get started quickly.

Overall, PyG simplifies the process of working with GNNs, making it a powerful tool for machine learning on graph-structured data.

https://github.com/pyg-team/pytorch_geometric

#python #deep_learning #glow_tts #hifigan #melgan #multi_speaker_tts #python #pytorch #speaker_encoder #speaker_encodings #speech #speech_synthesis #tacotron #text_to_speech #tts #tts_model #vocoder #voice_cloning #voice_conversion #voice_synthesis

The new version of TTS (Text-to-Speech) from Coqui.ai, called TTSv2, is now available with several improvements. It supports 16 languages and has better performance overall. You can fine-tune the models using the provided code and examples. The TTS system can now stream audio with less than 200ms latency, making it very responsive. Additionally, you can use over 1,100 Fairseq models and new features like voice cloning and voice conversion. This update also includes faster inference with the Tortoise model and support for multiple speakers and languages. These enhancements make it easier and more efficient to generate high-quality speech from text.

https://github.com/coqui-ai/TTS

#python #fno #fourier_neural_operator #neural_operator #neural_operators #partial_differential_equations #pde #pytorch #tensor_methods #tensorization #tensorly #uno

The `neuraloperator` library is a powerful tool for learning neural operators in PyTorch. It allows you to learn mappings between function spaces, which is different from regular neural networks. This library is useful because it makes your trained models work with data of any resolution, meaning you don't have to worry about the size of your data. You can easily install it using `pip install neuraloperator` and start training operators right away. The library also offers efficient models like the Tucker Tensorized FNO, which reduces the number of parameters needed, making it faster and more efficient. This helps you train and use complex models more effectively.

https://github.com/neuraloperator/neuraloperator

#python #cuda #deepseek #deepseek_llm #deepseek_v3 #inference #llama #llama2 #llama3 #llama3_1 #llava #llm #llm_serving #moe #pytorch #transformer #vlm

SGLang is a tool that makes working with large language models and vision language models much faster and more manageable. It has a fast backend runtime that optimizes model performance with features like prefix caching, continuous batching, and quantization. The frontend language is flexible and easy to use, allowing for complex tasks like chained generation calls and multi-modal inputs. SGLang supports many different models and has an active community behind it. This means you can get your models running quickly and efficiently, saving time and resources. Additionally, the extensive documentation and community support make it easier to get started and resolve any issues.

https://github.com/sgl-project/sglang

#python #gpu #llm #pytorch #transformers

The `ipex-llm` library is a powerful tool for accelerating Large Language Models (LLMs) on Intel GPUs, NPUs, and CPUs. It integrates seamlessly with popular frameworks like HuggingFace transformers, LangChain, LlamaIndex, and more. Here are the key benefits `ipex-llm` optimizes LLM performance with advanced quantization techniques (FP8, FP6, FP4, INT4) and self-speculative decoding, leading to significant speedups.
- **Wide Model Support** It works on various Intel hardware such as Arc GPUs, Core Ultra NPUs, and CPUs, making it versatile for different setups.
- **Easy Integration** Detailed quickstart guides, code examples, and tutorials help users get started quickly.

Overall, `ipex-llm` enhances the performance and usability of LLMs on Intel hardware, making it a valuable tool for developers and researchers.

https://github.com/intel/ipex-llm

#python #asr #automatic_speech_recognition #conformer #e2e_models #production_ready #pytorch #speech_recognition #transformer #whisper

WeNet is a powerful tool for speech recognition that helps turn spoken words into text. It's designed to be easy to use and works well in real-world situations, making it great for businesses and developers. WeNet provides accurate results on many public datasets and is lightweight, meaning it doesn't require a lot of resources to run. This makes it beneficial for users who need reliable speech-to-text functionality without complex setup or maintenance.

https://github.com/wenet-e2e/wenet

#cplusplus #cuda #cutlass #gpu #pytorch

Flux is a library that helps speed up machine learning on GPUs by overlapping communication and computation tasks. It supports various parallelisms in model training and inference, making it compatible with PyTorch and different Nvidia GPU architectures. This means you can train models faster because Flux combines the steps of sending data between GPUs (communication) and doing calculations (computation), allowing them to happen at the same time. This overlap reduces overall training time, which is beneficial for users working with large or complex models.

https://github.com/bytedance/flux

#jupyter_notebook #cnn #colab #colab_notebook #computer_vision #deep_learning #deep_neural_networks #fourier #fourier_convolutions #fourier_transform #gan #generative_adversarial_network #generative_adversarial_networks #high_resolution #image_inpainting #inpainting #inpainting_algorithm #inpainting_methods #pytorch

LaMa is a powerful tool for removing objects from images. It uses special techniques called Fourier Convolutions, which help it understand the whole image at once. This makes it very good at filling in large areas that are missing. LaMa can even work well with high-resolution images, even if it was trained on smaller ones. This means you can use it to fix photos where objects are in the way, making them look natural and complete again.

https://github.com/advimman/lama

#python #deep_learning #intel #machine_learning #neural_network #pytorch #quantization

Intel Extension for PyTorch boosts the speed of PyTorch on Intel hardware, including both CPUs and GPUs, by using special features like AVX-512, AMX, and XMX for faster calculations[5][2][4]. It supports many popular large language models (LLMs) such as Llama, Qwen, Phi, and DeepSeek, offering optimizations for different data types and easy GPU acceleration. This means you can run advanced AI models much faster and more efficiently on your Intel computer, with simple setup and support for both ready-made and custom models.

https://github.com/intel/intel-extension-for-pytorch

#jupyter_notebook #ai #artificial_intelligence #chatgpt #deep_learning #from_scratch #gpt #language_model #large_language_models #llm #machine_learning #python #pytorch #transformer

You can learn how to build your own large language model (LLM) like GPT from scratch with clear, step-by-step guidance, including coding, training, and fine-tuning, all explained with examples and diagrams. This approach mirrors how big models like ChatGPT are made but is designed to run on a regular laptop without special hardware. You also get access to code for loading pretrained models and fine-tuning them for tasks like text classification or instruction following. This helps you deeply understand how LLMs work inside and lets you create your own functional AI assistant, gaining practical skills in AI development[1][2][3][4].

https://github.com/rasbt/LLMs-from-scratch

#other #automl #chatgpt #data_analysis #data_science #data_visualization #data_visualizations #deep_learning #gpt #gpt_3 #jax #keras #machine_learning #ml #nlp #python #pytorch #scikit_learn #tensorflow #transformer

This is a comprehensive, regularly updated list of 920 top open-source Python machine learning libraries, organized into 34 categories like frameworks, data visualization, NLP, image processing, and more. Each project is ranked by quality using GitHub and package manager metrics, helping you find the best tools for your needs. Popular libraries like TensorFlow, PyTorch, scikit-learn, and Hugging Face transformers are included, along with specialized ones for time series, reinforcement learning, and model interpretability. This resource saves you time by guiding you to high-quality, actively maintained libraries for building, optimizing, and deploying machine learning models efficiently.

https://github.com/ml-tooling/best-of-ml-python