機械学習 · GitHub

As the core component of the Ascend for PyTorch community, TorchNPU is a deep learning adapter plugin built by Ascend for PyTorch, enabling the PyTorch framework to directly invoke Ascend NPU and providing developers with the powerful compute capabilities of Ascend AI processors. (About Ascend NPU: Ascend NPU (Neural Processing Unit) is a series of

• Basic Compute: Extensive support for PyTorch native APIs and custom APIs, covering mainstream AI scenarios with a consistent experience, enabling rapid model and algorithm implementation.
• Distributed: Supports accelerating distributed training via FSDP2. Core compute APIs support DTensor, along with collective communication primitives such as AllGather, AllReduce, and AllToAll, as well as point-to-point primitives like Send and Recv.

This is Andrew NG Coursera Handwritten Notes.

3 行のコードで高速かつ高精度な機械学習を実現

機械学習プログラミング100日間

Convolutional neural network for analyzing pentest screenshots

本書が主な対象とする大学院生や求職者の皆さんは、本書を読むことで得るものがあると私は信じています。しかし、最も経験豊富な研究者でさえ、本書を非常に興味深いと感じてくれることを願っています。

In this noteboook I will create a complete process for predicting stock price movements. Follow along and we will achieve some pretty good results. For that purpose we will use a Generative Adversarial Network (GAN) with LSTM, a type of Recurrent Neural Network, as generator, and a Convolutional Neural Network, CNN, as a discriminator. We use LSTM for the obvious reason that we are trying to predict time series data. Why we use GAN and specifically CNN as a discriminator? That is a good question: there are special sections on that later.

🌟The complete open-source release of the book 《 Deep Learning: Foundations and Concepts 》 and its related supporting resources

all kinds of text classification models and more with deep learning

The WeightWatcher tool for predicting the accuracy of Deep Neural Networks

Lightweight, powerful real-time speech translation with multilingual support and a multilingual UI.

• Local models: Run recognition models such as Qwen3-ASR and SenseVoiceSmall, and translation models such as HY-MT2 locally. The app can also search for and install other models from Hugging Face.
• Cloud models: Use speech recognition from Aliyun, MiniMax, and other providers; connect translation models through LLM protocols such as OpenAI-compatible APIs, Anthropic, or Ollama; or use the free MyMemory translation service.

Clean up noisy speech in real time with DPDFNet - open-source streaming speech enhancement for research, audio apps, and edge devices. Includes pretrained models, PyTorch code, ONNX/TFLite inference, 8/16/48 kHz support, and live demos.

🌟LLM / RLのオリジナル原理図100点以上📚、『大模型算法』の著者による力作！💥（LLM/RLアルゴリズムマップ100点以上）

ClearML - Auto-Magical CI/CD to streamline your AI workload. Experiment Management, Data Management, Pipeline, Orchestration, Scheduling & Serving in one MLOps/LLMOps solution

OpenPose：身体、顔、手、足を推定するリアルタイム複数人キーポイント検出ライブラリ

• 15, 18 or 25-keypoint body/foot keypoint estimation, including 6 foot keypoints. Runtime invariant to number of detected people.
• 2x21-keypoint hand keypoint estimation. Runtime depends on number of detected people. See OpenPose Training for a runtime invariant alternative.

Maia is a human-like neural network chess engine trained on millions of human games.

Automated deep learning algorithms implemented in PyTorch.

• NAS - TAS - Network Pruning via Transformable Architecture Search - NeurIPS-2019-TAS.md
• DARTS - DARTS: Differentiable Architecture Search - ICLR-2019-DARTS.md

🎨 ML Visuals には、科学的な文章の質を高めるために再利用・カスタマイズできる図版とテンプレートが含まれています。

ChatGPT资料汇总学习，持续更新......