Maschinelles Lernen · GitHub

GUI for marking bounded boxes of objects in images for training neural network Yolo v3 and v2

Data science interview questions and answers

Generative Flow Networks - GFlowNet

Implementation of Non-local Block.

Deep learning with cats (^._.^)

PyTorch Code for Energy-Based Transformers paper -- generalizable reasoning and scalable learning

Current state of supervised and unsupervised depth completion methods

Publikationsreife Schemata für neuronale Netzwerkarchitekturen.

Chat with your favourite LLaMA models in a native macOS app

• Supported Models: LlamaChat supports LLaMA, Alpaca and GPT4All models out of the box. Support for other models including Vicuna and Koala is coming soon. We are also looking for Chinese and French speakers to add support for Chinese LLaMA/Alpaca and Vigogne.
• Flexible Model Formats: LLamaChat is built on top of llama.cpp and llama.swift. The app supports adding LLaMA models in either their raw .pth PyTorch checkpoints form or the .ggml format.

Parametric differentiable curves with PyTorch for continuous embeddings, shape-restricted models, or KANs

• Differentiable: Custom autograd function ensures gradients flow properly through the curve evaluation.
• Vectorized: Vectorized operations for efficient batch and multi-curve evaluation.

Efficient Image Restoration with State-Dependent Forward Diffusion, TMLR 2026

An end-to-end AI pipeline that screens lung CT slices for nodules and localizes them, using patient risk factors, a CNN classifier, and U-Net segmentation.

• Multi-model decision pipeline. Three models with different roles are combined through explicit, auditable rules rather than a single opaque score.
• Disagreement-aware output. When the classifier and segmenter disagree, the system returns uncertain and states which model flagged the slice.

AI-powered deepfake detector that classifies uploaded face images and videos as Real or Fake with confidence scores. Full-stack app built with PyTorch (EfficientNet-B0), FastAPI, and Next.js — trained on 100k+ images and deployed with Vercel + Render.

This repository contains the source code for the paper First Order Motion Model for Image Animation

Learn all the mathematics required for deep learning complete with examples and explanations of their specific applications in the field and implement every concept using PyTorch.

• Mathematical Foundations: Detailed conceptual definitions paired with step-by-step solved examples.
• PyTorch Implementation: All mathematical concepts are implemented using the PyTorch framework for practical learning.

An optimized handwritten digit recognition model delivering exceptional accuracy, high-speed performance, and compatibility with low-end hardware, supported by comprehensive documentation, experiment tracking, data-driven decision-making, effective troubleshooting, and a modular project structure.

• Maximum execution speed
• Highly robust optimization

Alink is the Machine Learning algorithm platform based on Flink, developed by the PAI team of Alibaba computing platform.

An all-in-one toolkit for computer vision

• SOTA SSL Algorithms EasyCV provides state-of-the-art algorithms in self-supervised learning based on contrastive learning such as SimCLR, MoCO V2, Swav, DINO, and also MAE based on masked image modeling. We also provide standard benchmarking tools for ssl model evaluation.
• Vision Transformers EasyCV aims to provide an easy way to use the off-the-shelf SOTA transformer models trained either using supervised learning or self-supervised learning, such as ViT, Swin Transformer, and DETR Series. More models will be added in the future. In addition, we support all the pretrained models from timm.

EasyNLP: A Comprehensive and Easy-to-use NLP Toolkit

• Easy to use and highly customizable: In addition to providing easy-to-use and concise commands to call cutting-edge models, it also abstracts certain custom modules such as AppZoo and ModelZoo to make it easy to build NLP applications. It is equipped with the PAI PyTorch distributed training framework TorchAccelerator to speed up distributed training.
• Compatible with open-source libraries: EasyNLP has APIs to support the training of models from Huggingface/Transformers with the PAI distributed framework. It also supports the pre-trained models in EasyTransfer ModelZoo.