機械学習 · GitHub

A comprehensive, step-by-step guide to learning Machine Learning from absolute basics to advanced topics

• Report a problem (optional): Broken links, typos, or factual errors via GitHub Issues. That is a report, not a contribution channel.
• Learn on the Study Hub: nabidinmotion.com is the canonical reader experience

MulimgViewer is a multi-image viewer that can open multiple images in one interface, which is convenient for image comparison and image stitching.

A curated list of all the Awesome --Topic Name-- lists I've found till date relevant to Data lifecycle, ML and DL.

Domain knowledge driven 3D radiation dose prediction [PMB'22]

Interactive deep learning cell segmentation using partial annotations [MICCAI'26]

Deep neural network to extract intelligent information from invoice documents.

YOLO11 research prototype for detecting people associated with potentially dangerous objects in public-area imagery, with thesis evidence, reproducibility notes, and responsible-use guidance.

Multi-Task Deep Neural Networks for Natural Language Understanding

Awesome list for medical imaging agents: radiology agents, pathology agents, segmentation agents, medical VLM agents, self-evolving agents, benchmarks, datasets, tools, and papers.

Metal-native differentiable 3D Gaussian Splatting for Apple Silicon: fused forward+backward rasterizer on PyTorch MPS, no CUDA anywhere.

Estimating the Focal Length of a Monocular Image

• 🎯 16 mm mean absolute error on a held-out set of real photographs
• 📐 Reports both the 35mm-equivalent and the physical focal length, deriving the sensor crop factor from EXIF when the camera recorded it

nannyml: post-deployment data science in python

• End sleepless nights caused by not knowing your model performance 😴
• Analyse data drift and model performance over time

The book every data scientist needs on their desk.

A comprehensive paper list of deep learning for crack detection, in terms of learning paradigms, generalizability and datasets.

Official implementation of CLIP-Mesh: Generating textured meshes from text using pretrained image-text models

Real-time object detection on Android using the YOLO network with TensorFlow

Deep learning for brain tumor MRI: detection (99.4%) and 4-class typing (94.75%) via EfficientNet transfer learning + Grad-CAM.

Annif is a multi-algorithm automated subject indexing tool for libraries, archives and museums.