mjwen
Follow
Stars
⚡ TabPFN: Foundation Model for Tabular Data ⚡
Service to examine data processing pipelines (e.g., machine learning or deep learning pipelines) for uncertainty consistency (calibration), fairness, and other safety-relevant aspects.
The net:cal calibration framework is a Python 3 library for measuring and mitigating miscalibration of uncertainty estimates, e.g., by a neural network.
Uncertainty Toolbox: a Python toolbox for predictive uncertainty quantification, calibration, metrics, and visualization
E3x is a JAX library for constructing efficient E(3)-equivariant deep learning architectures built on top of Flax.
Segment Anything in Medical Images
A high-quality tool for convert PDF to Markdown and JSON.一站式开源高质量数据提取工具，将PDF转换成Markdown和JSON格式。
The book every data scientist needs on their desk.
PyTorch native quantization and sparsity for training and inference
A Python toolbox for performing gradient-free optimization
A tiling window manager for macOS based on binary space partitioning
Perl script to add indentation (leading horizontal space) to LaTeX files. It can modify line breaks before, during and after code blocks; it can perform text wrapping and paragraph line break remov…
An extremely fast LaTeX formatter written in Rust
Bayesian Modeling and Probabilistic Programming in Python
The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑🔬
Zotero is a free, easy-to-use tool to help you collect, organize, annotate, cite, and share your research sources.
The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…
Neural Networks: Zero to Hero
TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients.
Fine-tune SAM (Segment Anything Model) for computer vision tasks such as semantic segmentation, matting, detection ... in specific scenarios
Fine-tune Segment-Anything Model with Lightning Fabric.
EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything
The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
A machine learning software for extracting information from scholarly documents
A web scraping tool to systematically extract the text of scientific papers and corresponding metadata from university accessible journals.