Lists (4)
Stars
A delightful Firefly III companion web app for effortless transaction tracking
Vane is an AI-powered answering engine.
A small library to rectify masked images based on the mask contour
A list of (post-hoc) XAI for time series
Code for the tutorial on "Opportunities and Challenges for Online Deep Learning" presented at ECML PKDD 2023
Code from our paper "Template-guided Illumination Correction for Document Images with Imperfect Geometric Reconstruction " (ICCVW) 2023.
A unified interface to many trajectory forecasting datasets.
Inference, training and evaluation code for our models from the paper "Inv3D: a high-resolution 3D invoice dataset for template-guided single-image document unwarping" (ICDAR) 2023.
Code to generate the Inv3D dataset from our paper "Inv3D: a high-resolution 3D invoice dataset for template-guided single-image document unwarping" (ICDAR) 2023.
Semantic Meaningfulness: Evaluating counterfactual approaches for real world plausibility
Pip package for the CVPRW 2023 Paper "Lanelet2 for nuScenes: Enabling Spatial Semantic Relationships and Diverse Map-Based Anchor Paths".
Project page for the CVPRW 2023 Paper "Lanelet2 for nuScenes: Enabling Spatial Semantic Relationships and Diverse Map-Based Anchor Paths".
The original local LLM interface. Text, vision, tool-calling, training, and more. 100% offline.
Codebase for the ECML PKDD 2022 Research Paper: Detecting Anomalies with Autoencoders on Data Streams
A playbook for systematically maximizing the performance of deep learning models.
An unofficial styleguide and best practices summary for PyTorch
ManimML is a project focused on providing animations and visualizations of common machine learning concepts with the Manim Community Library.
"TSEvo: Counterfactuals for Time Series Classification" accepted at ICMLA '22.
Collection of LaTeX resources and examples.
Python-based research interface for blackbox and hyperparameter optimization, based on the internal Google Vizier Service.
Extended LaTeX template for CVPR/ICCV papers
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
Flet enables developers to easily build realtime web, mobile and desktop apps in Python. No frontend experience required.
An Open-Source Library for the interpretability of time series classifiers
Advanced evolutionary computation library built directly on top of PyTorch, created at NNAISENSE.