ingestr is a CLI tool to copy data between any databases with a single command seamlessly.

Build data pipelines with SQL and Python, ingest data from different sources, add quality checks, and build end-to-end flows.

A scikit-learn based module for multi-label et. al. classification

Code repository for the online course Hyperparameter Optimization for Machine Learning

Pretrained ConvNets for pytorch: NASNet, ResNeXt, ResNet, InceptionV4, InceptionResnetV2, Xception, DPN, etc.

Chronos: Pretrained Models for Probabilistic Time Series Forecasting

Code for reproducing the results of our "In Defense of the Triplet Loss for Person Re-Identification" paper.

Performance of various open source GBM implementations

A minimal benchmark for scalability, speed and accuracy of commonly used open source implementations (R packages, Python scikit-learn, H2O, xgboost, Spark MLlib etc.) of the top machine learning al…

👑 Multivariate exploratory data analysis in Python — PCA, CA, MCA, MFA, FAMD, GPA

1 Line of code data quality profiling & exploratory data analysis for Pandas and Spark DataFrames.

🔅 Shapash: User-friendly Explainability and Interpretability to Develop Reliable and Transparent Machine Learning Models

[ECCV 2024] Single Image to 3D Textured Mesh in 10 seconds with Convolutional Reconstruction Model.

Datasets, Transforms and Models specific to Computer Vision

Official PyTorch implementation of SegFormer

Refine high-quality datasets and visual AI models

ADE20K Dataset

OpenMMLab Detection Toolbox and Benchmark

COCO API - Dataset @ http://cocodataset.org/

Public repository for "The Surprising Effectiveness of Test-Time Training for Abstract Reasoning"

Publication-ready NN-architecture schematics.

My guide to setting up various Linux OSs

Open Source Computer Vision Library

A community-maintained Python framework for creating mathematical animations.

Download, model, analyze, and visualize street networks and other geospatial features from OpenStreetMap.

This repository accompanies the book "Deep Learning for Vision Systems".

(ECCV'22) FADE: Fusing the Assets of Decoder and Encoder for Task-Agnostic Upsampling