mispa-ms

super-gradients

Easily train or fine-tune SOTA computer vision models with one open source training library. The home of Yolo-NAS.

micrograd

A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API

py-motmetrics

:bar_chart: Benchmark multiple object trackers (MOT) in Python

TrackEval

HOTA (and other) evaluation metrics for Multi-Object Tracking (MOT).

ultralytics

NEW - YOLOv8 🚀 in PyTorch > ONNX > OpenVINO > CoreML > TFLite

BoT-SORT

BoT-SORT: Robust Associations Multi-Pedestrian Tracking

VideoX

VideoX: a collection of video cross-modal models

CLIP

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

train-CLIP

A PyTorch Lightning solution to training OpenAI's CLIP from scratch.

KalmanFilter

ByteTrack

[ECCV 2022] ByteTrack: Multi-Object Tracking by Associating Every Detection Box

vision_transformer

awesome-multimodal-ml

Reading list for research topics in multimodal machine learning

stable-diffusion

Latent Text-to-Image Diffusion

datasets

🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools

transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

video-transformers

Easiest way of fine-tuning HuggingFace video classification models

Transformers-Tutorials

This repository contains demos I made with the Transformers library by HuggingFace.

pytorch3d

PyTorch3D is FAIR's library of reusable components for deep learning with 3D data

leetcode-patterns

A pattern-based approach for learning technical interview questions

ClassyVision

An end-to-end PyTorch framework for image and video classification

system-design-interview

System design interview for IT companies

system-design-primer

Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.

E2E-TAD

[CVPR 2022] An Empirical Study of End-to-end Temporal Action Detection

BMN-Boundary-Matching-Network

A pytorch-version implementation codes of paper: "BMN: Boundary-Matching Network for Temporal Action Proposal Generation", which is accepted in ICCV 2019.

action-detection

temporal action detection with SSN

YOLOv6

YOLOv6: a single-stage object detection framework dedicated to industrial applications.

zero-shot-automl-with-pretrained-models

Official repository for the paper "Zero-Shot AutoML with Pretrained Models"

machine-learning-systems-design

A booklet on machine learning systems design with exercises. NOT the repo for the book "Designing Machine Learning Systems"

autovideo

AutoVideo: An Automated Video Action Recognition System