itsprakhar

scaling_on_scales

When do we not need larger vision models?

jepa

PyTorch code and models for V-JEPA self-supervised learning from video.

RL-algorithm-to-maximize-profit-for-a-cab-driver

Developing an RL based algorithm to maximize long term profit for cab drivers in a simulated environment.

117-Class-Image-Classification-Using-Eficientnet

In this notebook I have used Efficientnet to classify images containing people in different Yoga poses 🧘 (Yogasanas). I have achieved highest validation accuracy of 75% in this notebook. Feel free to fork this notebook and try to improve the model accuracy 😀

Dino_V2

Dino V2 for Classification, PCA Visualization, Instance Retrival: https://arxiv.org/abs/2304.07193

Downstream-Dinov2

Downstream-Dino-V2: A GitHub repository featuring an easy-to-use implementation of the DINOv2 model by Facebook for downstream tasks such as Classification, Semantic Segmentation and Monocular depth estimation.

gpt4-image-api

Small tool using selenium to get a temporary API endpoint for the ChatGPT Image Input / image recognition feature. Very quickly made, you should not rely on this on prod.

yolox-face-detection

How to train and use Yolox on custom dataset

ddg-image-downloader

Lazy way to download images from Duck Duck Go search results in bulk

DuckDuckGoImages

Search and download images using DuckDuckGo search engine

autodistill

Images to inference with no labeling (use foundation models to train supervised models).

AutoYOLO

ijepa

Official codebase for I-JEPA, the Image-based Joint-Embedding Predictive Architecture. First outlined in the CVPR paper, "Self-supervised learning from images with a joint-embedding predictive architecture."

hiera

Hiera: A fast, powerful, and simple hierarchical vision transformer.

dinov2

PyTorch code and models for the DINOv2 self-supervised learning method.

first-contributions

🚀✨ Help beginners to contribute to open source projects