Explore21's repositories
algorithmic-efficiency
MLCommons Algorithmic Efficiency is a benchmark and competition measuring neural network training speedups due to algorithmic improvements in both training algorithms and models.
awesome-virtual-try-on
A curated list of awesome research papers, projects, code, dataset, workshops etc. related to virtual try-on.
diffseg
DiffSeg is an unsupervised zero-shot segmentation method using attention information from a stable-diffusion model. This repo implements the main DiffSeg algorithm and additionally includes an experimental feature to add semantic labels to the masks based on a generated caption.
DIS
This is the repo for our new project Highly Accurate Dichotomous Image Segmentation
dog
DoG is SGD's Best Friend: A Parameter-Free Dynamic Step Size Schedule
EMP-SSL
This repository contains the implementation for the paper "EMP-SSL: Towards Self-Supervised Learning in One Training Epoch."
explore_forward_forward
Explore Geoffrey Hinton's Forward Forward algorithm for training neutral networks
GPU-Puzzles
Solve puzzles. Learn CUDA.
IC-Light
More relighting!
langchain-chat-with-documents
Chat with documents (pdf, docx, txt) using ChatGPT and Langchain
LLM-Training-Puzzles
What would you do with 1000 H100s...
lora
Using Low-rank adaptation to quickly fine-tune diffusion models.
multimodal-maestro
Effective prompting for Large Multimodal Models like GPT-4 Vision or LLaVA. 🔥
notebooks
Google Colab notebooks
stable-diffusion-tensorflow
Stable Diffusion in TensorFlow / Keras
supervision
We write your reusable computer vision tools. 💜
tajwarfahim.github.io
Personal website for Fahim Tajwar
Tensor-Puzzles
Solve puzzles. Improve your pytorch.
text2cinemagraph
Official Pytorch implementation of Text2Cinemagraph: Synthesizing Artistic Cinemagraphs from Text
Track-Anything
Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI.
Transformer-Puzzles
Puzzles for exploring transformers
Transformers-Tutorials
This repository contains demos I made with the Transformers library by HuggingFace.
vid2vid-zero
Zero-Shot Video Editing Using Off-The-Shelf Image Diffusion Models
VideoMAE
[NeurIPS'22] VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training
vit-cls_emb
Accompanying code for "Analyzing Vision Tranformers in Class Embedding Space" (NeurIPS '23)