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

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

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

Pretrain, finetune, deploy 20+ LLMs on your own data. Uses state-of-the-art techniques: flash attention, FSDP, 4-bit, LoRA, and more.

Tutorial Materials for "The Fundamentals of Modern Deep Learning with PyTorch" workshop at PyCon 2024

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

Super-resolution of 10 Sentinel-2 bands to 5-meter resolution, starting from L1C or L2A (Theia format) products.

Machine Learning Q and AI book

Implementing a ChatGPT-like LLM from scratch, step by step

Code Repository for Machine Learning with PyTorch and Scikit-Learn

This repository provides inference code to compute canopy height maps from aerial images, as described in the paper "Very high resolution canopy height maps from RGB imagery using self-supervised v…

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 arch…

Machine Learning Engineering Guides and Tools

Unsupervised visualization of image datasets using contrastive learning

This repo contains the official implementation of ICCV 2023 paper "Keep It SimPool: Who Said Supervised Transformers Suffer from Attention Deficit?"

This repository contains the implementation for the paper "EMP-SSL: Towards Self-Supervised Learning in One Training Epoch."

This repository contains the code used in the paper: A high-resolution canopy height model of the Earth. Here, we developed a model to estimate canopy top height anywhere on Earth. The model estima…

Code to reproduce our ICCV paper "Towards Improved Input Masking for Convolutional Neural Networks"

The WeightWatcher tool for predicting the accuracy of Deep Neural Networks

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

A Tensorflow implementation of "Next-ViT: Next Generation Vision Transformer for Efficient Deployment in Realistic Industrial Scenarios"

Remote sensing datasets for machine and deep learning, model deployment & software

Doodler. A web application built with plotly/dash for image segmentation with minimal supervision. Plays nicely with segmentation gym, https://github.com/Doodleverse/segmentation_gym

Official Pytorch implementations for "SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation" (NeurIPS 2022)

VICRegL official code base

Unsupervised Semantic Segmentation by Distilling Feature Correspondences

Leveraging BERT and c-TF-IDF to create easily interpretable topics.

PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO