DeepFTSG is the proposed network used for moving object detection.

Associating and Segmenting Objects with Transformers in High Quality (ASOT)

Refine high-quality datasets and visual AI models

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

Ensemble Detection Framework for cell tracking.

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

Resources for running compute jobs on the NSF NRP Nautilus HyperCluster

AI Toolkit for Healthcare Imaging

A simple Segment Anything WebUI based on Gradio.

Gradio UI for running Meta AI's Segment Anything on own hardware. Promptable segmentation via keypoints and bounding boxes.

ORM

Run GPT model on the browser with WebGPU. An implementation of GPT inference in less than ~1500 lines of vanilla Javascript.

Official repository of "Diffusion Adversarial Representation Learning for Self-supervised Vessel Segmentation", ICLR 2023.

A collection of sorting algorithms implemented in JS

Network Analysis in Python

ChatGPT @ Home: Large Language Model (LLM) chatbot application, written by ChatGPT

1st solution for Retinal Image Analysis for multi-Disease Detection Challenge(RIADD (ISBI-2021))

A library to inspect and extract intermediate layers of PyTorch models.

[CVPR 2022 Oral] Official Pytorch Implementation of "OmniFusion: 360 Monocular Depth Estimation via Geometry-Aware Fusion"

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

Motion U-Net is multi-cue autoencoder deep architecture for robust moving object detection

DziriBERT: a Pre-trained Language Model for the Algerian Dialect

🕹 Interactive K-Means with Qt and OpenGL, written in C++.

Importance of Self-Consistency in Active Learning for Semantic Segmentation (BMVC 2020)

A CUDA implementation of the marching cubes algorithm to reconstruct a 3D model from a CT Scan