deanofthewebb

aind_cv_capstone

In this project, I combine knowledge of computer vision techniques (OpenCV) and deep learning to build and end-to-end facial keypoint recognition system.

aiVision

behavioral_cloning_pipeline

Designed, trained, and validated a deep convolutional neural network model that predicts a steering angle from simulator input data

ChangeFormer

Official PyTorch implementation of our IGARSS'22 paper: A Transformer-Based Siamese Network for Change Detection

Data-Science-Starter-Kit

Dockerized Automated Configuration of TensorFlow 1.3 GPU in [Ubuntu 14.04 + CUDA 8.0 + cuDNN]

gsnet

Official code of ECCV 2020 paper "GSNet: Joint Vehicle Pose and Shape Reconstruction with Geometrical and Scene-aware Supervision". GSNet performs joint vehicle pose estimation and vehicle shape reconstruction with single RGB image as input.

lane_lines_tracking_pipeline

An automated lane-line tracking pipeline using advanced OpenCV techniques

spotify_streamer

Spotify Streamer Android App

traffic-sign-classification-with-keras

Traffic Signs Classifier Implemented with Keras Framework - [German Traffic Sign Recognition Benchmark](http://benchmark.ini.rub.de/?section=gtsrb&subsection=news) dataset

vehicle_detection_tracking_pipeline

A Tracking Pipeline for the Udacity Vehicle Detection Project

deanofthewebb/Anima

33B Chinese LLM, DPO QLORA, 100K context, AirLLM 70B inference with single 4GB GPU

deanofthewebb/AS-One

Easy & Modular Computer Vision Detectors and Trackers - Run YOLOv7,v6,v5,R,X in under 20 lines of code.

deanofthewebb/bubogpt

BuboGPT: Enabling Visual Grounding in Multi-Modal LLMs

deanofthewebb/DeepStream-Yolo

NVIDIA DeepStream SDK 6.0.1 configuration for YOLO models

deanofthewebb/DeepStream-Yolo-Seg

NVIDIA DeepStream SDK 6.3 / 6.2 / 6.1.1 / 6.1 / 6.0.1 / 6.0 implementation for YOLO-Segmentation models

deanofthewebb/deepstream_tao_apps

Sample apps to demonstrate how to deploy models trained with TAO on DeepStream

deanofthewebb/Depth-Anything-ONNX

ONNX-compatible Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data

deanofthewebb/DTLN

Tensorflow 2.x implementation of the DTLN real time speech denoising model. With TF-lite, ONNX and real-time audio processing support.

deanofthewebb/examples

Client code examples & integrations that utilize LM Studio's local inference server

deanofthewebb/image-quality-issues

FiftyOne Plugin for finding common image quality issues

deanofthewebb/label-studio-ml-backend

Configs and boilerplates for Label Studio's Machine Learning backend

deanofthewebb/minSDXL

Huggingface-compatible SDXL Unet implementation that is readily hackable

deanofthewebb/ml-facelit

Official repository of FaceLit: Neural 3D Relightable Faces (CVPR 2023)

deanofthewebb/mojo

The Mojo Programming Language

deanofthewebb/NeMo

NeMo: a toolkit for conversational AI

deanofthewebb/OSWorld

OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments

deanofthewebb/PaddleSpeech

Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translation and Keyword Spotting. Won NAACL2022 Best Demo Award.

deanofthewebb/PaliGemma

This repository contains examples of using PaliGemma for tasks such as object detection, segmentation, image captioning, etc.

deanofthewebb/recognize-anything

Code for the Recognize Anything Model (RAM) and Tag2Text Model

deanofthewebb/s2client-proto

StarCraft II Client - protocol definitions used to communicate with StarCraft II.

deanofthewebb/Segment-and-Track-Anything

An open-source project dedicated to tracking and segmenting any objects in videos, either automatically or interactively. The primary algorithms utilized include the Segment Anything Model (SAM) for key-frame segmentation and Associating Objects with Transformers (AOT) for efficient tracking and propagation purposes.

deanofthewebb/tao_pytorch_backend

TAO Toolkit deep learning networks with PyTorch backend

deanofthewebb/TensorRT-LLM

TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.

deanofthewebb/ToolBench

An open platform for training, serving, and evaluating large language model for tool learning.

deanofthewebb/UniCL

[CVPR 2022] Official code for "Unified Contrastive Learning in Image-Text-Label Space"

deanofthewebb/unilm

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

deanofthewebb/vipy

Python Tools for Visual Dataset Transformation

deanofthewebb/whisper

Robust Speech Recognition via Large-Scale Weak Supervision

deanofthewebb/YOLO-World

[CVPR 2024] Real-Time Open-Vocabulary Object Detection

deanofthewebb/yolov9

Implementation of paper - YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information