Harpreet Sahota

awesome-cvpr-2024. 🤩 An AWESOME Curated List of Papers, Workshops, Datasets, and Challenges from CVPR 2024

gui_agent_research_landscape. An awesome repository that maps the current landscape of GUI/OS Agent research

Hands-on-Data-Centric-Visual-AI. This repo contains code for the Coursera MOOC Hands-on Data Centric Visual AI

NVLabs_CRADIOV3. Implementing NVLabs C-RADIOv3 Embeddings Model as Remotely Sourced Zoo Model for FiftyOne

vggt. Implemeting Meta AI's VGGT as a FiftyOne Remote Zoo Model

moondream3. Implementing moondream3 as a Remote Source Zoo Model for FiftyOne

gui_dataset_creator. GUI Dataset Collector: A Tool for Capturing and Annotating GUI Interactions with annotations in COCO format

five-handy-things-embeddings. Five cool things you can do with Embeddings using FiftyOne!

fast_vlm. Integrating FastVLM as a Remote Source Zoo Model for FiftyOne

medgemma. Implementing MedGemma as a Remote Zoo Model for FiftyOne

CVPR-2024-Papers. Code to scrape CVPR website for list of accepted papers, find their arXiv links, extract metadata, and download pdfs

synthetic_gui_samples_plugins. A FiftyOne plugin for generating synthetic samples for datasets in COCO4GUI format

langchain-zoomcamp. Materials for 🦜🔗LangChain zoomcamp

moondream2-plugin. Use the Moondream2 model on your FiftyOne Dataset

car_dd_dataset_workshop. A workshop exploring the CarDD dataset + FiftyOne's Functionality

WayveScene101-to-FiftyOne. Parsing WayveScene101 datsaet into FiftyOne format

Kimi_VL_A3B. A FiftyOne Remotely Sourced Zoo Model integration for Moonshot AI's Kimi-VL-A3B models enabling object detection, keypoint localization, and image classification with strong GUI and document understanding capabilities.

UI_TARS. Implementing UI-TARS-1.5 as a Remote Zoo Model for FiftyOne

janus-vqa-fiftyone. A plugin to perform VQA tasks using Janus

getting-started-fo-experiences. Getting started with Fiftyone

visual_agents_workshop. Code for the Building GUI Agents That Actually Work series of workshops

crops3d_to_fiftyone. Parsing Crops3D dataset to FiftyOne format

isaac0_1. Integrating Isaac-0.1 by Perceptron as a Remote Source Zoo Model in FiftyOne

os_atlas. Integrating OS-Atlas Base into FiftyOne as a Remote Source Zoo Model

fiftyone_lerobot_importer. Import your LeRobot format dataset into FiftyOne format

paligemma2. Implementing PaliGemma-2-Mix as a Remote Zoo Model for FiftyOne

DCVAI-Challenge-Example-Submission. An example for submitting your results to the Data Centric Visual AI Competition

synthhuman_to_fiftyone. Parsing a subset of the SynthHuman dataset to FiftyOne format

nemo_retriever_parse_plugin. Implementing NVIDIA NeMo Retriever Parse as a FiftyOne Remote Zoo Model

minicpm-v. Integrating MiniCPM-V as a Remote Source Zoo Model in FiftyOne

florence2. Implementing Florence2 as a Remote Zoo Model for FiftyOne

hiera-video-embeddings-plugin. Videos Embeddings using Hiera for your FiftyOne Dataset

sql-from-the-ground-up. Learn SQL from the absolute fundamentals.

coco4gui_fiftyone. Implementing the COCO4GUI dataset type in FiftyOne with importers and exports

MiMo_VL. Implementing MiMo-VL as a Remote Zoo Model for FiftyOne

moondream2. Moondream2 implementation as a remotely sourced zoo model for FiftyOne

visual_document_retrieval. A FiftyOne Remotely Sourced Zoo Model integration for LlamaIndex's VDR model enabling natural language search across document images, screenshots, and charts in your datasets.

Nemotron_Nano_VL. Implementing Llama-3.1-Nemotron-Nano-VL-8B-V1 as a Remote Zoo Model for FiftyOne

vitpose-plugin. Run ViTPose Models from Hugging Face on your FiftyOne Dataset

fine-tuning-with-sft. Banishing spaghetti code from Colab notebooks! A practical toolkit for fine-tuning language models without drowning in boilerplate code, all while juggling with the only GPU I've got. 🍝🚀

practical-rag-scratchpad. My learnings, thoughts, and draft work for my upcoming Wiley Publications Book titled "Practical Retrieval Augmented Generation"

gui_actor. Implementing Microsoft's GUI Actor as a Remote Zoo Model for FiftyOne

medsiglip. Implementing MedSigLIP as a Remote Zoo Model for FiftyOne

ShowUI. Integrating ShowUI into FiftyOne as a Remote Source Zoo Model

GUI-Actor-for-FiftyOne. Fine-tuning GUI Actor to interact with the FiftyOne App

skyscenes-to-fiftyone. This is code that parses the SkyScenes dataset into FiftyOne format

depthpro-plugin. A FiftyOne plugin for applying the Apple Depth Pro model to your dataset

dataset-safari. Exploring some cool datasets from AI conferences in 2024

zero-shot-prediction-plugin. Run zero-shot prediction models on your data

pretrained-microscopy-models. Integrating microscopy segmentation and analysis models as FiftyOne Remote Source Zoo Models

deci_rag_demo. Jupyter Notebook

dataset-loader-toolkit. A configurable toolkit for loading and preprocessing datasets from the Hugging Face Hub with ease.