Beast code in Giters

Gabe Margolis's starred repositories

build-your-own-x

Master programming by recreating your favorite technologies from scratch.

segment-anything

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.

Language:Jupyter NotebookApache-2.045724 303 658

A repository for storing models that have been inter-converted between various frameworks. Supported frameworks are TensorFlow, PyTorch, ONNX, OpenVINO, TFJS, TFTRT, TensorFlowLite (Float32/16/INT8), EdgeTPU, CoreML.

Language:PythonMIT3437 112 329

ZoeDepth

Metric depth estimation from a single image

Language:Jupyter NotebookMIT2129 31 106

orbit

Unified framework for robot learning built on NVIDIA Isaac Sim

Language:PythonNOASSERTION898 21 317

ODISE

Official PyTorch implementation of ODISE: Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models [CVPR 2023 Highlight]

Language:PythonNOASSERTION831 40 42

walk-these-ways

Sim-to-real RL training and deployment tools for the Unitree Go1 robot.

Language:PythonNOASSERTION503 15 77

extreme-parkour

ICRA 2024: Train your parkour robot in less than 20 hours.

Language:PythonNOASSERTION489 9 45

CityLearn

Official reinforcement learning environment for demand response and load shaping

Language:PythonMIT452 20 56

fc-clip

[NeurIPS 2023] This repo contains the code for our paper Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIP

Language:PythonApache-2.0267 16 31

sim-web-visualizer

Web Based Visualizer for Simulation Environments

Language:PythonMIT261 8 5

PerspectiveFields

[CVPR 2023 Highlight] Perspective Fields for Single Image Camera Calibration

Language:Jupyter NotebookNOASSERTION172 6 17

SAMFeat

The official implementation of “Segment Anything Model is a Good Teacher for Local Feature Learning”.

Language:PythonMIT100 6 4

sphere-stereo

[CVPR2021] Real-Time Sphere Sweeping Stereo from Multiview Fisheye Images

Language:PythonNOASSERTION69 5 6

gym-kuka-mujoco

An OpenAI gym environment for the Kuka arm.

Language:PythonMIT39 5 5

AsymFormer

AsymFormer: Asymmetrical Cross-Modal Representation Learning for Mobile Platform Real-Time RGB-D Semantic Segmentation

Language:PythonApache-2.025 4 10

spatial_LDA

This repository contains the implementation of an image-based LDA model for use in semi-automation of the image annotation and data curation process. It uses unsupervised Latent Dirichlet Allocation (LDA), Scale-Invariant Feature Transform (SIFT), and ImageNet pre-trained Convolutional Neural Networks (CNNs) to group unlabeled images into different topics using clustered latent features.

Language:Python13 3 1

gmargo11