perseusdg Goto Github PK

adabins

torch.jit.script and torch.jit.trace scripts for adabins

airsim

Open source simulator for autonomous vehicles built on Unreal Engine / Unity, from Microsoft AI & Research

bts

From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimation

carla

Open-source simulator for autonomous driving research.

chatgpt_ros

ROS wrapper for ChatGPT API

cube_slam

CubeSLAM: Monocular 3D Object Detection and SLAM

deep-image-retrieval

End-to-end learning of deep visual representations for image retrieval

docker_setup

dpt

Dense Prediction Transformers

hackathon_vc_eth

kratos-qstp-assignment-solutions

Solutions to kratos qstp 2019

linux

Linux kernel source tree

monodepth2

[ICCV 2019] Monocular depth estimation from a single image

msi-ec

nvtensorrt

NVIDIA® TensorRT™, an SDK for high-performance deep learning inference, includes a deep learning inference optimizer and runtime that delivers low latency and high throughput for inference applications.

opencvdatasetmodifier

Creating large datasets from a small pool of images

openglue

Open Source Graph Neural Net Based Pipeline for Image Matching

ort

A Rust wrapper for ONNX Runtime

pidnet

This is the official repository for our recent work: PIDNet

plat-raspi

Unikraft on Raspberry Pi 3 B+

resnet_test

ros2_whisper

Whisper C++ inference action server for ROS 2

rosgpt

ROSGPT is a pioneering approach that combines the power of ChatGPT and ROS (Robot Operating System) to redefine human-robot interaction. By leveraging large language models like ChatGPT, ROSGPT enables the conversion of unstructured human language into actionable robotic commands. T

sgdepth

solar

PyTorch code for "SOLAR: Second-Order Loss and Attention for Image Retrieval". In ECCV 2020

tensorflow

An Open Source Machine Learning Framework for Everyone

tensorrt

PyTorch/TorchScript compiler for NVIDIA GPUs using TensorRT

tensorrt-rs

Rust library for running TensorRT accelerated deep learning models

tkdnn

Deep neural network library and toolkit to do high performace inference on NVIDIA jetson platforms

track-anything

Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI.