Triton backend that enables pre-process, post-processing and other logic to be implemented in Python.

This repository contains tutorials and examples for Triton Inference Server

NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.

The Triton Inference Server provides an optimized cloud and edge inferencing solution.

(CVPR 2021 Oral) Open World Object Detection

A General Toolbox for Identifying Object Detection Errors

An easy to use PyTorch to TensorRT converter

A project that optimizes OWL-ViT for real-time inference with NVIDIA TensorRT.

[CVPR 2022] Official Pytorch code for OW-DETR: Open-world Detection Transformer

Convert coco dataset to tfrecord for the tensorflow detection API.

Deep Learning for Camera Calibration and Beyond: A Survey

Fast and Accurate Extrinsic Calibration for Multiple LiDARs and Cameras

Standalone TFRecord reader/writer with PyTorch data loaders

A Collection of LiDAR-Camera-Calibration Papers, Toolboxes and Notes

RelTR: Relation Transformer for Scene Graph Generation: https://arxiv.org/abs/2201.11460v2

DockerFile with GPU support for TensorFlow and OpenCV

A PyTorch implementation of D-RISE

Keras documentation, hosted live at keras.io

基于TensorFlow2.x实现的YOLOv3，支持在自定义数据集上训练，支持保存为TFLite模型。A tensorflow2 implementation of YOLO_V3(Supports training on custom dataset and saving as tflite models.).

Convert CIFAR-10 and CIFAR-100 datasets into PNG images

CIFAR-10 raw jpeg images

Concept activation vectors for Keras

Code for the TCAV ML interpretability project

Google Research

YoloV3 Implemented in Tensorflow 2.0

Command-line program to download videos from YouTube.com and other video sites

Detect model's attention

End-to-End Object Detection with Transformers

Infrastructures™ for Machine Learning Training/Inference in Production.