leayz-888 Goto Github PK

bevformer

This is the official implementation of BEVFormer, a camera-only framework for autonomous driving perception, e.g., 3D object detection and semantic map segmentation.

conditionaldetr

This repository is an official implementation of the ICCV 2021 paper "Conditional DETR for Fast Training Convergence". (https://arxiv.org/abs/2108.06152)

cvprojects

computer vision projects | 计算机视觉等好玩的AI项目

dab-detr

[ICLR 2022] DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR

deeplabv3

PyTorch implementation of DeepLabV3, trained on the Cityscapes dataset.

deepstream_python_apps

DeepStream SDK Python bindings and sample applications

dn-detr

[CVPR 2022 Oral]Official implementation of DN-DETR

gfpgan

GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.

internimage

leayz-888

license-plate-recognization-pytorch

该工作的内容主要是面向**车牌识别系统。车牌的检测系统通过YOLOv3网络来实现，检测后的车牌会通过空间变换网络进行倾斜校正。校正后的图片经由LPRNet进行识别。目前在1000张图片上测试的最终准确率可达93.3%。实现者电子科技大学刘俊凯、陈昂、夏子寒

mobilenetv1_2_3-pytorch

models

A collection of pre-trained, state-of-the-art models in the ONNX format

objectdetection_script

一些关于目标检测的脚本的改进思路代码，详细请看readme.md

onnx-modifier

A tool to modify onnx models in a visualization fashion, based on Netron and Flask.

onnx-tensorrt

ONNX-TensorRT: TensorRT backend for ONNX

openpcdet_ros

OpenPCDet for ROS noetic, docker image also provided

pointnet-pointnet2

pointnet2.pytorch

A PyTorch Implementation of Pointnet++.

pointpillars_int8

ppq

PPL Quantization Tool (PPQ) is a powerful offline neural network quantization tool.

pytorch-auto-drive

PytorchAutoDrive: Segmentation models (ERFNet, ENet, DeepLab, FCN...) and Lane detection models (SCNN, PRNet, RESA, LSTR, BézierLaneNet...) based on PyTorch with fast training, visualization, benchmarking & deployment help

pytorch-cifar

95.16% on CIFAR10 with PyTorch

pytorch-fcn-easiest-demo

PyTorch Implementation of Fully Convolutional Networks (a very simple and easy demo).

pytorch-segtoolbox

用Pytorch复现常用语义分割网络，备用

pytorch2caffe

rknpu2

scnn_pytorch

Pytorch implementation of "Spatial As Deep: Spatial CNN for Traffic Scene Understanding"

simple-lama-inpainting

tensorrt

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.