Dongyuxin's repositories
----------
立体标定-校正-匹配
ImageSpider
百度图片爬虫,可以爬取原图
retinaface_tensorRT
tensorRT retinaface mobilenet
2019-CCF-BDCI-OCR-MCZJ-OCR-IdentificationIDElement
2019CCF-BDCI大赛 最佳创新探索奖获得者 基于OCR身份证要素提取赛题冠军 天晨破晓团队 赛题源码
ava_downloader
:arrow_double_down: Download AVA dataset (A Large-Scale Database for Aesthetic Visual Analysis)
bag2pcd_ros
extracting specific topic of point clouds from rosbag into pcd.
BEVFormer
[ECCV 2022] This is the official implementation of BEVFormer, a camera-only framework for autonomous driving perception, e.g., 3D object detection and semantic map segmentation.
BEVFusion
Offical PyTorch implementation of "BEVFusion: A Simple and Robust LiDAR-Camera Fusion Framework"
Coursera-ML-AndrewNg-Notes
吴恩达老师的机器学习课程个人笔记
DeepFashion
Apparel detection using deep learning
Face-Detector-1MB-with-landmark
1M人脸检测模型(含关键点)
hw
RTL, Cmodel, and testbench for NVDLA
keras-centernet
A Keras implementation of CenterNet with pre-trained model (unofficial)
MNN-APPLICATIONS
MNN applications by MNN, JNI exec, RK3399. Support tflite\tensorflow\caffe\onnx models.
OCR_DataSet
收集并整理有关OCR的数据集并统一标注格式,以便实验需要
onnx-simplifier
Simplify your onnx model
ORB-SLAM3forWindows
ORB-SLAM3 for Windows Platform
ORB_SLAM3_detailed_comments
Detailed comments for ORB-SLAM3
pytorch-image-models
PyTorch image models, scripts, pretrained weights -- (SE)ResNet/ResNeXT, DPN, EfficientNet, MixNet, MobileNet-V3/V2, MNASNet, Single-Path NAS, FBNet, and more
PytorchOCR
基于Pytorch的OCR工具库,支持常用的文字检测和识别算法
research-ms-loss
MS-Loss: Multi-Similarity Loss for Deep Metric Learning
roberta_zh
RoBERTa中文预训练模型: RoBERTa for Chinese
SLAMPaperReading
泡泡机器人北京线下SLAM论文分享资料
TensorRT-For-YOLO-Series
tensorrt for yolo series, nms plugin support
VINS-Fusion
An optimization-based multi-sensor state estimator
VINS_Fusion-comment
VINS-Fusion注释版本. This is a comment version of VINS_Fusion to record my own comprehension. The original codes fork from https://github.com/HKUST-Aerial-Robotics/VINS-Fusion.
YOLOv3-model-pruning
对 YOLOv3 做模型剪枝(network slimming),对于 oxford hand 数据集(因项目需要),模型剪枝后的参数量减少 80%,Infer 的速度达到原来 2 倍,mAP 基本不变