本仓库主要包含了针对目标检测数据集的增强手段和源码：图像的旋转，镜像，裁剪，亮度/对比度的变换等
☆134Dec 16, 2020Updated 5 years ago
Alternatives and similar repositories for DataAugmentation_ForObjectDetect
Users that are interested in DataAugmentation_ForObjectDetect are comparing it to the libraries listed below
Sorting:
- 目标检测数据集制作:VOC,COCO,YOLO等常用数据集格式的制作和互相转换脚本☆475Oct 21, 2021Updated 4 years ago
- 计算目标检测的指标：mAP，检出率，漏检率☆11Jan 29, 2021Updated 5 years ago
- 对VOC数据集进行数据增强☆23Jul 16, 2022Updated 3 years ago
- 基于pytorch的目标检测数据增强工具包。☆18Oct 21, 2021Updated 4 years ago
- 使用onnxruntime部署文档矫正，包括文档扭曲/模糊/阴影等情况，依然是包含C++和Python两个版本的程序☆16Jan 3, 2025Updated last year
- FingerGAN: A Constrained Fingerprint Generation Scheme for Latent Fingerprint Enhancement☆23May 23, 2024Updated last year
- Image augmentation and change bounding box at the same time.☆13Jun 20, 2022Updated 3 years ago
- 目标检测，关键点检测。A pure version of CenterNet, convenient for secondary development and easy to understand.☆21Dec 9, 2020Updated 5 years ago
- 飞翔的荷兰人带你入门目标检测-第一季(Yolo-v1)☆23Mar 24, 2023Updated 2 years ago
- ☆20Jan 30, 2021Updated 5 years ago
- This Repo will help to augment images with annotation files for object Detection☆10Mar 15, 2023Updated 3 years ago
- [CVIU 2019] ASSD learns to highlight useful regions on the feature maps while suppressing the irrelevant information, thereby providing r…☆40Feb 6, 2022Updated 4 years ago
- 对YOLO格式的数据实现数据增强，减少标注的工作量☆71Feb 27, 2025Updated last year
- Helmet Detection:detect persons with/without helmets using YOLOv3(头盔\安全帽检测：使用YOLOv3检测是否戴头盔\安全帽)☆40Mar 8, 2020Updated 6 years ago
- This script performs K-means Clustering on the Berkeley Deep Drive dataset to find the appropriate anchor boxes for YOLOv3. Originally it…☆32Jul 8, 2021Updated 4 years ago
- 使用OpenCV部署图像描述Image_Captioning，包含C++和Python两个版本的程序☆12Dec 22, 2023Updated 2 years ago
- 《动手学深度学习》：面向中文读者、能运行、可讨论。英文版即伯克利“深度学习导论（STAT 157）”教材。☆10Jul 27, 2019Updated 6 years ago
- CenterNet's inference.(C++)/基于CenterNet的旋转目标检测C++版☆28Dec 28, 2020Updated 5 years ago
- yolov5_ncnn in ununtu16.04☆10Nov 2, 2020Updated 5 years ago
- 使用opencv部署3D人脸重建3DDFA-V3，包含C++和Python两个版本的程序，只依赖opencv库就能运行☆40Aug 19, 2024Updated last year
- 使用ONNXRuntime部署人脸动漫化——AnimeGAN，包含C++和Python两个版本的代码实现☆44Jan 17, 2022Updated 4 years ago
- 双目图像拼接，双目相机立体匹配，得到深度图像等。☆11Apr 27, 2020Updated 5 years ago
- convert cityscape segmentation label to pascal voc bbox label☆12Mar 10, 2019Updated 7 years ago
- 使用onnxruntime部署夜间雾霾图像的可见度增强，包含C++和Python两个版本的程序☆13Feb 17, 2024Updated 2 years ago
- operate the xml files in the VOC dataset☆11Mar 23, 2019Updated 6 years ago
- Yet another ssd, with its runtime stack for libtorch, onnx and specialized accelerators.☆26Mar 21, 2025Updated last year
- yolov5训练转onnx转caffe工程 直接可用☆23Jan 10, 2022Updated 4 years ago
- ☆12Nov 16, 2020Updated 5 years ago
- Simple implementations of attention modules adapted for the biological data domain.☆14May 20, 2025Updated 10 months ago
- yolov7 pytorch☆14Mar 15, 2023Updated 3 years ago
- imgaug--Bounding Boxes augment☆88Apr 10, 2019Updated 6 years ago
- Pytorch Person ReID, including implementation of MGN, PCB, RPP, ResNet, MobileNetV2, and so on.☆29Dec 12, 2025Updated 3 months ago
- Vanilar-CNN face landmark☆23Aug 1, 2018Updated 7 years ago
- Deep Learning fingerprint recognition using PyTorch☆15Apr 17, 2022Updated 3 years ago
- generate randomly defects on positive samples and restore them with GAN.☆41Nov 19, 2020Updated 5 years ago
- 识别工厂中托盘和托盘上的孔☆13Sep 11, 2023Updated 2 years ago
- ☆11May 8, 2021Updated 4 years ago
- The implementation of the NeurIPS2020 paper: The Dilemma of TriHard Loss and an Element-Weighted TriHard Loss for Person Re-Identificatio…☆10Oct 22, 2020Updated 5 years ago
- 使用OpenCV部署CoupledTPS，包含了肖像矫正，不规则边界的图像矩形化，旋转图像矫正，三个模型。依然是包含C++和Python两个版本的程序☆20Jul 4, 2024Updated last year