liuhaobjtu的博客

yolo -> voc -> coco格式数据转换#https://github.com/liuhaobjtu/yolo_voc_coco_data_convert_visualizepython3 ./1_YOLO_to_VOC.pypython3 ./2_VOC_to_COCO.pycoco -> voc -> yolo格式数据转换#https://github.com/liuhaobjtu/yolo_voc_coco_data_convert_visuali

mmdetection2.0_tutorials.rarmmdetection2.0_All.rar（里面没有mmcv安装文件）这两个是windows的，是2.0，需要torch1.4.0，cuda10.0ubuntu_mmd2.3.tar.gzmmdetection-all_ubuntu.tar.gz（里面没有mmcv安装文件）这两个是ubuntu的，是2.3，可以使用torch1.5.0，cuda10.1我用的是windows的两个文件准备环境就用mydetection_pyt

训练VOC数据(liuhao_voc_kouzhao)1.准备数据集#1.创建软链接ln -s ../../../datasets/kouzhao/liuhao_voc_kouzhao/ .//detectron2-master/detectron2/data/datasets/builtin.py第206行 SPLITS = [ ("voc_2007_trainval", "VOC2007", "trainval"), ("voc_2007_train

训练COCO数据(liuhao_coco_kouzhao)1.准备数据集#1.创建软链接ln -s ../../../datasets/kouzhao/liuhao_coco_kouzhao/ .//detectron2-master/detectron2/data/datasets/builtin.py "liuhao_coco_kouzhao_train2017": ("liuhao_coco_kouzhao/train/train2017", "liuhao_coco_kouzh

下载https://github.com/facebookresearch/detectron2detectron2-master.zip我下载的detectron2版本是0.2.1detectron2_ubuntu.tar.gz就不用测试了,只是安装detectron2环境重点参考detectron2_train(ubuntu).tar.gzInstallation深度学习目标检测框架 detectron2 安装流程https://zhuanlan.zhihu.com/p/10