背景慢慢补充旋转框相关的资料，包括但不限于：论文、代码、数据集、竞赛等;欢迎继续补充1.数据集DOTA2.论文及代码(2020年之后)ReDet: A Rotation-equivariant Detector for Aerial Object Detection: CodeRethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss: CodeOriented R-CNN for Object Detection: CodeYOLOV5-Code Archives Tip
竟然有更新
不能抛弃它！
pytorch-image-classification-master 在这个里面 dataloader 里面 为什么多了二次图像
elif mode != "test":
#for train and val
all_data_path,labels = [],[]
image_folders = list(map(lambda x:root+x,os.listdir(root)))
jpg_image_1 = list(map(lambda x:glob(x+"/*.jpg"),image_folders))
jpg_image_2 = list(map(lambda x:glob(x+"/*.JPG"),image_folders))
all_images = list(chain.from_iterable(jpg_image_1 + jpg_image_2))