ReDet icon indicating copy to clipboard operation
ReDet copied to clipboard

Official code of the paper "ReDet: A Rotation-Equivariant Detector for Aerial Object Detection" (CVPR 2021)

Results 91 ReDet issues
Sort by recently updated
recently updated
newest added

ase\build.ninja... Compiling objects... Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) ninja: error: build.ninja:3: lexing error Traceback (most recent call last): File...

When I train the ReDet model with some RS images, the result during training is as shown below: 2022-08-0302:56:57,351-INFO- Epoch [48][40/61] lr :0.00629, eta :2:45:00, time :2.765, datatime :0.018, memory...

Thanks for your novel work ! I have trained the ReDet on my dataset, but i find it's a little slow when i test. I have convert the ReDet to...

在执行demo_large_image.py文件时总报错,这个ReDet_re50_refpn_1x_dota15_ms-9d1a523c.pth不是权重文件吗

Hai sir, I am trying to run some ablations for my project. I want to know if I can run ReDet by removing the neck (ReFPN) part completely. I tried...

您好,我按照ReDet_mmcls分支中的getting_started.md所说,下载了ILSVRC 2012的train和val数据集,并分别解压到了data/train和data/val路径下。同时我根据Get Started所说,下载了checkpoint文件,放在了re_resnet50_c8_batch256路径下。当我继续执行如下的指令时 `python tools/test.py configs/imagenet/resnet50_batch256.py checkpoints/re_resnet50_c8_batch256/epoch_100.pth` 发生如下报错: `No such file or directory: 'data/imagenet/meta/val.txt'` 请问我该如何获得此文件呢?我在ImageNet上找到了ILSVRC 2012数据集对应的annotation标注文件,但是文件格式是xml。 请问此txt文件是根据xml转换得到,还是需要手动创建?麻烦您能帮忙解惑,十分感谢!

![image](https://user-images.githubusercontent.com/54108453/133050621-6a273db0-dc36-4241-a420-95293d2e010f.png) 请问一下,您在DOTA2COCO.py这个文件中,计算了x_min, y_min,x_max,y_max.我没看到关于angle的信息啊?那OBB-detection如何学习角度呢?还有就是,在数据prepare的时候,难道不用删除没有object的图片和txt吗? 谢谢

Hello, thanks for the code. I'm trying to archive the 80.1% mAP on the Dota 1 dataset. I noticed when comparing the logs - that I got a different maximum...

Hai sir, I want to train ReDet on VisDrone dataset. For VisDrone dataset, the ground truth object segmentation details are not provided in annotation files. The annotation format for VisDrone...