-
in the dotadevkit, don't find ResultMerge_multi_process
-
**!python main.py --data_dir='/content/drive/My Drive/Bba' --num_epoch=80 --batch_size=16 --dataset=dota --phase=train**
File "main.py", line 6, in
from datasets.dataset_hrsc import HRSC
Fil…
-
https://github.com/yijingru/BBAVectors-Oriented-Object-Detection/blob/e070d39bec96811378eb00a33d0e3969ed7be352/datasets/dataset_dota.py#L47-L56
I'm really thank you for your sharing!
I have one q…
-
When I train the model on the DOTA dataset, the value of "hm loss" is NAN after 40 epochs. Do you know what is wrong?
但是results目录里面是空的，还有怎么将…
-
Hi Ming71,
This projects is a Creative idea, can you put this project in Ubuntu and Win running pipline, thank you very much. Looking forward to your reply.
-
Hi @ming71
I'm also working with rotate object detection, I'd like to introduce you to an efficient way to get coordinates of a rotated box, please refer to [get_corners](https://github.com/maudzung…
-
前辈您好，我在复现您在dota数据集上的结果时，遇到了一些问题，图片切片生成json文件没有按照您给的流程来，自己是dota_devkit切的，然后dota2coco转的json文件，环境配置好了，预训练权重也加载进来了，处理注释的程序dota.py出了点问题，您看应该怎么修改，谢谢
loading annotations into memory...
Done (t=0.85s)
crea…
-
RT
-
Hey,Mingtao.When I run ‘prepare.py’, I am prompted that the module‘DOTA_devkit’ cannot be found.I've seen it in the folder 'maskrcnn_benchmark'. Do I need to copy it out?if i use the pascalvoc
datase…