Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

submit_result_multimmodel.py #13

Open
daiguangzhao opened this issue Jun 8, 2020 · 7 comments
Open

submit_result_multimmodel.py #13

daiguangzhao opened this issue Jun 8, 2020 · 7 comments

Comments

@daiguangzhao
Copy link

您好,在46-47行
parser.add_argument('--test_dir', default='../data/test_data', type=str, help='./test_data')
parser.add_argument('--crop_dir', default='../data/cropped_aicity', type=str, help='./test_data')
并没有发现相关代码

@layumi
Copy link
Owner

layumi commented Jun 9, 2020

crop_dir 我用的是MaskRCNN 抠出来的car 类别的图。 对应文章中的image alignment的后处理
https://github.com/facebookresearch/detectron2

@HanwenCao
Copy link

HanwenCao commented Jun 28, 2020

crop_dir 我用的是MaskRCNN 抠出来的car 类别的图。 对应文章中的image alignment的后处理
https://github.com/facebookresearch/detectron2

郑博士您好 @layumi ,请问您的意思是crop操作不包含在这个respo里,而是需要自己额外手动扣吗?谢谢~
另外test_dir是怎么来的呢?

@layumi
Copy link
Owner

layumi commented Jun 28, 2020

@HanwenCao
是用detectron的模型来crop的。

@HanwenCao
Copy link

@HanwenCao
是用detectron的模型来crop的。

谢谢郑博士 @layumi ,请问test_dir,就是./data/test_data,是怎么prepare出来的?

@mozheng
Copy link

mozheng commented Jan 12, 2021

crop_dir 我用的是MaskRCNN 抠出来的car 类别的图。 对应文章中的image alignment的后处理
https://github.com/facebookresearch/detectron2

请问您crop是使用maskrcnn的检测结果还是分割结果

@layumi
Copy link
Owner

layumi commented Jan 12, 2021

@mozheng @HanwenCao 应该都行,当时是maskrcnn的检测结果。

@vokhidovhusan
Copy link

vokhidovhusan commented Mar 19, 2021

@layumi 您好
When I crop images, should I crops images from val set or directly from AIC20_ReID's image_query and image_test sets.

I am really confused about what dataset should I use for submit. Should I use AIC20_ReID's image_query and image_test sets or val dataset which created from train dataset.

Since AIC20_ReID's image_query and image_test dataset doesn't provide camera ID How can I make query_cam_preds_baidu.txt and gallery_cam_preds_baidu.txt files.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

5 participants