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

请问单张图像推理应如何修改 #8

Closed
garriton opened this issue May 1, 2022 · 6 comments
Closed

请问单张图像推理应如何修改 #8

garriton opened this issue May 1, 2022 · 6 comments
Labels
good first issue Good for newcomers

Comments

@garriton
Copy link

garriton commented May 1, 2022

请问单张图像推理应修改哪些地方?

感谢开源以及优秀的论文

@dyfcalid
Copy link
Collaborator

dyfcalid commented May 1, 2022

对于推理,需要提供输入图像、相机内参和相机外参。
目前只提供了OpenLane的训练和测试代码,对于单张图像的推理,您可以按照OpenLane的数据集格式和路径格式准备对应的图片和标注(相机内参和相机外参从标注中读取)作为validation。将persformer_openlane.py中args.evaluation置为True,修改图片和标注的路径args.dataset_dir和args.data_dir。

@garriton
Copy link
Author

garriton commented May 1, 2022

感谢!已完成!很棒的工作,大佬加油

@laikakano
Copy link

请问可以将单张推理的命令发一下吗

@garriton
Copy link
Author

改掉config/persformer_openlane.py 里的

    # 1000 sequence
    args.dataset_name = 'openlane'
    args.dataset_dir = '/mnt/disk01/openlane/images/'
    args.data_dir = '/mnt/disk01/openlane/lane3d_1000/'

按照OpenLane的数据集格式和路径格式,图片放在validation下面的文件夹里

-images
----training
--------segment-183829460855609442_430_000_450_000_with_camera_labels
----validation
--------segment-183829460855609442_430_000_450_000_with_camera_labels
------------要推理的图片
-lane3d_300
----training
--------segment-183829460855609442_430_000_450_000_with_camera_labels
----validation
--------segment-183829460855609442_430_000_450_000_with_camera_labels
------------找个OpenLane里面的真值json放进去,重命名成要推理的图片(这里主要是我只看可视化结果,对数值不在意,如果你有真的真值就放真的吧

然后运行

python main_persformer.py --mod=PersFormer --batch_size=1

请问可以将单张推理的命令发一下吗

@laikakano
Copy link

十分感谢,美好的一天~

@ZC0102-shu
Copy link

十分感谢,美好的一天~

请问你在其他数据上预测的效果如何?

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

No branches or pull requests

5 participants