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

Coco dataset #13

Open
1z2213 opened this issue Oct 12, 2023 · 2 comments
Open

Coco dataset #13

1z2213 opened this issue Oct 12, 2023 · 2 comments

Comments

@1z2213
Copy link

1z2213 commented Oct 12, 2023

Hi, thank you very much for your great work!
What should I do if I want to train the coco dataset, after all the Megadepth dataset is too big!
I think first use superpoint to export the coco dataset detections to generate a series of npz files, then execute the command python3 -m dump.dump_megadepth --feature_type spp --base_path path_of_megadepth --save_ path your_save_path, is this correct?
Looking forward to your reply!

@feixue94
Copy link
Owner

feixue94 commented Nov 4, 2023

Hello,

Sorry for the late reply.

For training on coco dataset, a better way is to generate paired images online with perspective projection function in opencv. I have tried the training on coco only, but the performance is not very good.

I will try to provide the training scripts on coco.

@1z2213
Copy link
Author

1z2213 commented Nov 5, 2023

你好

对不起,回复晚了。

对于coco数据集的训练,更好的方法是在opencv中使用透视投影功能在线生成配对图像。我只尝试过coco的训练,但表现不是很好。

我会尝试在 coco 上提供训练脚本。

Hello,

Sorry for the late reply.

For training on coco dataset, a better way is to generate paired images online with perspective projection function in opencv. I have tried the training on coco only, but the performance is not very good.

I will try to provide the training scripts on coco.

Thank you very much for your reply.
Since my own training dataset is similar to coco, I need your training code for training coco. Looking forward to your training scripts!

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

2 participants