You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hi, thanks for your great work!
I have tried a lot of experiments to fintune your metric depth estimation model with nuscenes dataset. But I find that the results turns worse ( “corrugations” appear) after about 3K steps like images below. The situation becomes more intense as training steps increases.
And I found that the effect of this phenomenon varies for images with different input resolutions. Can you tell me why this phenomenon occurs?
I have been troubled by this issue for a long time. I would be extremely grateful if I could get your answer.
The text was updated successfully, but these errors were encountered:
@xiaobh1519 Hello, I am also fine-tuning metric depth estimation using a custom dataset. I plan to use the KITTI config. My image size is 2160*3840. Can you tell me what modifications you made?Thanks a lot!
Even though I changed the image size to 2160*3840 in the KITTI config, it does not match the printed values from the config. Is there any problem with this situation?
Hi, thanks for your great work!
![image](https://private-user-images.githubusercontent.com/79265019/329961899-f610af23-5d0a-470e-8dcb-d00713444a67.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.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.FpQtWhO3D2ulU16RdLe0cD7p_r0752mn9lZSNXj_lws)
![image](https://private-user-images.githubusercontent.com/79265019/329961787-5063042d-5045-4005-8a76-7120ada00c40.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.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.A8wmg-lZMDfJ12aFca8wh3JAlf2NSr2gH5ieTH6AimE)
![image](https://private-user-images.githubusercontent.com/79265019/329962002-f8294655-c72f-4420-9648-a172654f7b0e.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.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.NptTIgg4v0d1tCj4kO8-JTVpWCH9elXM96_B7c0XN7c)
I have tried a lot of experiments to fintune your metric depth estimation model with nuscenes dataset. But I find that the results turns worse ( “corrugations” appear) after about 3K steps like images below. The situation becomes more intense as training steps increases.
And I found that the effect of this phenomenon varies for images with different input resolutions. Can you tell me why this phenomenon occurs?
I have been troubled by this issue for a long time. I would be extremely grateful if I could get your answer.
The text was updated successfully, but these errors were encountered: