Unable to reproduce inference results

[howard5758]

Hi,

First I'd like to sincerely thank the author for sharing this amazing work.
When I tried the provided colab with default setting (indoor), the resulting plot was quite poor.

Similar problem occurred when I cloned the repo and tested on both indoor and outdoor pairs on
indoor_ds.ckpt and outdoor_ds.ckpt

Can anyone advise on this?
Thank you very much!

[JiamingSuen]

Hi @howard5758, a recent bug fix (3955e99 and #41) breaks the compatibility of the released model weights. We will fix this issue very soon and release the new models, thanks for the heads up.

[howard5758]

Understood. Thank you so much for the quick response and the information :)

[angshine]

Hi, this issue has been fixed in the most recent commit.

[howard5758]

Hi, thanks for the prompt actions.

I cloned the repo again and first encountered the following error:

I removed the line "temp_bug_fix=config['coarse']['temp_bug_fix'])" and it still gave similar inference result as yesterday.
I then downloaded the new indoor_ds model you shared earlier, but saw a bunch of missing keys in state_dict and was unable to perform inference.

Really appreciate your help :)

[angshine]

Hi @howard5758, can you share the script(mytest.py) and the config you are using? I think this relates to a misconfiguration of the project (e.g. mixing old & new files🤔).

[howard5758]

Hi @angshine , mytest.py is basically the exact same code from demo_single_pair.ipynb
The only part I modified is commenting out "temp_bug_fix=config['coarse']['temp_bug_fix'])" in src/loftr/loftr.py
Currently the provided colab is still giving me the keyerror:

Can you kindly double check the colab maybe then I can directly follow the steps there.
Thank you very much!

[angshine]

Hi, sorry for the inconvenience, and thank you for your time! I have updated the code and tested the colab and demo_single_pair.ipynb results, and they all work appropriately now. Just make sure you use temp_buf_fix=True with the new ckpt. We will polish the logic in later releases.

[howard5758]

Hi, I can confirm the provided colab work appropriately. Thank you so much for the help!

[GabbySuwichaya]

Hi! Just wonder if the new trained weight is updated ?

[JiamingSuen]

The updated weight is in the google drive folder here

[GabbySuwichaya]

Thanks! Such a good news. Are they all updated ? All the cases?

[xmba15]

@JiamingSuen Can you also update outdoor_ds.ckpt? I still see the problem mentioned above with outdoor_ds.ckpt.