Guangkai Xu

@lw0210 Hi, thanks for reporting this bug! This bug happens due to the absence of high-quality and mid-quality datasets, and we have fixed this situation in our latest code.

@lw0210 This error occurs due to the incorrect rgb_path in train_annotation.json. Please prepare the training data following the step 'Training-2' and put it under ```Train/datasets```. If you would like to...

@lw0210 The validation datasets should contain depth images rather than disparity images, which has been filtered automatically in our latest released code. Also, please update the annotation files of taskonomy...

@lw0210 Hi, Sorry for the late response due to some busy work. If you want to load the self-trained checkpoint, please follow this to modify your code: https://github.com/aim-uofa/AdelaiDepth/issues/44#issuecomment-1188822214. It will...

The code for 'shift_model' and 'focal_model' have not been released yet. We will consider reorganizing and releasing it but it will be time-spending. Thanks for your understanding!

Hi, it seems there exists some invalid file paths in the annotation files. I will double-check them and release as soon as possible. Thanks!

@lw0210 This bug happened because the validation datasets should contain depth images rather than disparity images, which have been fixed just now. Please download the latest annotation files of taskonomy...

The change of batchsize will not cause the loss nan. I ever faced the "loss nan" problem due to the crop operation. If the depth image becomes invalid(0) for the...

> Sorry, Maybe I didn't express it correctly before. I hope I can make it clear this time, thank you for your patience again! > > For SLAM, there are...

Hi, the surface normal checkpoint will be released soon (around 1-2 days).