jbrownkramer

I am trying to get embeddings in depth images, but I am also struggling since I have to guess at the normalization process. @Leeinsu1 have you tried using a baseline...

@StanLei52 Oh, that looks great! I looked at your paper and code. It seems to follow the same data normalization pipeline as Omnivore and ImageBind. One missing piece of information...

I will look into LanguageBind. I will say this: I updated the processing on my pipeline to match the circular shift, quantization, and camera intrinsics as the NYU data. The...

Below is the transformation pipeline in LanguageBind. The starting format is depth in mm (NOT DISPARITY). I ran their inference example from the git homepage and max_depth is configured to...

Another comment is that the use of RandomResizedCrop in augmentation during training might largely break the connection between scale and the object being imaged. It might be good to maintain...

Here you go. You should be able to replace RandomResizedCrop in RGBD_Processor_Train with this. It is untested code, FYI. ``` import torch import torchvision.transforms.functional as F from torchvision.transforms import RandomResizedCrop...

In the read me, the parts list for two arms links to some STS3215 Servos that are $15 each, and the parts list for 1 arm is a different link...

Just to bump this again. There are two different US links to the STS3215 Servos in README.md. The first one is $15/each and the second one is < $14/each. I...

Hi, @pkooij that makes sense! In that case I would suggest changing the list in the "Parts For Two Arms" section of the README.md to match the links in the...