Panos

Hi, Yes, we extract 1 feature (the bottleneck of the AE) per point-cloud. We don't apply any test-augmentations. I will try to release the notebook/code soon. Thanks a lot for...

On Sep 9, 2019, at 5:59 PM, Matteo Moro wrote: Hi optas, Hi, Yes, we extract 1 feature (the bottleneck of the AE) per point-cloud. Hi optas! When you talk...

I can't help with Windows:( sorry. I will leave it open in case someone else can. Best,

Hi, you are right the sample_speaker.py can be used to create captions for **whatever** images you want to. However, to do this you need to provide a .csv file that...

Hello, sorry for the long-due reply. Did you figure it out? Judging by the numbers of your tensors, I think you are pointing via the sample_speaker.py (via the passed config.json.txt)...

Hi, First, let's clarify that object classification, given a point cloud, is a different task from classifying a referred target object given some text. The asymmetry noted above highlights that...

Dear Mr. Ramachandran, I have never used Octave, so unfortunately, the answer is no. If you decide to go on and implement any/some parts in Octave perhaps you would like...

Dear recipient, I have stopped actively developing this library and from the attached image is hard to understand the problem. Can you be more specific? Also, I would recommend to...

Hi @scopophobic - A good dataset to start is the very manageable (pixel size, tokens, etc.) [VQA-Small](https://github.com/oumi-ai/oumi/blob/main/src/oumi/datasets/vision_language/vqav2_small.py). If you "saturate" this fast, then you can also explore the [Caulron](https://github.com/oumi-ai/oumi/blob/main/src/oumi/datasets/vision_language/the_cauldron.py) collection,...