athnzc

This issue is almost 2 years old, however I'm citing a solution in case anyone else needs it: [Running Tensorflow 1.x on Google Colab](https://github.com/googlecolab/colabtools/issues/3266#issuecomment-1348660900).

@theshadow18 Did you manage to solve it? If yes, please provide the solution if possible and close the issue.

@TontonTremblay thank you for the prompt response! Were you perhaps able to find the correct 3d models?

@TontonTremblay Thank you! Unfortunately even using the 3D model with the correct texture did not improve the results. I have not changed anything else compared to my initial comment. Would...

@TontonTremblay to be honest I am a little confused....I was under the impression that the weights you provide ([these ones](https://drive.google.com/file/d/1ergPUxKDRoeIOvqWOpmWzoR-jmNk0ou1/view?usp=drive_link)) are produced from training on the meat can shiny dataset....

@TontonTremblay I see! so, which reference frame should I use given the annotations of the shiny meat can dataset? Note that I'm evaluating the inference results using `scripts/metrics/add_compute.py`.

Hello, your specs are not sufficient unfortunately. Check this thread here for the requirements: [https://github.com/NVlabs/BundleSDF/issues/18](https://github.com/NVlabs/BundleSDF/issues/18)

You are using the RTX 2070 super to run the code? 8 GB VRAM? I'm also trying to figure out how to run the code, on an RTX 3070, and...

@zahid990170 Did you run the `build.sh` script inside the container?

Hello, have you perhaps checked your data for any negative values, or otherwise values that don't make sense for your dataset? Regarding negative values specifically, there is a chance you...