resurgo97

Am I training properly?

21

I am not familiar with ASR tasks, so I'd be so glad if anyone answer my question: I am training ContextNet which is basically rnn-t type model as in the...

I installed jax with the below command, `pip install --upgrade "jax[cpu]" install -q neural_tangents==0.2.2 livelossplot` but I come across the error `jax.api does not exist` while importing `neural tangent` package...

19,349,663 is not a prime.

1

19,349,663 is divisible by 41. Regardless, I really appreciate your work. Thanks!

Hi, I want to run this code on the Blender (or NeRF-Synthetic) dataset. However, I couldn’t find any configuration file specifically for this dataset. I can try to adjust the...

How does dust3r use known camera poses in global alignment?

1

Hello, I'm testing dust3r with the Lego dataset using known camera poses to determine if this improves the (world-coordinate) pointmap generation during the global alignment optimization process. I've successfully loaded...

``` Warning, cannot find cuda-compiled version of RoPE2D, using a slow pytorch version instead ``` Has anyone measured the impact of CUDA-compiled RoPE2D on dust3r's inference time? Thanks

How do you guys use splatviz?

1

I assume most researchers train the 3DGS model on remote servers with high-end GPUs, but running it with X11 forwarding wouldn't give real-time rendering. I can think of two possible...

Incorporating Known Camera Poses in Global Alignment Optimization

5

I'm seeking a way to run global alignment optimization with known camera poses. After examining the code, I've identified some challenges: 1. `cam2w` matrices are constructed in `make_K_cam_depth`, but they...