Lakshya Gupta

icon location Toronto, Canada icon location I am a developer working in applications of AI and machine learning. I love exploring the intersection of my hobbies and ML like I did with badminton and music!

Results 6 issues of Lakshya Gupta

RuntimeError: CUDA error: no kernel image is available for execution on the device when initializing CUDA for gsplat

3 comment

I am working with the following: Ubuntu 22.04.4 LTS Nvidia driver: 555.42.06 Nvidia RTX 3080 Ti I have multiple cuda installations in the /usr/local folder but I have added the...

Couple of Methodology questions

Hey authors. Thank you for this insanely insightful paper. I read through the entirety of your paper and had some questions which I hoped you could explain or address in...

Is there a function to get relationship between pixel and the gaussians it is impacted by?

1 comment

Is there a function that can help me access the relationship between a pixel and gaussian splats such that I can get the set of gaussian ids that impact a...

Why can't I run this on any CUDA device except cuda:0?

2 comment

I tried to modify the codebase a little to allow me to run it on different cuda device but I always end up with an "illegal memory access was encountered"...

Why is there no difference in bpp if `test_quantize` uses compression with or without entropy coding?

Wonder why the bpp remains almost the same regardless of whether I change the compress functions to `compress` or `compress_wo_ec` with appropriate corresponding decompress and analysis functions. Is there a...

Why train for quantization AFTER image representation?

At present, the way the README states this, the quantization training script (train_quantize) is executed after train.py has already generated the gaussian model for a given image. We then run...