How to set N_rand value to get the same output as shown in the repository?
Closed this issue · 3 comments
Hi @limacv,
This is amazing work.
I am using Nvidia RTX 3060 GPU (Memory=VRAM 12 GB) to train the algorithm.
After 1200 iterations, the code throws this error
I was wondering how to set the N_rand
value to get the output?
Thanks
Adwait
I have one more query, is it possible to use image metrics like Features Similarity Index Matrix (FSIM)
along with SSIM for this code?
Hi, I'm using 1 V100 (32GB) with N_rand = 1024. The memory required is roughly proportional to N_rand. So I guess you can first try N_rand = 1024 * (12 / 32) ~= 350. For other image metrics, just implement your own metrics in the test stage.
Thanks for the response, @limacv.
I was able to successfully (albeit with a smaller N_rand, chunk, and netchunk) replicate the results of your algorithm on my GPU.
This is the command I used.
python3 run_nerf.py --config configs/demo_blurball.txt --N_rand 128 --chunk 384 --netchunk 768
- Results after 20,000 iterations
blurball_full_spiral_020000_rgb.mp4
- Results after 40,000 iterations
blurball_full_spiral_040000_rgb.mp4
- Results after 60,000 iterations (final)
blurball_full_spiral_060000_rgb.mp4
Thanks for your help.