Closed deeprobo-dev closed 2 years ago
The configs are designed to train on GPUs with more memory, like 2080's. Since your GPU has half the memory you should reduce the load by about half. You can do so by changing in the config file, the values of nerf.train.num_random_rays (that's how many rays per image in an iteration) and nerf.train.chunksize (it divides the MLP queries into chunks, you can halve that without reducing the number of pixels to shoot rays through). Play around with these until it fits in your memory.
Do so for nerf.eval.chunksize if necessary
Thanks a lot. Now able to run it.
Hi I am getting "CUDA out of memory. Tried to allocate 20.00 MiB (GPU 0; 5.80 GiB total capacity; 4.51 GiB already allocated; 34.31 MiB free; 4.57 GiB reserved in total by PyTorch). on running train_transformed_rays.py script."
Please find the below details of error:
Note: My system configuration- i7, 1TB SSD, 16GB RAM and gtx2060 graphics. Can you please confirm if system configuration is the problem or anything else and if so then what is the minimum system requirement?