Roger Jackey
Roger Jackey
When I use the tiny-cuda-nn to train a network, I need to take the derivative of one of the intermediate outputs of the network. When I backward the loss function...
When I try to train a network, I need to take the derivative of one of the intermediate outputs of the network, the code is as follows ```python class Network(torch.nn.Module):...
When I was debugging the code, I found a problem: by modifying ```target_sample_batch_size```, ```init_batch_size```, ```render_step_size``` does not change the GPU memory footprint, only by modifying the network size, such as...
**Is your feature request related to a problem? Please describe.** When I attempted to integrate works like [Sat-NeRF](https://github.com/centreborelli/satnerf) into NeRFStudio, I discovered the difficulty of adapting the satellite image processing...
The UTM coordinate system is more suitable for the grid-based distribution of point coordinates compared to ECEF. I am exploring a grid-density based NeRF method and would like to use...