Haoyuan Wang

Tensor device problems in code

2

In some situation, training code raises a device error: ``` cuda error: an illegal memory access was encountered ``` After debug I found that the main reason is `Tensor` used...

In other GAN papers, we usually train `D` for `k` steps and train `G` for only one step in each GAN training iteration In this case, the `z` used for...

As your paper writes: But your code in `model.py` is: ``` def forward(self, input_y, input_u, k): if k == 0: t_hat = self.max_operation(input_y) else: t_hat = self.max_operation(input_u) - 0.5 *...

## Description of Changes This PR enhances the `AttrDict` class in the codebase to support generic types for type hinting. This change is necessary to ensure compatibility with Python 3.8....

Code: https://github.com/onpix/LLNeRF Paper: https://arxiv.org/abs/2307.10664 Project webpage: https://whyy.site/paper/llnerf

The value range of guidemap is incorrect.

4

I check the PyTorch doc and found that in function `grid_sample`: > In the case of 5D inputs, grid[n, d, h, w] specifies the x, y, z pixel locations for...

The results look a bit blurry.

7

Thanks for your contribution and the fantastic work! I tried running your code with the default settings according to your instructions on README. However, I failed to get an output...

args is not defined in train_across_scene.py

3

as titled, `train_across_scene.py:L212` is: ```python if args.render_train: ... ``` But `args` is not defined.