Yash Kant

Working with multidimensional input and output

2

Hi, Thank you for the great library! I want to use multi-dimensional input and output arrays in the setup [without reshaping to 1-D]. For this, I'm using system verilog instead...

Query about Training Time

19

Hi, Thanks for the code, I was trying to run the training over CelebA dataset with 4 RTX 6000 GPUs, and see the below log -- ``` [Experiment: celebAOutputDir] [GPU:...

Hello there, I was wondering if there was any explanation available for scaling frequencies as done on this [line](https://github.com/marcoamonteiro/pi-GAN/blob/master/siren/siren.py#L136) in the siren.py file. Appreciate any help! --- Best, Yash Kant

intution behind known_view_scale

1

hi! thanks for incorporating zero123 in this repo! I was wondering why did you choose to rescale the known view when using it [here](https://github.com/ashawkey/stable-dreamfusion/blob/main/main.py#L68). and how it would potentially affect...

Hi there! I love this project, and have been replacing all my dataset loaders with it! I have some .beton files of my dataset that I need to update with...

Hi! Thanks for releasing the code. I get the following error when running render.py ``` *** stack smashing detected ***: terminated [1] 725162 abort (core dumped) python render.py --config ../data/whiteTiger/configs.yml...

Possible Bug in in micro_child.py

2

Hi, It appears to me that while building the input to the next pooling layer, we are throwing away layers[0] element with this line. https://github.com/melodyguan/enas/blob/d1a90ac915301198f2a30ce136e9040e6c4235ff/src/cifar10/micro_child.py#L277 I think it should be...

What is the warmup stage doing exactly?

9

Hi, thanks for releasing the code! I attempted training on the human video, and saw that nerf_coarse is trained for 5 epochs to warmup using an SMPL mesh loaded from...