Some question about Phase I

[fhan235]

Hello, I want to ask some questions related to Phase I. I use the code provided in this repo and run the following command

python phase1_inference.py --g 1_wy --s 1.2 --d "20231017_wy" --steps_one 501 --steps_two 1001

After running, I export the deformed template as an obj file and visualize it in the blender. It looks like this:

and the generated masks 0_step2_1000.jpg look like this

I noticed that the generated 0_step2_1000.jpg is the same as experiments/20231017_wy/0_step2_1000.jpg in this repository. Therefore, I would like to inquire if this is considered a normal occurrence.

[fhan235]

I also run inference on the jacket case, and this works well. It looks like this:

So, is there something wrong with the 1_wy? Thank you in advance for your response.