search

wangqiang9 / SketchKnitter

About PyTorch implementation of SketchKnitter: Vectorized Sketch Generation with Diffusion Models, ICLR 2023, Spotlight.
MIT License
54 stars 8 forks source link

Some questions about samples #7

Closed ydyhello closed 1 year ago

ydyhello commented 1 year ago

Thank you very much for the code, I have some questions I would like to ask. The sample.py does not save any samples anywhere.

sample_all = bin_pen(sample_all, args.pen_break)
print(f"sample all {sample_all} is saved!")

This code seems to be printing the whole vector ?

wangqiang9 commented 1 year ago

sorry, the print message is not very accurate, I have modified the comments and code in this section. Thank you for your feedback.

ydyhello commented 1 year ago

sorry, the print message is not very accurate, I have modified the comments and code in this section. Thank you for your feedback.

Thank you so much for your work!

ydyhello commented 1 year ago

sorry, the print message is not very accurate, I have modified the comments and code in this section. Thank you for your feedback.

sample_all = th.cat((sample, pen_state), 2).cpu()
sample_all = bin_pen(sample_all, args.pen_break)

How to save sample_all in .npz format, I didn't find it in your code.

dngu7 commented 1 year ago

Second this. Because of this, there is no way to evaluate or benchmark the paper's results.

LizzyEw commented 1 year ago

Same question here. How can we save "sample_all" to get a result ?