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

Question about draw_sketch.py #9

Closed LizzyEw closed 1 year ago

LizzyEw commented 1 year ago

Hi there! Firstly, thank you for your advice about sample_all in sample.py! However, I noticed that in your dataset such as moon.npz, the size of data.train (as shown in the 80th line in draw_sketch.py) is 70000×3. While the size I get in sample_all.npz (from the 73rd line in sample.py) is 16×96×4. So could you please explain how you save sample_all into the true npz file? I've tried np.savez(args.save_path + "sample0.npz", train=sample_all) but it didn't work when draw_sketch. Thank you for your help agian!

wangqiang9 commented 1 year ago

Hi，The right saved sizes Batch_size, image_size, 3. So I think may be there are error of you saving code. I have updated the code for saving npz files in the latest code: https://github.com/XDUWQ/SketchKnitter/blob/8a44cf138acba2c406d71bd0350b94ed755ad26c/sample.py#L74