pkuanjie / stylenas Goto Github PK

Hi,
I am trying to run photo_transfer.py as documented in README. But I have the following errors:

1. load_lua is not available in pytorch 1.3. So import load_lua fails.

The most frequent recommendation is to use torchfile, which I tried.
https://github.com/bshillingford/python-torchfile

2. But this fails in VGG_with_decoder.py on line 12.

Any help is appreciated.

Thanks!

Congrats on the amazing advancements on Style Transfer tech.

1. Can this run on a mobile device? Specifically Android

2. What would be the kind of performance we would see vis-a-vis https://www.tensorflow.org/lite/models/style_transfer/overview?

3. I tried the linked Google library, but the final output has too many distortions. If I give a face as content image, the style transfer output comes with too many wrinkles. How would StyleNAS compare?

4. Is the license MIT?

Thanks

Is this code under a license of some kind? Is it open for modification and reuse?

Hi,

I am running photo_transfer.py with the given content and style images. All the settings are in default. However, the results are not satisfying as shown. Here is what I get for the first pair:

And for the second:

Are the provided model weights up-to-date? Or is the default d_control variable in photo_transfer.py in the optimal configuration? Are the results produced with the given settings?
Many thanks.

Hello,

Your pretained model uploaded on https://drive.google.com/drive/folders/15PP0K55jH2tBeWfLAYG7r0LuW0RZvmKd are not working.

Could you reupload them ? I have this error : Error opening archive: Unrecognized archive format

Thank you.