User Tools

Site Tools


cs501r_f2016:lab13

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision
Previous revision
cs501r_f2016:lab13 [2017/11/11 10:05]
wingated
cs501r_f2016:lab13 [2017/11/11 10:11]
wingated
Line 39: Line 39:
  
   - lab10_scaffold.py - Lab 10 scaffolding code   - lab10_scaffold.py - Lab 10 scaffolding code
-  - vgg16.py.txt - The VGG16 model+  - vgg16.py - The VGG16 model
   - content.png - An example content image   - content.png - An example content image
-  - style.png|An example style image+  - style.png ​An example style image
  
 You will also need the VGG16 pre-trained weights: You will also need the VGG16 pre-trained weights:
Line 144: Line 144:
 I found that it was important to clip pixel values to be in [0,​255]. ​ To do that, every 100 iterations I extracted the image, clipped it, and then assigned it back in. I found that it was important to clip pixel values to be in [0,​255]. ​ To do that, every 100 iterations I extracted the image, clipped it, and then assigned it back in.
  
-...although now that I think about it, perhaps I should have been operating on whitened images from the beginning! ​ You should probably try that.+**...although now that I think about it, perhaps I should have been operating on whitened images from the beginning! ​ You should probably try that.**
  
  
cs501r_f2016/lab13.txt ยท Last modified: 2017/11/11 10:11 by wingated