Discriminator synthesis (update on parameters and use of multiple lay…

…ers)
PDillis · Sep 25, 2021 · 7be2ca0 · 7be2ca0
1 parent 0732bca
commit 7be2ca0
Show file tree

Hide file tree

Showing 2 changed files with 225 additions and 132 deletions.
diff --git a/README.md b/README.md
@@ -24,10 +24,10 @@ the projection video as different `.jpg` files, as well as the projected disenta
 * **Synthesize images with your Discriminator**: Run `python discriminator_synthesis.py --help` for generating images with 
 the second network you have trained, the Discriminator. The following is a *starting code*, meant to inspire more usage of
   this network. Currently, there are two options available now:
-  * Deep dream: Inspired by DeepDream, we use our Discriminator instead of VGG. A starting image can be used, or a seed 
+  * *Discriminator Dream*: Inspired by DeepDream, we use our Discriminator instead of VGG. A starting image can be used, or a seed 
     that will generate a random image. Check available options via `python discriminator_synthesis.py dream --help`
-  * Deep ream zoom: Zoom in (or out) and rotate the image, creating an interesting video. The final video can be reversed,
-  giving more options to the user. Check available options via `python discriminator_synthesis.py dream-zoom --help`
+  * *Discriminator Dream zoom*: Zoom in (or out), rotate, pan horizontally or vertically each frame; the result will be saved as a `.mp4` 
+    video, which can be reversed, giving more options to the user. Check available options via `python discriminator_synthesis.py dream-zoom --help`
 
 **Note**: There's an option to `--compress` the generated videos using 
 [`ffmpeg-python`](https://github.com/kkroening/ffmpeg-python). Remember to install it via `pip3 install ffmpeg-python`