Here's something I've found really useful in my DeOldify research: Keep a separate huge master set of images created from various sources (eg open images), then use Jupyter notebooks made specifically to generate training datasets from that master and output them elsewhere. 1/
-
-
Thanks, interesting! Do you leverage video frames or streams as a data source for training / testing? Could be interesting to add a feature to invert the color of an image and then colorize/enhance it. For tintype photos.
-
I haven't really done much with video since August 2019, and I haven't tried that yet. It's on the radar though!
- Show replies
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.