-
Notifications
You must be signed in to change notification settings - Fork 0
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Visualize using GAN #16
Conversation
…unction-interpretability into add_generator
…unction-interpretability into add_generator
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Nice! Glad things are converging.
LGTM
if isinstance(img, tuple): | ||
img_obs = img[0] | ||
img_next_obs = img[1] | ||
# TODO(df): check if I have to dump between these |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
FYI: You can record as much as you want and then dump at the end (as long as you don't dump the same key multiple times, of course.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I'll just go ahead and merge, as we discussed, since I didn't find any problems. I'll just remove this todo if I successfully run interpret with wandb myself.
Modify interpret.py to support visualizing input in the space of a trained generator's outputs.
Tested by running interpret.py to see if it ran without error (plus pre-commit hooks).