-
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
Evaluation module (+ code for training/eval FeatureFlow) #5
base: main
Are you sure you want to change the base?
Conversation
…able_layers the ones from the pretrained feature encoder.
…e to visualize the qqplots and the reconstructed images from the base distributions.
return data | ||
|
||
|
||
def latent_radial_qqplot(models: Dict[str, Flow], data: datasets, n_samples, save_to=None): |
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.
This function is similar to the one here: https://github.com/aai-institute/USFlows/blob/main/src/explib/visualization.py. However it has been modified to work with the FeatureFlow (even if the reconstruction process is not working properly).
plt.close() | ||
return np.transpose(np_imgs, (1,2, 0)) | ||
|
||
def plot_digits(models: dict[str, Flow], n_samples=100, im_shape=(28, 28), save_to=None): #sqrtn: int |
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.
This function is similar to the one in: https://github.com/aai-institute/USFlows/blob/main/src/explib/visualization.py. However the original function calls the nsample function that I couldn't find anywhere.
PR for two main features:
Plots saved:
Adressed Issues: