Skip to content
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

Add tutorial performing anomaly detection based on likelihoods from generative models #298

Conversation

Warvito
Copy link
Collaborator

@Warvito Warvito commented Mar 11, 2023

Implements #112

Warvito added 4 commits March 1, 2023 22:29
Signed-off-by: Walter Hugo Lopez Pinaya <[email protected]>
…n-based-on-likelihoods-from-generative-models
Signed-off-by: Walter Hugo Lopez Pinaya <[email protected]>
Signed-off-by: Walter Hugo Lopez Pinaya <[email protected]>
@Warvito Warvito changed the title Add tutorial performing anomaly detection based on likelihoods from generative models [WIP] Add tutorial performing anomaly detection based on likelihoods from generative models Mar 11, 2023
Signed-off-by: Walter Hugo Lopez Pinaya <[email protected]>
@Warvito Warvito changed the title [WIP] Add tutorial performing anomaly detection based on likelihoods from generative models Add tutorial performing anomaly detection based on likelihoods from generative models Mar 11, 2023
Signed-off-by: Walter Hugo Lopez Pinaya <[email protected]>
Copy link
Collaborator

@marksgraham marksgraham left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Nice tutorial :) Two minor comments


# %% [markdown]
# ### Transformer Training
# We will train the Transformer for 100 epochs.
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

It's set to 5 in the training loop

# %% [markdown]
# ## Image-wise anomaly detection
#
# To verify the performance of the VQ-VAE + Transformerperforming unsupervised anomaly detection, we will use the images from the test set of the MedNIST dataset. We will consider images from the `HeadCT` class as in-distribution images.
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Missing space in "VQ-VAE + Transformer performing"

Signed-off-by: Walter Hugo Lopez Pinaya <[email protected]>
@Warvito Warvito merged commit 8484a44 into main Mar 13, 2023
@Warvito Warvito deleted the 112-add-tutorial-performing-anomaly-detection-based-on-likelihoods-from-generative-models branch March 18, 2023 19:44
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

Add tutorial performing anomaly detection based on likelihoods from Generative Models
2 participants