You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hi! I think I may have found a bug, at least it is for my purposes.
During the deformation, the dataset is split up into 3: A tenth is validation set and the remainder is then split into two equally sized sets, the two half sets - correct?
However, in explore_latent_space line 102-111, it seems that the indices for the second half set are found by subtracting the indices of the first half set from the full dataset. That means that the second half set now includes the validation set:
When I print out the size of the latent space, I do also get a larger array for half set 2 than half set 1. For the beta amylase dataset for example, I have 2127 rows/images for half set 1, and 2599 for half set 2.
The text was updated successfully, but these errors were encountered:
Hi! I think I may have found a bug, at least it is for my purposes.
During the deformation, the dataset is split up into 3: A tenth is validation set and the remainder is then split into two equally sized sets, the two half sets - correct?
However, in explore_latent_space line 102-111, it seems that the indices for the second half set are found by subtracting the indices of the first half set from the full dataset. That means that the second half set now includes the validation set:
DynaMight/dynamight/evaluation/explore_latent_space.py
Line 109 in 59e033f
When I print out the size of the latent space, I do also get a larger array for half set 2 than half set 1. For the beta amylase dataset for example, I have 2127 rows/images for half set 1, and 2599 for half set 2.
The text was updated successfully, but these errors were encountered: