yzhao062/pyod

AutoEncoder does not generate a symmetric model

Open

#138 ouverte le 3 nov. 2019

Voir sur GitHub
 (3 commentaires) (0 réactions) (0 assignés)Python (1 308 forks)batch import
bughelp wanted

Métriques du dépôt

Stars
 (7 762 stars)
Métriques de merge PR
 (Merge moyen 4j 17h) (14 PRs mergées en 30 j)

Description

Hi,

I plotted the model when printing the model summary: https://github.com/yzhao062/pyod/blob/da68f50ee79bd74777d2d406cac6dcfad412e599/pyod/models/auto_encoder.py#L187

And it seems that you added an extra layer at the beginning with the same dimension as the input. I don't know why this is required because it would generate an asymmetric model. Here is the model I printed out:

model

The final dimension would be like 645-645-100-100-500-9-500-100-100-645.

I think the problem might be caused by this line: https://github.com/yzhao062/pyod/blob/da68f50ee79bd74777d2d406cac6dcfad412e599/pyod/models/auto_encoder.py#L224

The performance is similar after I commented out the above line.

Please correct me if I miss something! Thanks!

Guide contributeur