yzhao062/pyod

AutoEncoder does not generate a symmetric model

Open

#138 opened on Nov 3, 2019

View on GitHub
 (3 comments) (0 reactions) (0 assignees)Python (1,308 forks)batch import
bughelp wanted

Repository metrics

Stars
 (7,762 stars)
PR merge metrics
 (Avg merge 4d 17h) (14 merged PRs in 30d)

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!

Contributor guide