ResNet Auto-encoder

[A_Mahmoud (Ahmed Mhamoud)]

Hi,

Is there any best practice about how to implement an auto-encoder based on resnet architecture ? i.e. how to decrease in the dimensionality with keeping skip connections safe from the bottleneck ?

Best

[Max1]

Ahmed, if the purpose of the auto-encoder is feature extraction, here’s what could potentially be interesting:

Anomaly Detection

@coderama’s first post is an excellent one - thanks for de-cloaking! @gohar it’s better to use a “real” loss function instead of an autoencoder if possible, since that way you can be sure that the features that are being used to detect anomalies are the ones you care about. Are there any labels that you could use? You may also be interested in looking at triplet and siamese networks: https://arxiv.org/abs/1412.6622 Are you able to share your dataset? I’m interested in teaching …