Why training autoencoder architecture different from inference?

oke-aditya / image_similarity

PyTorch Blog Post On Image Similarity Search

https://oke-aditya.github.io/image_similarity/

Apache License 2.0

249 stars 59 forks source link

Why training autoencoder architecture different from inference? #11

Open ahan-2000 opened 3 months ago

ahan-2000 commented 3 months ago

Hi, during training using the ipynb file we have a autoencoder architecture which differs from what we have imported as torch_models during the inference part. Why is it so?

oke-aditya commented 3 months ago

Can you check the torch_infer.py file it used the same model in training.