KANG IL LEE

Unfortunately, this package has the problem which you suffered. I already had a similar issue before. If you prune a neural network having residual connections, this package excessively prunes the...

Addtion to good answer from @willyfh, I recommend you to read following paper for your comprehension about the mechanism. [Uninformed Students: Student–Teacher Anomaly Detection with Discriminative Latent Embeddings, CVPR 2020](https://openaccess.thecvf.com/content_CVPR_2020/papers/Bergmann_Uninformed_Students_Student-Teacher_Anomaly_Detection_With_Discriminative_Latent_Embeddings_CVPR_2020_paper.pdf)