Loading DenseNet Checkpoints for CIFAR-10/100

pokaxpoka / deep_Mahalanobis_detector

Code for the paper "A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks".

340 stars 78 forks source link

Open superctj opened 2 years ago

superctj commented 2 years ago

Thank you for open sourcing this great project. The way you saved the Cifar10/100 checkpoints makes it hard to reuse the pre-trained Densenets in another project. Could you please release the checkpoints that can be loaded like https://github.com/pokaxpoka/deep_Mahalanobis_detector/blob/90c2105e78c6f76a2801fc4c1cb1b84f4ff9af63/OOD_Baseline_and_ODIN.py#L49

superctj commented 2 years ago

Never mind. The workaround is to keep the same directory structure and load the entire model

saandeepa93 commented 8 months ago

Can you please let me know the solution for this?