Category-held-out natural vs. artificial object recognition with ResNet18, robustness tests, representation analysis, and Grad-CAM.
-
Updated
Sep 11, 2026 - Jupyter Notebook
Category-held-out natural vs. artificial object recognition with ResNet18, robustness tests, representation analysis, and Grad-CAM.
From-scratch PyTorch Inception-ResNet-v2 image classification with a Caltech-256 training pipeline, TensorBoard logging, checkpointing, and torch.export support.
To associate your repository with the caltech-256 topic, visit your repo's landing page and select "manage topics."