|
Download README.md from trshstar/VisionCorruptor: direct link, hf CLI and curl.
- Browser
- Download file 909 Bytes
-
https://huggingface.co/trshstar/VisionCorruptor/resolve/main/README.md
- Command line
-
hf download hf://trshstar/VisionCorruptor/README.md
-
curl -L -o README.md https://huggingface.co/trshstar/VisionCorruptor/resolve/main/README.md
909 Bytes
metadata
license: mit
language:
- en
base_model:
- timm/resnet18.a1_in1k
VisionCorruptor
VisionCorruptor is an end-to-end image corruption classification pipeline built using PyTorch. It classifies 64×64 images from the Tiny ImageNet-C dataset into 15 corruption types (e.g., gaussian_noise, motion_blur, jpeg_compression) using a CNN architecture.
Includes:
Custom PyTorch Dataset for Tiny ImageNet-C (non-standard nested structure)
ResNet-18 training with early stopping, validation tracking, and test evaluation
Visualization: loss/accuracy plots, confusion matrix, sample images
📊 Results Summary
Model: ResNet-18
Validation Accuracy: 97.37%
Test Accuracy: 97.28%
Parameters: ~11M
Notes: Baseline CNN
Best model checkpoint: best_model.pth
Trained on 15 corruption types from Tiny ImageNet-C
mage size: 64×64 | Batch size: 64 | Optimizer: Adam | Early stopping: 3 epochs