--- title: Lab 1 CIFAR-10 classifier emoji: 🖼️ colorFrom: blue colorTo: green sdk: gradio sdk_version: 5.49.1 python_version: '3.12' app_file: app.py suggested_hardware: zero-a10g --- ResNet-18 trained on CIFAR-10 in Google Colab, with MLflow experiment tracking. The Predict tab exposes the `/predict` Gradio API. Metrics displays actual test results, per-class precision/recall/F1 and the confusion matrix. Deployment files and evaluation assets are supplied by `scripts/publish.py`. The model is loaded at a fixed Hub commit recorded in `deployment.json`.