Update README.md

README.md

@@ -9,5 +9,21 @@ app_file: app.py
 pinned: false
 license: mit
 ---
+# 🐶🐱 Image Classifier – Multi-Model
+
+Try 3 backbones (ViT / ResNet / EfficientNet) on any image. We show **top-5 predictions** and **latency** to highlight accuracy vs speed trade-offs.
+
+## Quickstart
+- Upload an image
+- Pick a model in the dropdown
+- Click **Predict**
+
+## Why this matters (hackathon pitch)
+Different backbones behave differently. This demo makes those trade-offs visible to judges/users in one place.
+
+## Roadmap
+- Eval notebook → Confusion Matrix + Accuracy + ROC (binary subsets)
+- Auto-publish plots to this README
+- n8n workflow to re-run eval on new models and notify with results
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference