Upload 3 files

README.md

@@ -0,0 +1,43 @@
+---
+title: Stop Sign Predictor
+emoji: 🦀
+colorFrom: yellow
+colorTo: yellow
+sdk: gradio
+sdk_version: 5.47.2
+app_file: app.py
+pinned: false
+license: mit
+---
+# Stop Sign Classifier
+
+This is a simple Gradio app that wraps an **AutoGluon MultiModalPredictor** trained on images of stop signs.  
+Upload a traffic sign and the model will predict whether it contains a **Stop Sign**.
+
+## Features
+- Upload your own image (PNG/JPG) or use your webcam.
+- Get predictions with **probabilities** (Stop Sign vs No Stop Sign).
+- Preview **example images** for quick testing.
+- Built with [AutoGluon](https://auto.gluon.ai/stable/index.html) + [Gradio](https://gradio.app/).
+
+## How It Works
+- The trained model is downloaded directly from Hugging Face Hub (`scottymcgee/image-classifier`).
+- Images are preprocessed (resized to 256x256) and passed into the model.
+- Probabilities are returned and displayed in a simple UI.
+
+## Example Inputs
+- Clear stop sign picture
+- Street scene without stop sign
+- Mixed images
+
+## Files in this Space
+- `app.py`: Gradio interface.
+- `requirements.txt`: Dependencies.
+- `README.md`: This documentation.
+
+## Notes
+- This app is for **educational/demo** purposes.
+- Model was trained by a classmate as part of Homework 2 (CMU 24679).
+- Deployment exercise for **Driving an Image Network Model with Gradio** assignment.
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,69 @@
+import gradio
+import pandas as pd
+import PIL.Image
+import tempfile, pathlib, requests, io
+
+from huggingface_hub import snapshot_download
+from autogluon.multimodal import MultiModalPredictor
+
+# Hugging Face model repo (no .zip file here, it’s a direct directory)
+MODEL_REPO_ID = "scottymcgee/image-classifier"
+
+# Download full repo snapshot locally
+repo_dir = snapshot_download(repo_id=MODEL_REPO_ID)
+
+# Load predictor directly
+PREDICTOR = MultiModalPredictor.load(repo_dir)
+
+# Explicit class labels
+CLASS_LABELS = {0: "🚫 No Stop Sign", 1: "🛑 Stop Sign"}
+
+def do_predict(pil_img: PIL.Image.Image):
+    if pil_img is None:
+        return {"Error": 1.0}
+    pil_resized = pil_img.convert("RGB").resize((256, 256))
+    
+    # Save to tmp for AutoGluon input
+    tmpdir = pathlib.Path(tempfile.mkdtemp())
+    img_path = tmpdir / "input.png"
+    pil_img.save(img_path)
+
+    df = pd.DataFrame({"image": [str(img_path)]})
+
+    # Predict probabilities
+    proba_df = PREDICTOR.predict_proba(df)
+
+    # Map columns to nice names
+    pretty_dict = {}
+    for idx, col in enumerate(proba_df.columns):
+        label = CLASS_LABELS.get(idx, str(col))
+        pretty_dict[label] = float(proba_df.iloc[0][col])
+    return pil_img, pil_resized, pretty_dict
+
+EXAMPLES = [
+    ["examples/stop1.jpg"],
+    ["examples/no_stop1.jpg"],
+    ["examples/stop2.jpg"],
+]
+
+with gradio.Blocks() as demo:
+    gradio.Markdown("# 🛑 Stop Sign Classifier")
+    gradio.Markdown("Upload a traffic image. The model shows the **original**, the **preprocessed**, and the prediction.")
+
+    with gradio.Row():
+        image_in = gradio.Image(type="pil", label="Upload image", sources=["upload", "webcam"])
+        proc_out = gradio.Image(type="pil", label="Preprocessed (256x256)")
+        proba_pretty = gradio.Label(num_top_classes=2, label="Class probabilities")
+
+    image_in.change(fn=do_predict, inputs=[image_in], outputs=[orig_out, proc_out, proba_pretty])
+
+    gradio.Examples(
+        examples=EXAMPLES,
+        inputs=[image_in],
+        outputs=[proc_out, proba_pretty],
+        fn=do_predict,
+        cache_examples=False,
+    )
+
+if __name__ == "__main__":
+    demo.launch()

requirements.txt

@@ -0,0 +1,5 @@
+autogluon.multimodal
+gradio
+huggingface_hub
+pillow
+pandas