Add example images

Dockerfile

@@ -25,6 +25,11 @@ COPY . /app
 # Hugging Face sets $PORT; Gunicorn will bind to it.
 ENV PORT=7860
 ENV MODEL_PATH=models/alexnext_vsf_bext.pth
+ENV CONFUSion_PATH=images/TP.jpg
+ENV TP_PATH=images/TP.jpg
+ENV TN_PATH=images/TN.jpg
+ENV FN_PATH=images/FN.jpg
+ENV FP_PATH=images/FP.jpg
 ENV FLASK_DEBUG=0
 
 # Single worker (GPU inference), thread worker for simplicity

app.py

@@ -1,11 +1,12 @@
 import os
-from typing import Any
-from flask import Flask, jsonify, request, send_from_directory
+from typing import Any, Dict
+from flask import Flask, jsonify, request, send_from_directory, abort
 from PIL import Image
 import torch
 import torch.nn.functional as F
 from dotenv import load_dotenv
 from model_loader import load_alexnet_model, preprocess_image
+from flask_cors import CORS
 
 load_dotenv(override=True)
 
@@ -14,11 +15,25 @@ PORT = int(os.getenv("PORT", os.getenv("FLASK_PORT", "7860")))
 HOST = "0.0.0.0"
 MODEL_PATH = os.getenv("MODEL_PATH", "models/alexnext_vsf_bext.pth")
 
+# Preset image paths via ENV
+TP_PATH = os.getenv("TP_PATH", "images/TP.jpg")
+TN_PATH = os.getenv("TN_PATH", "images/TN.jpg")
+FN_PATH = os.getenv("FN_PATH", "images/FN.jpg")
+FP_PATH = os.getenv("FP_PATH", "images/FP.jpg")
+
+PRESET_MAP: Dict[str, str] = {
+    "TP": TP_PATH,
+    "TN": TN_PATH,
+    "FN": FN_PATH,
+    "FP": FP_PATH,
+}
+
 # Single worker is safest for GPU inference
 torch.set_num_threads(1)
 
 # Create app and static hosting
 app = Flask(__name__, static_folder="static", static_url_path="")
+CORS(app)
 
 # Device selection
 DEVICE = torch.device("cuda" if torch.cuda.is_available() else "cpu")
@@ -29,48 +44,84 @@ model.to(DEVICE).eval()
 
 @app.get("/")
 def root() -> Any:
-    # serve your frontend
     return send_from_directory(app.static_folder, "index.html")
 
 @app.get("/health")
 def health() -> Any:
     return jsonify({"status": "ok", "device": str(DEVICE)})
 
-def load_image(file_stream):
-    return Image.open(file_stream).convert("RGB")
-
+def load_image(file_stream_or_path):
+    if isinstance(file_stream_or_path, str):
+        return Image.open(file_stream_or_path).convert("RGB")
+    return Image.open(file_stream_or_path).convert("RGB")
+
+def run_inference(img: Image.Image) -> Dict[str, Any]:
+    input_tensor = preprocess_image(img).to(DEVICE)
+    with torch.no_grad():
+        output = model(input_tensor)
+        probabilities = F.softmax(output[0], dim=0).detach().cpu()
+    pred_prob, pred_idx = torch.max(probabilities, dim=0)
+    predicted_class = classes[int(pred_idx)]
+    return {
+        "class": predicted_class,
+        "confidence": float(pred_prob),
+        "probabilities": {cls: float(prob) for cls, prob in zip(classes, probabilities.tolist())},
+    }
+
+# --- Existing upload classification ---
 @app.post("/predict_AlexNet")
 def predict_alexnet() -> Any:
     if "image" not in request.files:
         return jsonify({"error": "Missing file field 'image'."}), 400
-
     file = request.files["image"]
     if not file:
         return jsonify({"error": "Empty file."}), 400
-
     try:
         img = load_image(file.stream)
-        input_tensor = preprocess_image(img).to(DEVICE)
-
-        with torch.no_grad():
-            output = model(input_tensor)
-            probabilities = F.softmax(output[0], dim=0).detach().cpu()
-
-        pred_prob, pred_idx = torch.max(probabilities, dim=0)
-        predicted_class = classes[int(pred_idx)]
-
-        result = {
-            "class": predicted_class,
-            "confidence": float(pred_prob),
-            "probabilities": {
-                cls: float(prob) for cls, prob in zip(classes, probabilities.tolist())
-            },
-        }
+        result = run_inference(img)
         return jsonify(result)
-
     except Exception as e:
         return jsonify({"error": f"Failed to process image: {e}"}), 400
 
+# --- NEW: classify a preset image ---
+@app.post("/predict_preset")
+def predict_preset() -> Any:
+    try:
+        payload = request.get_json(force=True, silent=False)
+    except Exception:
+        payload = None
+    if not payload or "preset" not in payload:
+        return jsonify({"error": "Missing JSON field 'preset' (TP|TN|FN|FP)."}), 400
+
+    key = str(payload["preset"]).upper()
+    if key not in PRESET_MAP:
+        return jsonify({"error": f"Invalid preset '{key}'. Use one of: TP, TN, FN, FP."}), 400
+
+    path = PRESET_MAP[key]
+    if not os.path.exists(path):
+        return jsonify({"error": f"Preset image not found on server: {path}"}), 404
+
+    try:
+        img = load_image(path)
+        result = run_inference(img)
+        result.update({"preset": key, "path": path})
+        return jsonify(result)
+    except Exception as e:
+        return jsonify({"error": f"Failed to process preset image: {e}"}), 400
+
+# --- NEW: serve preset thumbnails safely ---
+@app.get("/preset_image/<label>")
+def preset_image(label: str):
+    key = str(label).upper()
+    if key not in PRESET_MAP:
+        abort(404)
+    path = PRESET_MAP[key]
+    if not os.path.exists(path):
+        abort(404)
+    directory, filename = os.path.split(os.path.abspath(path))
+    # Let Flask serve the actual file bytes
+    return send_from_directory(directory, filename)
+
 if __name__ == "__main__":
     debug = bool(int(os.getenv("FLASK_DEBUG", "0")))
     app.run(host=HOST, port=PORT, debug=debug)

confusion_matrix_examples.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75665f0fda9ce346e3d4ef1a4ed3d774b4a2581394ae784829d27be1df1cb7b6
+size 42369

confusion_matrix_examples/collection_summary.txt

@@ -0,0 +1,19 @@
+Confusion Matrix Example Collection Summary
+======================================================================
+Model: /work/cssema416/202610/22/Gurinder/alexnet_vsf_best.pth
+
+Datasets Searched:
+  Stable Diffusion:
+    - /work/cssema416/202610/22/test
+    - /work/cssema416/202610/22/train
+  Midjourney:
+    - /work/cssema416/202610/22/Midjourney_Exp2/test
+    - /work/cssema416/202610/22/Midjourney_Exp2/train
+  DALLE:
+    - /work/cssema416/202610/22/dalle
+
+Results:
+True Positives (TP):  10/10
+True Negatives (TN):  10/10
+False Positives (FP): 10/10
+False Negatives (FN): 10/10

requirements.txt

@@ -2,3 +2,4 @@ flask>=3.0.0
 pillow>=10.0.0
 gunicorn>=21.2.0
 python-dotenv>=1.0.0
+Flask-Cors>=4.0.0