Update Backend/app.py

Backend/app.py

@@ -1,6 +1,7 @@
 from fastapi import FastAPI, HTTPException
 from fastapi.middleware.cors import CORSMiddleware
-from fastapi.responses import JSONResponse
+from fastapi.responses import JSONResponse, FileResponse
+from fastapi.staticfiles import StaticFiles
 from pydantic import BaseModel
 import base64
 from io import BytesIO
@@ -10,23 +11,33 @@ import cv2
 import os
 import traceback
 from keras.models import load_model
-from fastapi.responses import FileResponse
-from fastapi.staticfiles import StaticFiles
 
-# Load the trained model
-model_path = os.path.join(os.path.dirname(__file__), 'emotion_model.keras')
-model = load_model(model_path)
+# Initialize FastAPI app
+app = FastAPI()
 
-# Mount the frontend folder to serve static files
+# Mount static files from Frontend
 app.mount("/static", StaticFiles(directory="Frontend"), name="static")
 
-# Emotion and emoji maps
+# Add CORS middleware
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+# Load model and cascade
+model_path = os.path.join(os.path.dirname(__file__), 'emotion_model.keras')
+model = load_model(model_path)
+face_cascade = cv2.CascadeClassifier(cv2.data.haarcascades + 'haarcascade_frontalface_default.xml')
+
+# Emoji and emotion maps
+BASE_DIR = os.path.dirname(os.path.abspath(__file__))
 emotion_dict = {
     0: "Angry", 1: "Disgusted", 2: "Fearful", 3: "Happy",
     4: "Neutral", 5: "Sad", 6: "Surprised"
 }
-
-BASE_DIR = os.path.dirname(os.path.abspath(__file__))
 emoji_map = {
     0: os.path.join(BASE_DIR, "emojis", "angry.png"),
     1: os.path.join(BASE_DIR, "emojis", "disgusted.png"),
@@ -37,27 +48,16 @@ emoji_map = {
     6: os.path.join(BASE_DIR, "emojis", "surprised.png")
 }
 
-# Initialize FastAPI app
-app = FastAPI()
-app.add_middleware(
-    CORSMiddleware,
-    allow_origins=["*"],
-    allow_credentials=True,
-    allow_methods=["*"],
-    allow_headers=["*"],
-)
-
+# Schema
 class ImageData(BaseModel):
     image: str
 
-# Load Haarcascade once
-face_cascade = cv2.CascadeClassifier(cv2.data.haarcascades + 'haarcascade_frontalface_default.xml')
-
+# Serve homepage
 @app.get("/")
 def serve_homepage():
     return FileResponse("Frontend/index.html")
 
-
+# Process image
 @app.post("/process_image")
 async def process_image(data: ImageData):
     try:
@@ -73,7 +73,7 @@ async def process_image(data: ImageData):
             raise HTTPException(status_code=400, detail="No face detected")
 
         for (x, y, w, h) in faces:
-            roi_gray = gray[y:y + h, x:x + w]
+            roi_gray = gray[y:y+h, x:x+w]
             roi = cv2.resize(roi_gray, (48, 48))
             roi = roi.astype("float") / 255.0
             roi = np.expand_dims(roi, axis=-1)