app.py

from fastapi import FastAPI, File, UploadFile, HTTPException
from fastapi.responses import HTMLResponse
from pydantic import BaseModel
from typing import List
import cv2
from PIL import Image
import numpy as np
from io import BytesIO
from deepface import DeepFace
import requests

class InputData(BaseModel):
    data: str

app = FastAPI()

def buscar_existe(imagen):
    face_cascade = cv2.CascadeClassifier('haarcascade_frontalface_default.xml')
    #imagen = cv2.imread('carro.jpg')
    gray_frame = cv2.cvtColor(imagen, cv2.COLOR_BGR2GRAY)
    # Convert grayscale frame to RGB format
    rgb_frame = cv2.cvtColor(gray_frame, cv2.COLOR_GRAY2RGB)
    # Detect faces in the frame
    faces = face_cascade.detectMultiScale(gray_frame, scaleFactor=1.1, minNeighbors=5, minSize=(30, 30))
    emocion = "Sin Emocion"
    for (x, y, w, h) in faces:
        face_roi = rgb_frame[y:y + h, x:x + w]
    # Perform emotion analysis on the face ROI
        result = DeepFace.analyze(face_roi, actions=['emotion'], enforce_detection=False)
    # Determine the dominant emotion
        emocion = result[0]['dominant_emotion']
    
    return emocion

# Ruta de predicción
@app.post('/predict/')
async def predict(input: InputData):
    try:
        image_url = input.data

        # Descargar la imagen desde la URL
        response = requests.get(image_url)
        if response.status_code != 200:
            raise HTTPException(status_code=400, detail="No se pudo descargar la imagen")

        # Leer la imagen y convertir a formato OpenCV
        image_bytes = BytesIO(response.content)
        image = Image.open(image_bytes).convert("RGB")
        image_np = np.array(image)
        image_cv = cv2.cvtColor(image_np, cv2.COLOR_RGB2BGR)

        prediction = buscar_existe(image_cv)
        return {"prediction": prediction}
    except Exception as e:
        raise HTTPException(status_code=500, detail=str(e))