app.py

import streamlit as st
import tensorflow as tf
import numpy as np
import cv2
from huggingface_hub import hf_hub_download
from tensorflow.keras.models import load_model
from io import BytesIO
from PIL import Image
import requests

# Authenticate and download model from Hugging Face
repo_id = "Hammad712/closed_eye_detection"
filename = "Closed_Eye_Detection_98.h5"
model_path = hf_hub_download(repo_id=repo_id, filename=filename)

# Load the downloaded model
model = load_model(model_path)

# Set image dimensions
img_height, img_width = 150, 150

# Custom CSS
def set_css(style):
    st.markdown(f"<style>{style}</style>", unsafe_allow_html=True)

combined_css = """
    .main, .sidebar .sidebar-content { background-color: #1c1c1c; color: #f0f2f6; }
    .block-container { padding: 1rem 2rem; background-color: #333; border-radius: 10px; box-shadow: 0px 4px 10px rgba(0, 0, 0, 0.5); }
    .stButton>button, .stDownloadButton>button { background: linear-gradient(135deg, #ff7e5f, #feb47b); color: white; border: none; padding: 10px 24px; text-align: center; text-decoration: none; display: inline-block; font-size: 16px; margin: 4px 2px; cursor: pointer; border-radius: 5px; }
    .stSpinner { color: #4CAF50; }
    .title {
        font-size: 3rem;
        font-weight: bold;
        display: flex;
        align-items: center;
        justify-content: center;
    }
    .colorful-text {
        background: -webkit-linear-gradient(135deg, #ff7e5f, #feb47b);
        -webkit-background-clip: text;
        -webkit-text-fill-color: transparent;
    }
    .black-white-text {
        color: black;
    }
    .small-input .stTextInput>div>input {
        height: 2rem;
        font-size: 0.9rem;
    }
    .small-file-uploader .stFileUploader>div>div {
        height: 2rem;
        font-size: 0.9rem;
    }
    .custom-text {
        font-size: 1.2rem;
        color: #feb47b;
        text-align: center;
        margin-top: -20px;
        margin-bottom: 20px;
    }
"""

# Streamlit application
st.set_page_config(layout="wide")

st.markdown(f"<style>{combined_css}</style>", unsafe_allow_html=True)

st.markdown('<div class="title"><span class="colorful-text">Eye</span> <span class="black-white-text">Detection Model</span></div>', unsafe_allow_html=True)
st.markdown('<div class="custom-text">Upload an image or provide a URL to predict whether the eyes are open or closed.</div>', unsafe_allow_html=True)

# Input for image URL or path
with st.expander("Input Options", expanded=True):
    url = st.text_input("Enter image URL", "")
    uploaded_file = st.file_uploader("Or upload an image", type=["jpg", "jpeg", "png"])

def load_image_from_url(url):
    response = requests.get(url)
    img = Image.open(BytesIO(response.content)).convert('RGB')
    return np.array(img)

if uploaded_file is not None or url:
    if uploaded_file is not None:
        # Read the uploaded image
        file_bytes = np.asarray(bytearray(uploaded_file.read()), dtype=np.uint8)
        image = cv2.imdecode(file_bytes, 1)
    elif url:
        # Read the image from URL
        image = load_image_from_url(url)
        image = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)

    # Resize and preprocess the image
    resized_image = cv2.resize(image, (img_height, img_width))
    input_image = resized_image.reshape((1, img_height, img_width, 3)) / 255.0

    # Perform inference
    predictions = model.predict(input_image)
    prediction = predictions[0][0]

    def get_label(prediction):
        return "Open Eye" if prediction >= 0.5 else "Closed Eye"

    label = get_label(prediction)

    # Display the image and prediction
    st.image(image, channels="BGR", caption='Uploaded Image' if uploaded_file is not None else 'Image from URL')
    st.markdown(f"### Prediction: {prediction:.2f}, Label: {label}")

    # Provide a download button for the uploaded image (optional)
    img_byte_arr = BytesIO()
    img = Image.fromarray(cv2.cvtColor(image, cv2.COLOR_BGR2RGB))
    img.save(img_byte_arr, format='JPEG')
    img_byte_arr = img_byte_arr.getvalue()

    st.download_button(
        label="Download Image",
        data=img_byte_arr,
        file_name="processed_image.jpg",
        mime="image/jpeg"
    )