app.py

import streamlit as st
import tensorflow as tf
import numpy as np
from PIL import Image
import requests
from io import BytesIO
import pandas as pd

# Move st.set_page_config() to the top
st.set_page_config(page_title="Fish Species Classifier", page_icon="🐠", layout="wide")

# Load model
@st.cache_resource
def load_model():
    return tf.keras.models.load_model('fish_classification_model.h5')

model = load_model()

# Class names
class_names = ['Black Sea Sprat', 'Gilt Head Bream', 'Horse Mackerel', 'Red Mullet', 'Red Sea Bream', 'Sea Bass', 'Shrimp', 'Striped Red Mullet', 'Trout']  # Sınıf isimleri

# Function to get fish emoji
def get_fish_emoji(fish_name):
    emoji_dict = {
        'Black Sea Sprat': '🐟',
        'Gilt Head Bream': '🐠',
        'Horse Mackerel': '🐟',
        'Red Mullet': '🐡',
        'Red Sea Bream': '🐠',
        'Sea Bass': '🐟',
        'Shrimp': '🦐',
        'Striped Red Mullet': '🐡',
        'Trout': '🐟'
    }
    return emoji_dict.get(fish_name, '🐠')

# Add a background image
background_image = """
<style>
[data-testid="stAppViewContainer"] > .main {
    background-image: url("https://images.unsplash.com/photo-1498574932731-e711f7092d07");
    background-size: cover;
    background-position: center center;
    background-repeat: no-repeat;
    background-attachment: local;
}
</style>
"""
st.markdown(background_image, unsafe_allow_html=True)

# Custom CSS for better styling
st.markdown("""
    <style>
    .big-font {
        font-size:50px !important;
        color: #0e1117;
        text-align: center;
    }
    .result-font {
        font-size:30px !important;
        color: #0e1117;
        text-align: center;
    }
    </style>
    """, unsafe_allow_html=True)

# Title with emoji
st.markdown('<p class="big-font">🐠 Fish Species Classification 🐟</p>', unsafe_allow_html=True)

# File uploader
uploaded_file = st.file_uploader("Upload a fish image", type=["jpg", "jpeg", "png"])

# URL input
image_url = st.text_input("Or enter an image URL")

if uploaded_file is not None or image_url:
    if uploaded_file is not None:
        image = Image.open(uploaded_file)
    else:
        response = requests.get(image_url)
        image = Image.open(BytesIO(response.content))
    
    st.image(image, caption='Uploaded Image', use_column_width=True)  # Yüklenen resmi göster
    
    # Preprocess image
    image = image.resize((224, 224))
    image_array = np.array(image) / 255.0
    image_array = np.expand_dims(image_array, axis=0)  # Resmi ön işle
    
    # Make prediction
    prediction = model.predict(image_array)
    predicted_class = class_names[np.argmax(prediction)]
    confidence = np.max(prediction)  # Tahmin yap
    
    # Display result with emoji
    st.markdown(f'<p class="result-font">Predicted fish species: {predicted_class} {get_fish_emoji(predicted_class)}</p>', unsafe_allow_html=True)
    st.markdown(f'<p class="result-font">Confidence: {confidence:.2f}</p>', unsafe_allow_html=True)

    # Display bar chart of probabilities
    st.subheader("Prediction Probabilities")
    prob_df = pd.DataFrame({'Species': class_names, 'Probability': prediction[0]})
    prob_df = prob_df.sort_values('Probability', ascending=False).reset_index(drop=True)
    st.bar_chart(prob_df.set_index('Species'))

# Add some information about the project
st.sidebar.title("About")
st.sidebar.info(
    "This app uses a deep learning model to classify fish species. "
    "Upload an image or provide a URL to get started!"
)

# Add a footer
st.markdown(
    """
    <style>
    #MainMenu {visibility: hidden;}
    footer {visibility: hidden;}
    .footer {
        position: fixed;
        left: 0;
        bottom: 0;
        width: 100%;
        background-color: rgba(14, 17, 23, 0.5);
        color: white;
        text-align: center;
    }
    </style>
    <div class="footer">
        <p>Developed with ❤️ by AE</p>
    </div>
    """,
    unsafe_allow_html=True
)