app.py

import streamlit as st
import cv2
import numpy as np
from tensorflow.keras.preprocessing import image
import tensorflow as tf

# Load the saved model (replace with your model filename)
model = tf.keras.models.load_model('cat_dog_classifier.keras')

# Image dimensions for the model
img_width, img_height = 224, 224


def preprocess_image(img):
  """Preprocesses an image for prediction."""
  img = cv2.resize(img, (img_width, img_height))
  img = img.astype('float32') / 255.0
  img = np.expand_dims(img, axis=0)
  return img


def predict_class(image):
  """Predicts image class and probabilities."""
  preprocessed_img = preprocess_image(image)
  prediction = model.predict(preprocessed_img)
  class_names = ['cat', 'dog']  # Adjust class names according to your model
  return class_names[np.argmax(prediction)], np.max(prediction)


def display_results(class_name, probability):
  """Displays prediction results in a progress bar style."""
  st.write(f"**Predicted Class:** {class_name}")

  # Create a progress bar using st.progress
  progress = st.progress(0)
  for i in range(100):
    progress.progress(i + 1)
    if i == int(probability * 100):
      break
  st.write(f"**Probability:** {probability:.2f}")


def main():
  """Main app function."""
  st.title("Image Classifier")
  st.write("Upload an image to classify it as cat or dog.")

  uploaded_file = st.file_uploader("Choose an image...", type="jpg")
  if uploaded_file is not None:
    image = cv2.imdecode(np.frombuffer(uploaded_file.read(), np.uint8), cv2.IMREAD_COLOR)
    st.image(image, caption="Uploaded Image", use_column_width=True)

    predicted_class, probability = predict_class(image)
    display_results(predicted_class, probability)

main()
# if __name__ == '__main__':
#   main()