import cv2  # Assuming you have OpenCV installed
import numpy as np
from tensorflow.keras.preprocessing import image
import tensorflow as tf
# Load the saved model
model = tf.keras.models.load_model('cat_dog_classifier.keras')  # Replace with your model filename
img_width, img_height = 224, 224  # VGG16 expects these dimensions


# Function to preprocess an image for prediction
def preprocess_image(img_path):
    img = cv2.imread(img_path)  # Read the image
    img = cv2.resize(img, (img_width, img_height))  # Resize according to model input size
    img = img.astype('float32') / 255.0  # Normalize pixel values
    img = np.expand_dims(img, axis=0)  # Add a batch dimension (model expects batch of images)
    return img


# Get the path to your new image
new_image_path = 'test1/11.jpg'  # Replace with your image path

# Preprocess the image
preprocessed_image = preprocess_image(new_image_path)

# Make prediction
prediction = model.predict(preprocessed_image)

# Decode the prediction (assuming class 0 is cat, 1 is dog)
predicted_class = int(prediction[0][0] > 0.5)  # Threshold of 0.5 for binary classification
class_names = ['cat', 'dog']  # Adjust class names according to your model

print(f"Predicted class: {class_names[predicted_class]}")