import gradio as gr
import tensorflow as tf
from PIL import Image
import numpy as np

# Load your custom regression model
model_path = "freshwaterfish_classifier_model_BasicKeras.keras"
model = tf.keras.models.load_model(model_path)

labels = ['Catfish', 'Freshwater Eel', 'Goby', 'Perch']

# Define regression function
def predict_regression(image):
    # Preprocess image
    image = Image.fromarray(image.astype('uint8'))
    image = image.resize((224, 224)).convert('RGB')
    image = np.array(image)
    print(image.shape)
    # Predict
    prediction = model.predict(image[None, ...])  # Assuming single regression value
    confidences = {labels[i]: np.round(float(prediction[0][i]), 2) for i in range(len(labels))}
    return confidences

# Define the file paths for the test images
test_images = ["myImages/Egli1.jpeg", "myImages/Egli2.jpeg", "myImages/Wels1.jpeg", "myImages/Wels2.jpeg"]

# Load and preprocess the test images
example_images = [np.array(Image.open(image_path).resize((224, 224)).convert('RGB')) / 255.0 for image_path in test_images]

# Create Gradio interface
input_image = gr.Image()
output_text = gr.Textbox(label="Predicted Value")
interface = gr.Interface(fn=predict_regression, 
                         inputs=input_image, 
                         outputs=gr.Label(),
                         title="Freshwater Fish Classifier",
                         description="This model predicts four species of a freshwater fish from the lake of constance.",
                        examples=example_images
                        )
interface.launch()