import gradio as gr
from transformers import pipeline
from PIL import Image

# Function to classify the face shape
def classify_face_shape(image):
    
    # Initialize the pipeline
    pipe = pipeline("image-classification", model="metadome/face_shape_classification")
    
    # Run the pipeline on the uploaded image
    output = pipe(image)
    # Log the output for debugging
    print("Pipeline output for shape:", output)
    # Format the output to be compatible with gr.outputs.Label
    formatted_output = {item['label']: item['score'] for item in output}
    
    return formatted_output
    
def classify_age(image):
    pipe = pipeline("image-classification", model="nateraw/vit-age-classifier")
    # Run the pipeline on the uploaded image
    output = pipe(image)
    
    print("Pipeline output for age:", output)
    # Format the output to be compatible with gr.outputs.Label
    formatted_output = {item['label']: item['score'] for item in output}
    
    return formatted_output
    
def classify_skin_type(image):
    pipe = pipeline("image-classification", model="dima806/skin_types_image_detection")
    
    # Run the pipeline on the uploaded image
    output = pipe(image)
    
    print("Pipeline output for skin_type:", output)
    # Format the output to be compatible with gr.outputs.Label
    formatted_output = {item['label']: item['score'] for item in output}
    
    return formatted_output

def classify_acne_type(image):
    pipe = pipeline("image-classification", model="imfarzanansari/skintelligent-acne")
    
    # Run the pipeline on the uploaded image
    output = pipe(image)
    
    print("Pipeline output for acne:", output)
    # Format the output to be compatible with gr.outputs.Label
    formatted_output = {item['label']: item['score'] for item in output}
    
    return formatted_output

def classify_hair_color(image):
    
    #pipe = pipeline("image-classification", model="enzostvs/hair-color")
    pipe = pipeline("image-classification", model="londe33/hair_v02")
    
    # Run the pipeline on the uploaded image
    output = pipe(image)
    
    print("Pipeline output for hir color:", output)
    # Format the output to be compatible with gr.outputs.Label
    formatted_output = {item['label']: item['score'] for item in output}
    
    return formatted_output

def classify_eye_shape(image):
    
    pipe = pipeline("image-classification", model="justingrammens/eye-shape")
    
    # Run the pipeline on the uploaded image
    output = pipe(image)
    
    print("Pipeline output for eye shape:", output)
    # Format the output to be compatible with gr.outputs.Label
    formatted_output = {item['label']: item['score'] for item in output}
    
    return formatted_output
    
    
def classify_image_with_multiple_models(image):
    face_shape_result = classify_face_shape(image)
    age_result = classify_age(image)
    skin_type_result = classify_skin_type(image)
    acne_results = classify_acne_type(image)
    hair_color_results = classify_hair_color(image)
    eye_shape = classify_eye_shape(image)

    return face_shape_result, age_result, skin_type_result, acne_results, hair_color_results, eye_shape


# Create the Gradio interface
demo = gr.Interface(
    fn=classify_image_with_multiple_models,  # The function to run
    inputs=gr.Image(type="pil"),
    outputs=[
        gr.Label(num_top_classes=5, label="Face Shape"), 
        gr.Label(num_top_classes=5, label="Age"), 
        gr.Label(num_top_classes=3, label="Skin Type"), 
        gr.Label(num_top_classes=5, label="Acne Type"), 
        gr.Label(num_top_classes=5, label="Hair Color"), 
        gr.Label(num_top_classes=4, label="Eye Shape")
    ],
    title="Multiple Model Classification",
    description="Upload an image to classify the face using mutiple classification models"
)
    
demo.launch(auth=("admin", "pass1234"))
#demo.launch()