model.py

import tensorflow as tf
from datasets import load_dataset
from tensorflow.keras.preprocessing import image
import numpy as np
from sklearn.model_selection import train_test_split

# Load the HAM10000 dataset using Hugging Face datasets library
dataset = load_dataset("Nagabu/HAM10000")

# Preprocess and prepare the dataset
def preprocess_image(img_path, target_size=(224, 224)):
    img = image.load_img(img_path, target_size=target_size)
    img_array = image.img_to_array(img)
    img_array = np.expand_dims(img_array, axis=0) / 255.0  # Normalize pixel values
    return img_array
def load_model():
    model = tf.keras.models.load_model('skin_cancer_model.h5')
    return model
def prepare_data():
    # Assuming you have a directory of images and their corresponding labels
    # Create the dataset
    images = []
    labels = []

    # Extract image paths and labels from the dataset
    for example in dataset['train']:
        images.append(example['image'])  # Path to the image
        labels.append(example['dx'])  # The label (skin cancer class)
    
    # Convert lists to numpy arrays
    images = np.array(images)
    labels = np.array(labels)

    # Split into train and test sets
    x_train, x_test, y_train, y_test = train_test_split(images, labels, test_size=0.2, random_state=42)

    return x_train, x_test, y_train, y_test

# Simple CNN Model
def build_model():
    model = tf.keras.models.Sequential([
        tf.keras.layers.Conv2D(32, (3, 3), activation='relu', input_shape=(224, 224, 3)),
        tf.keras.layers.MaxPooling2D(2, 2),
        tf.keras.layers.Conv2D(64, (3, 3), activation='relu'),
        tf.keras.layers.MaxPooling2D(2, 2),
        tf.keras.layers.Conv2D(128, (3, 3), activation='relu'),
        tf.keras.layers.Flatten(),
        tf.keras.layers.Dense(128, activation='relu'),
        tf.keras.layers.Dense(7, activation='softmax')  # 7 classes for skin cancer types
    ])
    model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])
    return model