import numpy as np from sklearn.model_selection import train_test_split from tensorflow.keras.models import Sequential from tensorflow.keras.layers import Conv2D, MaxPooling2D, Flatten, Dense from tensorflow.keras.utils import to_categorical from tensorflow.keras.preprocessing.image import ImageDataGenerator # Simulated dataset loading function # X: images, y: labels, skin_tones: 0 for lighter, 1 for darker X = np.load('face_images.npy') # shape (num_samples, 64, 64, 3) y = np.load('face_labels.npy') # shape (num_samples,) skin_tones = np.load('skin_tones.npy') # shape (num_samples,) # Split data X_train, X_test, y_train, y_test, skin_train, skin_test = train_test_split( X, y, skin_tones, test_size=0.2, random_state=42, stratify=y) # Data augmentation for darker skin tones datagen = ImageDataGenerator( rotation_range=10, width_shift_range=0.1, height_shift_range=0.1, horizontal_flip=True ) # Separate darker skin tone samples dark_indices = np.where(skin_train == 1)[0] X_dark = X_train[dark_indices] y_dark = y_train[dark_indices] # Augment darker skin tone images to balance dataset augmented_images = [] augmented_labels = [] for i in range(len(X_dark)): x = X_dark[i].reshape((1,) + X_dark[i].shape) aug_iter = datagen.flow(x, batch_size=1) for _ in range(3): # create 3 augmented images per original batch = next(aug_iter) augmented_images.append(batch[0]) augmented_labels.append(y_dark[i]) # Combine original and augmented data X_train_balanced = np.concatenate([X_train, np.array(augmented_images)]) y_train_balanced = np.concatenate([y_train, np.array(augmented_labels)]) skin_train_balanced = np.concatenate([skin_train, np.ones(len(augmented_images))]) # Convert labels to categorical num_classes = len(np.unique(y)) y_train_cat = to_categorical(y_train_balanced, num_classes) y_test_cat = to_categorical(y_test, num_classes) # Compute class weights to balance classes from sklearn.utils import class_weight class_weights = class_weight.compute_class_weight('balanced', classes=np.unique(y_train_balanced), y=y_train_balanced) class_weight_dict = dict(enumerate(class_weights)) # Define simple CNN model model = Sequential([ Conv2D(32, (3,3), activation='relu', input_shape=(64,64,3)), MaxPooling2D(2,2), Conv2D(64, (3,3), activation='relu'), MaxPooling2D(2,2), Flatten(), Dense(64, activation='relu'), Dense(num_classes, activation='softmax') ]) model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy']) # Train model with class weights model.fit(X_train_balanced, y_train_cat, epochs=15, batch_size=32, class_weight=class_weight_dict, validation_split=0.1) # Evaluate overall accuracy loss, overall_acc = model.evaluate(X_test, y_test_cat, verbose=0) # Evaluate accuracy by skin tone from sklearn.metrics import accuracy_score y_pred_probs = model.predict(X_test) y_pred = np.argmax(y_pred_probs, axis=1) acc_lighter = accuracy_score(y_test[skin_test == 0], y_pred[skin_test == 0]) acc_darker = accuracy_score(y_test[skin_test == 1], y_pred[skin_test == 1]) print(f'Overall accuracy: {overall_acc*100:.2f}%') print(f'Accuracy on lighter skin tones: {acc_lighter*100:.2f}%') print(f'Accuracy on darker skin tones: {acc_darker*100:.2f}%')
Before changes:
Overall accuracy: 90%
Accuracy on lighter skin tones: 95%
Accuracy on darker skin tones: 75%
After changes:
Overall accuracy: 88%
Accuracy on lighter skin tones: 90%
Accuracy on darker skin tones: 86%