Solving over fitting problem in computer vision project, data augmentation

1 of the files Data needs Data augmentation to increase number of images from 24 to 240


Code
rom keras import regularizers

IMG_SIZE = 224
input_shape = (IMG_SIZE, IMG_SIZE, 3)
model4 = models.Sequential()
model4.add(Conv2D(32, kernel_size=(3, 3),activation='LeakyReLU',padding = 'Same',input_shape=input_shape,kernel_regularizer=regularizers.L1L2(l1=1e-5, l2=1e-4),bias_regularizer=regularizers.L2(1e-4),activity_regularizer=regularizers.L2(1e-5)))
model4.add(Conv2D(32,kernel_size=(3, 3), activation='LeakyReLU',padding = 'Same',kernel_regularizer=regularizers.L1L2(l1=1e-5, l2=1e-4),bias_regularizer=regularizers.L2(1e-4),activity_regularizer=regularizers.L2(1e-5)))
model4.add(Conv2D(filters=64, kernel_size=(3, 3), activation='relu'))
model4.add(Flatten())
model4.add(Dense(64, activation='LeakyReLU'))
model4.add(Dense(num_classes, activation='softmax'))
model4.summary()
model4.compile(optimizer=keras.optimizers.Adam(lr=3e-4),loss='categorical_crossentropy',metrics=['accuracy'])
history4=model4.fit(train_ds.prefetch(tf.data.AUTOTUNE),
epochs=30,
verbose=2,
validation_data=val_ds.prefetch(tf.data.AUTOTUNE))