keras_classifier.py

'''Train a simple deep CNN on the CIFAR10 small images dataset.
It gets to 75% validation accuracy in 25 epochs, and 79% after 50 epochs.
(it's still underfitting at that point, though).

https://github.com/keras-team/keras/blob/master/examples/cifar10_cnn.py
'''

from __future__ import print_function
import keras
from keras.preprocessing.image import ImageDataGenerator, array_to_img, img_to_array, load_img
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation, Flatten
from keras.layers import Conv2D, MaxPooling2D
from keras.callbacks import History
from keras import backend as K
import os
import numpy as np
import pandas as pd

from scraper.met_scraper import get_starting_id
import utils

img_width, img_height = 150, 150
batch_size = 32 # or 16?
num_classes = 10
epochs = 3  # ???
nb_train_samples = 9000
nb_validation_samples = 1000
save_dir = os.path.join(os.getcwd(), 'saved_models')
model_name = 'keras_artwork_classifier_trained_model.h5'
train_data_dir = "data/training"
test_data_dir = "data/testing"

LAST_SCRAPED_ID = 100888

# Resource: https://blog.keras.io/building-powerful-image-classification-models-using-very-little-data.html


if K.image_data_format() == 'channels_first':
    input_shape = (3, img_width, img_height)
else:
    input_shape = (img_width, img_height, 3)

# Model taken from example image classification code
model = Sequential()
model.add(Conv2D(32, (3, 3), padding='same', input_shape=input_shape))
model.add(Activation('relu'))
model.add(Conv2D(32, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))

model.add(Conv2D(64, (3, 3), padding='same'))
model.add(Activation('relu'))
model.add(Conv2D(64, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))

model.add(Flatten())
model.add(Dense(512))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(num_classes))
model.add(Activation('softmax'))

# initiate RMSprop optimizer
# opt = keras.optimizers.rmsprop(lr=0.0001, decay=1e-6)

# Let's train the model using RMSprop
model.compile(loss='categorical_crossentropy',
              optimizer='rmsprop',
              metrics=['accuracy'])

# training data augmentation
train_datagen = ImageDataGenerator(
    #rotation_range=40,
    rescale=1. / 255,
    shear_range=0.2,
    zoom_range=0.2,
    width_shift_range=0.1,  # randomly shift images horizontally (fraction of total width)
    height_shift_range=0.1,  # randomly shift images vertically (fraction of total height)
    horizontal_flip=True,
    fill_mode='nearest')

# testing data augmnetation
test_datagen = ImageDataGenerator(rescale=1. / 255)

train_generator = train_datagen.flow_from_directory(
    train_data_dir,
    target_size=(img_width, img_height),
    batch_size=batch_size,
    class_mode='categorical')

testing_generator = test_datagen.flow_from_directory(
    test_data_dir,
    target_size=(img_width, img_height),
    batch_size=batch_size,
    class_mode='categorical')

history = History()

model.fit_generator(
    train_generator,
    steps_per_epoch=nb_train_samples // batch_size,
    epochs=epochs,
    validation_data=testing_generator,
    validation_steps=nb_validation_samples // batch_size,
    verbose=2,
    callbacks=[history])

# Save model and weights
if not os.path.isdir(save_dir):
    os.makedirs(save_dir)
model_path = os.path.join(save_dir, model_name)
model.save(model_path)
print('Saved trained model at %s ' % model_path)

print(history.epoch)
print(history.history)

# Score trained model.
# scores = model.evaluate(testing_data, testing_labels, verbose=1)
# print('Test loss:', scores[0])
# print('Test accuracy:', scores[1])