keras fashion dataset

from keras.datasets import fashion_mnist

(train_X, train_Y), (test_X, test_Y) = fashion_mnist.load_data()

import numpy as np
from keras.utils import to_categorical
import matplotlib.pyplot as plt

print('Training data shape : ', train_X.shape, train_Y.shape)
print('Testing data shape : ', test_X.shape, test_Y.shape)


classes = np.unique(train_Y)
nClasses = len(classes)
print('Total number of outputs : ', nClasses)
print('Output classes : ', classes)

plt.figure(figsize=[5, 5])

# Cam așa arată prima imagine din setul de trainig
'''
plt.subplot(121)
plt.imshow(train_X[10, :, :], cmap='gray')
plt.title("Ground Truth : {}".format(train_Y[0]))
plt.savefig('prima_imagine_train.png')
'''
# Cam așa arată prima imagine din setul de test
'''
plt.subplot(122)
plt.imshow(test_X[10, :, :], cmap='gray')
plt.title("Ground Truth : {}".format(test_Y[0]))
plt.savefig('prima_imagine_test.png')
'''

train_X = train_X.reshape(-1, 28, 28, 1)
test_X = test_X.reshape(-1, 28, 28, 1)
print(train_X.shape, test_X.shape)

train_X = train_X.astype('float32')
test_X = test_X.astype('float32')
train_X = train_X / 255.
test_X = test_X / 255.

# Îmi place de mor one-hot encoding
train_Y_one_hot = to_categorical(train_Y)
test_Y_one_hot = to_categorical(test_Y)

print('Original label:', train_Y[0])
print('After conversion to one-hot:', train_Y_one_hot[0])

from sklearn.model_selection import train_test_split

train_X, valid_X, train_label, valid_label = train_test_split(train_X, train_Y_one_hot, test_size=0.2, random_state=13)

print(train_X.shape, valid_X.shape, train_label.shape, valid_label.shape)

import keras
from keras.models import Sequential, Input, Model
from keras.layers import Dense, Dropout, Flatten
from keras.layers import Conv2D, MaxPooling2D
from keras.layers.normalization import BatchNormalization
from keras.layers.advanced_activations import LeakyReLU


batch_size = 64
epochs = 20
num_classes = 10

fashion_model = Sequential()
fashion_model.add(Conv2D(32, kernel_size=(3, 3), activation='linear', padding='same', input_shape=(28, 28, 1)))
fashion_model.add(LeakyReLU(alpha=0.1))
fashion_model.add(MaxPooling2D((2, 2), padding='same'))
fashion_model.add(Dropout(0.25))
fashion_model.add(Conv2D(64, (3, 3), activation='linear', padding='same'))
fashion_model.add(LeakyReLU(alpha=0.1))
fashion_model.add(MaxPooling2D(pool_size=(2, 2), padding='same'))
fashion_model.add(Dropout(0.25))
fashion_model.add(Conv2D(128, (3, 3), activation='linear', padding='same'))
fashion_model.add(LeakyReLU(alpha=0.1))
fashion_model.add(MaxPooling2D(pool_size=(2, 2), padding='same'))
fashion_model.add(Dropout(0.4))
fashion_model.add(Flatten())
fashion_model.add(Dense(128, activation='linear'))
fashion_model.add(LeakyReLU(alpha=0.1))
fashion_model.add(Dropout(0.3))
fashion_model.add(Dense(num_classes, activation='softmax'))

from keras.utils import plot_model
plot_model(fashion_model, to_file='model.png')

fashion_model.compile(loss=keras.losses.categorical_crossentropy, optimizer=keras.optimizers.Adam(),
                      metrics=['accuracy'])

print(fashion_model.summary())

fashion_train_dropout = fashion_model.fit(train_X, train_label, batch_size=batch_size, epochs=epochs, verbose=1,
                                          validation_data=(valid_X, valid_label))

fashion_model.save("fashionistu.h5py")

test_eval = fashion_model.evaluate(test_X, test_Y_one_hot, verbose=0)
print('Test loss:', test_eval[0])
print('Test accuracy:', test_eval[1])

accuracy = fashion_train_dropout.history['acc']
val_accuracy = fashion_train_dropout.history['val_acc']
loss = fashion_train_dropout.history['loss']
val_loss = fashion_train_dropout.history['val_loss']
epochs = range(len(accuracy))

plt.figure(figsize=[5, 5])

plt.figure()
plt.subplot(121)
plt.plot(epochs, accuracy, 'bo', label='Training accuracy')
plt.plot(epochs, val_accuracy, 'b', label='Validation accuracy')
plt.title('Training and validation accuracy')
plt.legend()
plt.savefig('UNU.png')
plt.show()


plt.figure()
plt.subplot(122)
plt.plot(epochs, loss, 'bo', label='Training loss')
plt.plot(epochs, val_loss, 'b', label='Validation loss')
plt.title('Training and validation loss')
plt.legend()
plt.savefig('DOI.png')
plt.show()