AE

-- coding: utf-8 --

"""AE1.ipynb

Automatically generated by Colaboratory.

Original file is located at https://colab.research.google.com/drive/1PTUrfACLskfbIOF8AeZot1vRrp7SkTy5 """

import numpy as np from tensorflow import keras from tensorflow.keras import layers import matplotlib.pyplot as plt

(x_train, _), (x_test, _) = keras.datasets.mnist.load_data()

Normalize and reshape the input data

x_train = x_train / 255.0 x_test = x_test / 255.0

x_train = np.reshape(x_train, (len(x_train), 28, 28, 1))

x_test = np.reshape(x_test, (len(x_test), 28, 28, 1))

from keras.layers import Flatten, Dense, Reshape

input_img = keras.Input(shape=(28, 28, 1)) encoded = Flatten()(input_img) encoded = Dense(64, activation='relu')(encoded) decoded = Dense(784, activation='sigmoid')(encoded) decoded = Reshape((28, 28, 1))(decoded)

autoencoder = keras.Model(input_img, decoded) autoencoder.compile(optimizer='adam', loss='binary_crossentropy')

autoencoder.summary()

from tensorflow.keras.utils import plot_model plot_model(autoencoder, to_file='model_visualization.png', show_shapes=True)

autoencoder.fit(x_train, x_train, epochs=10, batch_size=128, shuffle=True, validation_data=(x_test, x_test))

Test the autoencoder

decoded_imgs = autoencoder.predict(x_test)

Display some results

n = 10 # Number of digits to display plt.figure(figsize=(20, 4)) for i in range(n):

Original images

ax = plt.subplot(2, n, i + 1) plt.imshow(x_test[i].reshape(28, 28)) plt.gray() ax.get_xaxis().set_visible(False) ax.get_yaxis().set_visible(False)

Decoded images

ax = plt.subplot(2, n, i + 1 + n) plt.imshow(decoded_imgs[i].reshape(28, 28)) plt.gray() ax.get_xaxis().set_visible(False) ax.get_yaxis().set_visible(False) plt.show()

RNN

-- coding: utf-8 --

"""RNN.ipynb

Automatically generated by Colaboratory.

Original file is located at https://colab.research.google.com/drive/1RYw2R5oyRY1Dl1dQEybYpT5GhtJSra2z """

import numpy as np from tensorflow.keras.datasets import imdb from tensorflow.keras.models import Sequential from tensorflow.keras.layers import Embedding, LSTM, Dense from tensorflow.keras.preprocessing import sequence

Set random seed for reproducibility

np.random.seed(42)

Set the maximum number of words to be used (vocabulary size)

max_words = 5000

Load the IMDB dataset

(x_train, y_train), (x_test, y_test) = imdb.load_data(num_words=max_words)

Pad sequences to a fixed length

max_length = 100 x_train = sequence.pad_sequences(x_train, maxlen=max_length) x_test = sequence.pad_sequences(x_test, maxlen=max_length)

Create the RNN model

model = Sequential() model.add(Embedding(max_words, 32, input_length=max_length)) model.add(LSTM(100)) model.add(Dense(1, activation='sigmoid'))

Compile the model

model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])

Print the model summary

print(model.summary())

Train the model

batch_size = 64 epochs = 5 model.fit(x_train, y_train, batch_size=batch_size, epochs=epochs, validation_data=(x_test, y_test))

Evaluate the model

scores = model.evaluate(x_test, y_test, verbose=0) print('Test loss:', scores[0]) print('Test accuracy:', scores[1])

CNN

-- coding: utf-8 --

"""CNN1.ipynb

Automatically generated by Colaboratory.

Original file is located at https://colab.research.google.com/drive/133p22NryABJ8evbwD4GFIjP0JqgcjvGY """

import tensorflow as tf from tensorflow.keras import datasets, layers, models import matplotlib.pyplot as plt

(train_images, train_labels), (test_images, test_labels) = datasets.cifar100.load_data()

train_images, test_images = train_images/255.0, test_images/255.0

for i in range(25): plt.subplot(5,5,i+1) plt.imshow(train_images[i])

from keras.layers import Conv2D, MaxPooling2D, Flatten, Dense

model = models.Sequential() model.add(Conv2D(64,(3,3), activation = 'relu', input_shape=(32,32,3))) model.add(MaxPooling2D((2,2))) model.add(Conv2D(128,(3,3), activation = 'relu'))

model.add(Flatten()) model.add(Dense(256, activation='relu')) model.add(Dense(100, activation='relu'))

model.summary()

from keras.utils import custom_object_scope

model.compile(optimizer='adagrad', loss='sparse_categorical_crossentropy', metrics=['accuracy']) history = model.fit(train_images, train_labels, epochs=3, batch_size=128, validation_split=0.2)

plt.plot(history.history['accuracy']) plt.plot(history.history['val_accuracy'])

test_loss, test_accuracy = model.evaluate(test_images, test_labels) print("accuracy: "+test_accuracy) print("loss: "+test_loss)

history2 = model.fit(train_images, train_labels, epochs=3, batch_size=256, validation_split=0.2)

plt.plot(history2.history['accuracy']) plt.plot(history2.history['val_accuracy'])

test_loss2, test_accuracy2 = model.evaluate(test_images, test_labels) print("accuracy: "+test_accuracy2) print("loss: "+test_loss2)