USE Jupyter Notebook
NB: Please only do Tasks 1-2
We will combine what we’ve learned about convolution, max-pooling and feed-forward layers, to build a ConvNet classifier for images.
Given Code:
in[]from __future__ import absolute_import, division, print_function
# Prerequisits
!pip install pydot_ng
!pip install graphviz
!apt install graphviz > /dev/null
# import statements
import tensorflow as tf
import tensorflow.contrib.eager as tfe
import numpy as np
import matplotlib.pyplot as plt
from IPython import display
%matplotlib inline
# Enable the interactive TensorFlow interface, which is easier to understand as a beginner.
try:
tf.enable_eager_execution()
print(‘Running in Eager mode.’)
except ValueError:
print(‘Already running in Eager mode’)
in[]cifar = tf.keras.datasets.cifar10
(train_images, train_labels), (test_images, test_labels) = cifar.load_data()
cifar_labels = [‘airplane’, ‘automobile’, ‘bird’, ‘cat’, ‘deer’, ‘dog’, ‘frog’, ‘horse’, ‘ship’, ‘truck’]
in[]# Take the last 10000 images from the training set to form a validation set
train_labels = train_labels.squeeze()
validation_images = train_images[-10000:, :, :]
validation_labels = train_labels[-10000:]
train_images = train_images[:-10000, :, :]
train_labels = train_labels[:-10000]
in[]print(‘train_images.shape = {}, data-type = {}’.format(train_images.shape, train_images.dtype))
print(‘train_labels.shape = {}, data-type = {}’.format(train_labels.shape, train_labels.dtype))
print(‘validation_images.shape = {}, data-type = {}’.format(validation_images.shape, validation_images.dtype))
print(‘validation_labels.shape = {}, data-type = {}’.format(validation_labels.shape, validation_labels.dtype))
in[]plt.figure(figsize=(10,10))
for i in range(25):
plt.subplot(5,5,i+1)
plt.xticks([])
plt.yticks([])
plt.grid(‘off’)
in[]# Define the convolutinal part of the model architecture using Keras Layers.
model = tf.keras.models.Sequential([
tf.keras.layers.Conv2D(filters=48, kernel_size=(3, 3), activation=tf.nn.relu, input_shape=(32, 32, 3), padding=’same’),
tf.keras.layers.MaxPooling2D(pool_size=(3, 3)),
tf.keras.layers.Conv2D(filters=128, kernel_size=(3, 3), activation=tf.nn.relu, padding=’same’),
tf.keras.layers.MaxPooling2D(pool_size=(3, 3)),
tf.keras.layers.Conv2D(filters=192, kernel_size=(3, 3), activation=tf.nn.relu, padding=’same’),
tf.keras.layers.Conv2D(filters=192, kernel_size=(3, 3), activation=tf.nn.relu, padding=’same’),
tf.keras.layers.Conv2D(filters=128, kernel_size=(3, 3), activation=tf.nn.relu, padding=’same’),
tf.keras.layers.MaxPooling2D(pool_size=(3, 3)),
in[]model.summary()
in[]model.add(tf.keras.layers.Flatten()) # Flatten “squeezes” a 3-D volume down into a single vector.
model.add(tf.keras.layers.Dense(1024, activation=tf.nn.relu))
model.add(tf.keras.layers.Dropout(rate=0.5))
model.add(tf.keras.layers.Dense(1024, activation=tf.nn.relu))
model.add(tf.keras.layers.Dense(10, activation=tf.nn.softmax))
in[]tf.keras.utils.plot_model(model, to_file=’small_lenet.png’, show_shapes=True, show_layer_names=True)
display.display(display.Image(‘small_lenet.png’))
in[]batch_size = 128
num_epochs = 10 # The number of epochs (full passes through the data) to train for
# Compiling the model adds a loss function, optimiser and metrics to track during training
model.compile(optimizer=tf.train.AdamOptimizer(),
loss=tf.keras.losses.sparse_categorical_crossentropy,
metrics=[‘accuracy’])
# The fit function allows you to fit the compiled model to some training data
model.fit(x=train_images,
y=train_labels,
batch_size=batch_size,
epochs=num_epochs,
validation_data=(validation_images, validation_labels.astype(np.float32)))
print(‘Training complete’)
in[]metric_values = model.evaluate(x=test_images, y=test_labels)
print(‘Final TEST performance’)
for metric_value, metric_name in zip(metric_values, model.metrics_names):
print(‘{}: {}’.format(metric_name, metric_value))
in[]img_indices = np.random.randint(0, len(test_images), size=[25])
sample_test_images = test_images[img_indices]
sample_test_labels = [cifar_labels[i] for i in test_labels[img_indices].squeeze()]
predictions = model.predict(sample_test_images)
max_prediction = np.argmax(predictions, axis=1)
prediction_probs = np.max(predictions, axis=1)
in[]plt.figure(figsize=(10,10))
for i, (img, prediction, prob, true_label) in enumerate(
zip(sample_test_images, max_prediction, prediction_probs, sample_test_labels)):
plt.subplot(5,5,i+1)
plt.xticks([])
plt.yticks([])
plt.grid(‘off’)
plt.imshow(img)
plt.xlabel(‘{} ({:0.3f})’.format(cifar_labels[prediction], prob))
plt.ylabel(‘{}’.format(true_label))
NB: Please only do Tasks 1-2
Tensorflow documentation: from ‘tensorflow.org’ website: search: ‘tf.keras.layers.BatchNormalization’
research paper: search on web: ‘proceedings.mlr.press/v37/ioffe15.pdf’
NB: Please only do Tasks 1-2