# ATTENTION: Please do not alter any of the provided code in the exercise. Only add your own code where indicated
# ATTENTION: Please do not add or remove any cells in the exercise. The grader will check specific cells based on the cell position.
# ATTENTION: Please use the provided epoch values when training.
import csv
import numpy as np
import tensorflow as tf
from tensorflow.keras.preprocessing.image import ImageDataGenerator
from os import getcwd
def get_data(filename):
# You will need to write code that will read the file passed
# into this function. The first line contains the column headers
# so you should ignore it
# Each successive line contians 785 comma separated values between 0 and 255
# The first value is the label
# The rest are the pixel values for that picture
# The function will return 2 np.array types. One with all the labels
# One with all the images
#
# Tips:
# If you read a full line (as 'row') then row[0] has the label
# and row[1:785] has the 784 pixel values
# Take a look at np.array_split to turn the 784 pixels into 28x28
# You are reading in strings, but need the values to be floats
# Check out np.array().astype for a conversion
with open(filename) as training_file:
# Your code starts here
all_lines = training_file.readlines()[1:]
length = len(all_lines)
labels = np.zeros(length)
images = np.zeros((length, 28, 28))
for idx, line in enumerate(all_lines):
line = line.strip().split(',')
if not line:
continue
labels[idx] = int(line[0])
image = np.asarray(line[1:], dtype=np.float32)
image = np.array_split(image, 28)
images[idx, :, :] = image
# Your code ends here
return images, labels
path_sign_mnist_train = f"{getcwd()}/../tmp2/sign_mnist_train.csv"
path_sign_mnist_test = f"{getcwd()}/../tmp2/sign_mnist_test.csv"
training_images, training_labels = get_data(path_sign_mnist_train)
testing_images, testing_labels = get_data(path_sign_mnist_test)
# Keep these
print(training_images.shape)
print(training_labels.shape)
print(testing_images.shape)
print(testing_labels.shape)
# Their output should be:
# (27455, 28, 28)
# (27455,)
# (7172, 28, 28)
# (7172,)
# In this section you will have to add another dimension to the data
# So, for example, if your array is (10000, 28, 28)
# You will need to make it (10000, 28, 28, 1)
# Hint: np.expand_dims
training_images = np.expand_dims(training_images, axis=-1)# Your Code Here
testing_images = np.expand_dims(testing_images, axis=-1)# Your Code Here
# Create an ImageDataGenerator and do Image Augmentation
train_datagen = ImageDataGenerator(
# Your Code Here
rescale=1./255,
rotation_range=20,
width_shift_range=0.2,
height_shift_range=0.2,
shear_range=0.2,
zoom_range=0.2,
fill_mode='nearest',
horizontal_flip=True)
validation_datagen = ImageDataGenerator(
rescale=1./255)
# Keep These
print(training_images.shape)
print(testing_images.shape)
# Their output should be:
# (27455, 28, 28, 1)
# (7172, 28, 28, 1)
# Define the model
# Use no more than 2 Conv2D and 2 MaxPooling2D
model = tf.keras.models.Sequential([
tf.keras.layers.Conv2D(64, (3,3), activation='relu', input_shape=(28, 28, 1)),
tf.keras.layers.MaxPooling2D((2,2)),
tf.keras.layers.Conv2D(32, (3,3), activation='relu'),
tf.keras.layers.MaxPooling2D((2,2)),
tf.keras.layers.Flatten(),
tf.keras.layers.Dense(128, activation='relu'),
tf.keras.layers.Dense(25, activation='softmax')])
# Compile Model.
model.compile(optimizer = 'adam',
loss = 'sparse_categorical_crossentropy',
metrics = ['acc'])
# Train the Model
train_generator = train_datagen.flow(training_images, training_labels)
validation_generator = validation_datagen.flow(testing_images, testing_labels)
history = model.fit_generator(train_generator,
epochs=2,
verbose=1,
validation_data=validation_generator)
model.evaluate(testing_images, testing_labels, verbose=0)
# Plot the chart for accuracy and loss on both training and validation
%matplotlib inline
import matplotlib.pyplot as plt
acc = history.history['acc']
val_acc = history.history['val_acc']
loss = history.history['loss']
val_loss = history.history['val_loss']
epochs = range(len(acc))
plt.plot(epochs, acc, 'r', label='Training accuracy')
plt.plot(epochs, val_acc, 'b', label='Validation accuracy')
plt.title('Training and validation accuracy')
plt.legend()
plt.figure()
plt.plot(epochs, loss, 'r', label='Training Loss')
plt.plot(epochs, val_loss, 'b', label='Validation Loss')
plt.title('Training and validation loss')
plt.legend()
plt.show()
# Now click the 'Submit Assignment' button above.
%%javascript
<!-- Save the notebook -->
IPython.notebook.save_checkpoint();
%%javascript
IPython.notebook.session.delete();
window.onbeforeunload = null
setTimeout(function() { window.close(); }, 1000);