In this notebook, a template is provided for you to implement your functionality in stages which is required to successfully complete this project. If additional code is required that cannot be included in the notebook, be sure that the Python code is successfully imported and included in your submission, if necessary. Sections that begin with 'Implementation' in the header indicate where you should begin your implementation for your project. Note that some sections of implementation are optional, and will be marked with 'Optional' in the header.
In addition to implementing code, there will be questions that you must answer which relate to the project and your implementation. Each section where you will answer a question is preceded by a 'Question' header. Carefully read each question and provide thorough answers in the following text boxes that begin with 'Answer:'. Your project submission will be evaluated based on your answers to each of the questions and the implementation you provide.
Note: Code and Markdown cells can be executed using the Shift + Enter keyboard shortcut. In addition, Markdown cells can be edited by typically double-clicking the cell to enter edit mode.
Visualize the German Traffic Signs Dataset. This is open ended, some suggestions include: plotting traffic signs images, plotting the count of each sign, etc. Be creative!
The pickled data is a dictionary with 4 key/value pairs:
In [2]:
import hashlib
import os
import pickle
from urllib.request import urlretrieve
import numpy as np
from PIL import Image
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import LabelBinarizer
from sklearn.utils import resample
from tqdm import tqdm
from zipfile import ZipFile
import math
import numpy as np
import tensorflow as tf
from tqdm import tqdm
import matplotlib.pyplot as plt
In [3]:
training_file = 'traffic-sign-data/train.p'
testing_file = 'traffic-sign-data/test.p'
with open(training_file, mode='rb') as f:
train = pickle.load(f)
with open(testing_file, mode='rb') as f:
test = pickle.load(f)
train_features, train_labels, train_size, train_coords = train['features'], train['labels'], train['sizes'], train['coords']
test_features, test_labels, test_size, test_coords = test['features'], test['labels'], test['sizes'], test['coords']
In [4]:
assert len(train_features) == len(train_labels), 'features must be same size as labels'
In [5]:
# Reshape train features
train_features = np.arange(len(train_features)*1024).reshape((len(train_features), 1024))
test_features = np.arange(len(test_features)*1024).reshape((len(test_features), 1024))
In [6]:
assert len(train_features) == len(train_labels), 'features must be same size as labels'
In [7]:
_epochs_completed = 0
_index_in_epoch = 0
_num_examples = len(train_features)
In [10]:
"""
Helper-function for flattening a layer
A convolutional layer produces an output tensor with 4 dimensions. We will add fully-connected layers after the
convolution layers, so we need to reduce the 4-dim tensor to 2-dim which can be used as input to the fully-connected layer.
"""
def flatten_layer(layer):
# Get the shape of the input layer.
layer_shape = layer.get_shape()
# The shape of the input layer is assumed to be:
# layer_shape == [num_images, img_height, img_width, num_channels]
# The number of features is: img_height * img_width * num_channels
# We can use a function from TensorFlow to calculate this.
num_features = layer_shape[1:4].num_elements()
# Reshape the layer to [num_images, num_features].
# Note that we just set the size of the second dimension
# to num_features and the size of the first dimension to -1
# which means the size in that dimension is calculated
# so the total size of the tensor is unchanged from the reshaping.
layer_flat = tf.reshape(layer, [-1, num_features])
# The shape of the flattened layer is now:
# [num_images, img_height * img_width * num_channels]
# Return both the flattened layer and the number of features.
return layer_flat, num_features
# Problem 1 - Implement Min-Max scaling for greyscale image data
def normalize_greyscale(image_data):
"""
Normalize the image data with Min-Max scaling to a range of [0.1, 0.9]
:param image_data: The image data to be normalized
:return: Normalized image data
"""
# ToDo: Implement Min-Max scaling for greyscale image data
a = 0.1
b = 0.9
x_min = np.min(image_data)
x_max = np.max(image_data)
x_prime = [a + (((x-x_min)*(b-a))/(x_max-x_min)) for x in image_data]
# print(image_data, ' normalized to ---> ', x_prime)
return np.array(x_prime)
def plot_images(X_dataset, labels, sample_size=10):
count = 0 #book keeping for plots
n_labels = len(labels)
fig = plt.figure(figsize=(sample_size, n_labels))
grid = gridspec.GridSpec(n_labels, sample_size, wspace=0.0, hspace=0.0)
labelset_pbar = tqdm(range(n_labels), desc='Sample test images', unit='labels')
for i in labelset_pbar:
ind = labels == i
subset_x = X_dataset[ind,] #get all images that belong to class i
for x in range(sample_size):
img = random.choice(subset_x) #randomly pick one image from class i
ax = plt.Subplot(fig, grid[count])
ax.set_xticks([])
ax.set_yticks([])
ax.imshow(img, cmap='gray')
fig.add_subplot(ax)
count +=1
# hide the borders
if i == (n_labels-1):
all_axes = fig.get_axes()
for ax in all_axes:
for sp in ax.spines.values():
sp.set_visible(False)
Convert to greyscale since intuitively we know there are no two traffic signs with the same design differentiated by color
In [11]:
# [Adapted from Lesson 7 - MiniFlow]
# Turn labels into numbers and apply One-Hot Encoding
train_features = normalize_greyscale(train_features)
test_features = normalize_greyscale(test_features)
num_channels = 1
In [66]:
# number of training examples
n_train = len(X_train)
# number of testing examples
n_test = len(X_test)
# Tuple with height and width of images used to reshape arrays.
image_shape = X_train.shape[1:3]
# how many classes are in the dataset
n_classes = len(np.unique(y_train))
img_size = image_shape[0]
# Images are stored in one-dimensional arrays of this length.
img_size_flat = img_size * img_size
print("Number of training examples =", n_train)
print("Number of testing examples =", n_test)
print("img_size_flat:", img_size_flat)
print("Image data shape =", image_shape)
print("Number of classes =", n_classes)
Function used to plot 9 images in a 3x3 grid, and writing the true and predicted classes below each image.
In [67]:
def plot_images1(images, cls_true, cls_pred=None):
# assert len(images) == len(cls_true)
# Create figure with 3x3 sub-plots.
fig, axes = plt.subplots(3, 3)
fig.subplots_adjust(hspace=0.3, wspace=0.3)
for i, ax in enumerate(axes.flat):
# Plot image.
ax.imshow(images[i], cmap='binary')
# Show true and predicted classes.
if cls_pred is None:
xlabel = "True: {0}".format(cls_true[i])
else:
xlabel = "True: {0}, Pred: {1}".format(cls_true[i], cls_pred[i])
# Show the classes as the label on the x-axis.
ax.set_xlabel(xlabel)
# Remove ticks from the plot.
ax.set_xticks([])
ax.set_yticks([])
# Ensure the plot is shown correctly with multiple plots
# in a single Notebook cell.
plt.show()
In [68]:
### Data exploration visualization goes here.
### Feel free to use as many code cells as needed.
In [69]:
# Get the first images from the test-set.
images = X_test[0:9]
# Get the true classes for those images.
y_true = y_test[0:9]
# Plot the images and labels using our helper-function above.
plot_images(images=images, cls_true=y_true)
Design and implement a deep learning model that learns to recognize traffic signs. Train and test your model on the German Traffic Sign Dataset.
There are various aspects to consider when thinking about this problem:
Here is an example of a published baseline model on this problem. It's not required to be familiar with the approach used in the paper but, it's good practice to try to read papers like these.
In [1]:
### Preprocess the data here.
### Feel free to use as many code cells as needed.
Answer:
In [2]:
### Generate data additional (if you want to!)
### and split the data into training/validation/testing sets here.
### Feel free to use as many code cells as needed.
Answer:
In [6]:
### Define your architecture here.
### Feel free to use as many code cells as needed.
What does your final architecture look like? (Type of model, layers, sizes, connectivity, etc.) For reference on how to build a deep neural network using TensorFlow, see Deep Neural Network in TensorFlow from the classroom.
Answer:
In [5]:
### Train your model here.
### Feel free to use as many code cells as needed.
Answer:
Answer:
Take several pictures of traffic signs that you find on the web or around you (at least five), and run them through your classifier on your computer to produce example results. The classifier might not recognize some local signs but it could prove interesting nonetheless.
You may find signnames.csv useful as it contains mappings from the class id (integer) to the actual sign name.
In [3]:
### Load the images and plot them here.
### Feel free to use as many code cells as needed.
Answer:
In [4]:
### Run the predictions here.
### Feel free to use as many code cells as needed.
Answer:
In [ ]:
### Visualize the softmax probabilities here.
### Feel free to use as many code cells as needed.
Use the model's softmax probabilities to visualize the certainty of its predictions, tf.nn.top_k could prove helpful here. Which predictions is the model certain of? Uncertain? If the model was incorrect in its initial prediction, does the correct prediction appear in the top k? (k should be 5 at most)
Answer:
Answer:
Note: Once you have completed all of the code implementations and successfully answered each question above, you may finalize your work by exporting the iPython Notebook as an HTML document. You can do this by using the menu above and navigating to \n", "File -> Download as -> HTML (.html). Include the finished document along with this notebook as your submission.
In [ ]: