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.
In [1]:
# Load pickled data
import pickle
# TODO: Fill this in based on where you saved the training and testing data
training_file = 'train.p'
testing_file = '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)
X_train, y_train = train['features'], train['labels']
X_test, y_test = test['features'], test['labels']
The pickled data is a dictionary with 4 key/value pairs:
'features' is a 4D array containing raw pixel data of the traffic sign images, (num examples, width, height, channels).'labels' is a 2D array containing the label/class id of the traffic sign. The file signnames.csv contains id -> name mappings for each id.'sizes' is a list containing tuples, (width, height) representing the the original width and height the image.'coords' is a list containing tuples, (x1, y1, x2, y2) representing coordinates of a bounding box around the sign in the image. THESE COORDINATES ASSUME THE ORIGINAL IMAGE. THE PICKLED DATA CONTAINS RESIZED VERSIONS (32 by 32) OF THESE IMAGESComplete the basic data summary below.
In [2]:
### Replace each question mark with the appropriate value.
# TODO: Number of training examples
n_train = len(X_train)
# TODO: Number of testing examples.
n_test = len(X_test)
# TODO: What's the shape of an traffic sign image?
image_shape = X_train[0].shape
# TODO: How many unique classes/labels there are in the dataset.
n_classes = len(set(y_test))
print("Number of training examples =", n_train)
print("Number of testing examples =", n_test)
print("Image data shape =", image_shape)
print("Number of classes =", n_classes)
Visualize the German Traffic Signs Dataset using the pickled file(s). This is open ended, suggestions include: plotting traffic sign images, plotting the count of each sign, etc.
The Matplotlib examples and gallery pages are a great resource for doing visualizations in Python.
NOTE: It's recommended you start with something simple first. If you wish to do more, come back to it after you've completed the rest of the sections.
In [3]:
### Data exploration visualization goes here.
import random
import numpy as np
import matplotlib.pyplot as plt
# Visualizations will be shown in the notebook.
%matplotlib inline
index = random.randint(0, len(X_train))
image = X_train[index].squeeze()
plt.figure(figsize=(1,1))
plt.imshow(image, cmap="gray")
print(y_train[index])
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.
NOTE: The LeNet-5 implementation shown in the classroom at the end of the CNN lesson is a solid starting point. You'll have to change the number of classes and possibly the preprocessing, but aside from that it's plug and play!
In [4]:
### Preprocess the data here.
from sklearn.utils import shuffle
# Implement Min-Max scaling for image data
def normalize(image_data):
a = 0.01
b = 0.99
color_min = 0.0
color_max = 255.0
return a + ( ( (image_data - color_min) * (b - a) )/(color_max - color_min))
# Normalize train features and test features
X_train = normalize(X_train)
X_test = normalize(X_test)
X_train, y_train = shuffle(X_train, y_train)
In [5]:
from sklearn.model_selection import train_test_split
X_train = np.append(X_train, X_test, axis=0)
y_train = np.append(y_train, y_test, axis=0)
X_train, X_validation, y_train, y_validation = train_test_split(
X_train,
y_train,
test_size=0.02,
random_state=42)
Implement the LeNet-5 neural network architecture.
The LeNet architecture accepts a 32x32xC image as input, where C is the number of color channels. Since the images are color, C is 3 in this case.
Layer 1: Convolutional. The output shape should be 28x28x6.
Activation. Your choice of activation function.
Pooling. The output shape should be 14x14x6.
Layer 2: Convolutional. The output shape should be 10x10x16.
Activation. Your choice of activation function.
Pooling. The output shape should be 5x5x16.
Flatten. Flatten the output shape of the final pooling layer such that it's 1D instead of 3D. The easiest way to do is by using tf.contrib.layers.flatten, which is already imported for you.
Layer 3: Fully Connected. This should have 120 outputs.
Activation. Your choice of activation function.
Layer 4: Fully Connected. This should have 84 outputs.
Activation. Your choice of activation function.
Layer 5: Fully Connected (Logits). This should have 43 outputs.
Return the result of the 2nd fully connected layer.
In [6]:
from tensorflow.contrib.layers import flatten
import tensorflow as tf
model_name = 'lenet_report'
EPOCHS = 40
BATCH_SIZE = 120
def LeNet(x):
# Hyperparameters
mu = 0
sigma = 0.01
keep_prob = 1
# Layer 1: Convolutional. Input = 32x32x3. Output = 28x28x6.
conv1_W = tf.Variable(tf.truncated_normal(shape=(5, 5, 3, 6), mean = mu, stddev = sigma))
conv1_b = tf.Variable(tf.zeros(6))
conv1 = tf.nn.conv2d(x, conv1_W, strides=[1, 1, 1, 1], padding='VALID') + conv1_b
# SOLUTION: Activation.
conv1 = tf.nn.relu(conv1)
# SOLUTION: Pooling. Input = 28x28x6. Output = 14x14x6.
conv1 = tf.nn.max_pool(conv1, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='VALID')
# SOLUTION: Layer 2: Convolutional. Output = 10x10x16.
conv2_W = tf.Variable(tf.truncated_normal(shape=(5, 5, 6, 16), mean = mu, stddev = sigma))
conv2_b = tf.Variable(tf.zeros(16))
conv2 = tf.nn.conv2d(conv1, conv2_W, strides=[1, 1, 1, 1], padding='VALID') + conv2_b
# SOLUTION: Activation.
conv2 = tf.nn.relu(conv2)
# SOLUTION: Pooling. Input = 10x10x16. Output = 5x5x16.
conv2 = tf.nn.max_pool(conv2, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='VALID')
# SOLUTION: Flatten. Input = 5x5x16. Output = 400.
fc0 = flatten(conv2)
# SOLUTION: Layer 3: Fully Connected. Input = 400. Output = 120.
fc1_W = tf.Variable(tf.truncated_normal(shape=(400, 120), mean = mu, stddev = sigma))
fc1_b = tf.Variable(tf.zeros(120))
fc1 = tf.matmul(fc0, fc1_W) + fc1_b
# SOLUTION: Activation.
fc1 = tf.nn.relu(fc1)
# SOLUTION: Layer 4: Fully Connected. Input = 120. Output = 84.
fc2_W = tf.Variable(tf.truncated_normal(shape=(120, 84), mean = mu, stddev = sigma))
fc2_b = tf.Variable(tf.zeros(84))
fc2 = tf.matmul(fc1, fc2_W) + fc2_b
# SOLUTION: Activation.
fc2 = tf.nn.relu(fc2)
fc2 = tf.nn.dropout(fc2, keep_prob)
# Layer 5: Fully Connected. Input = 84. Output = 43.
fc3_W = tf.Variable(tf.truncated_normal(shape=(84, 43), mean = mu, stddev = sigma))
fc3_b = tf.Variable(tf.zeros(43))
logits = tf.matmul(fc2, fc3_W) + fc3_b
return logits
In [7]:
x = tf.placeholder(tf.float32, (None, 32, 32, 3))
y = tf.placeholder(tf.int32, (None))
one_hot_y = tf.one_hot(y, 43)
In [8]:
### Train your model here.
rate = 0.001
logits = LeNet(x)
cross_entropy = tf.nn.softmax_cross_entropy_with_logits(logits, one_hot_y)
loss_operation = tf.reduce_mean(cross_entropy)
optimizer = tf.train.AdamOptimizer(learning_rate = rate)
training_operation = optimizer.minimize(loss_operation)
correct_prediction = tf.equal(tf.argmax(logits, 1), tf.argmax(one_hot_y, 1))
accuracy_operation = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
saver = tf.train.Saver()
In [9]:
def evaluate(X_data, y_data):
num_examples = len(X_data)
total_accuracy = 0
sess = tf.get_default_session()
for offset in range(0, num_examples, BATCH_SIZE):
batch_x, batch_y = X_data[offset:offset+BATCH_SIZE], y_data[offset:offset+BATCH_SIZE]
accuracy = sess.run(accuracy_operation, feed_dict={x: batch_x, y: batch_y})
total_accuracy += (accuracy * len(batch_x))
return total_accuracy / num_examples
In [10]:
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
num_examples = len(X_train)
print("Training...")
print()
for i in range(EPOCHS):
X_train, y_train = shuffle(X_train, y_train)
for offset in range(0, num_examples, BATCH_SIZE):
end = offset + BATCH_SIZE
batch_x, batch_y = X_train[offset:end], y_train[offset:end]
sess.run(training_operation, feed_dict={x: batch_x, y: batch_y})
validation_accuracy = evaluate(X_validation, y_validation)
print("EPOCH {} ...".format(i+1))
print("Validation Accuracy = {:.3f}".format(validation_accuracy))
print()
saver.save(sess, './models/'+model_name)
print("Model saved")
Answer:
Answer:
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:
Layer 1: Convolutional. The output shape is 28x28x6.
Activation. I am using RELU activation layer.
Pooling. I am using Max Pooling which outputs the shape 14x14x6.
Layer 2: Convolutional. The output shape is 10x10x16.
Activation. I am using RELU activation layer.
Pooling. I am using Max Pooling which outputs the shape 5x5x16.
Flatten. Flatten the output shape of the final pooling layer such that it's 1D instead of 3D. I do is by using tf.contrib.layers.flatten.
Layer 3: Is a Fully Connected layer with 120 outputs.
Activation. I am using RELU activation layer.
Layer 4: Is a Fully Connected layer with 84 outputs.
Activation. I am using RELU activation layer.
Layer 5: Fully Connected (Logits) with 43 outputs.
Answer:
What approach did you take in coming up with a solution to this problem? It may have been a process of trial and error, in which case, outline the steps you took to get to the final solution and why you chose those steps. Perhaps your solution involved an already well known implementation or architecture. In this case, discuss why you think this is suitable for the current problem.
Answer:
In [11]:
with tf.Session() as sess:
print ('loading '+model_name+'...')
saver.restore(sess, './models/'+model_name)
print('loaded')
test_accuracy = evaluate(X_test, y_test)
print("Test Accuracy = {:.3f}".format(test_accuracy))
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.
Answer:
I have used 9 images (Thanks to Tyler Lanigan for the images).
A summary of the test signs and their categories is shown in the following table:
| Test Image | Sign Category |
|---|---|
| 1 | Wild Animals Crossing - ? |
| 2 | Bicycles crossing - 29 |
| 3 | Children Crossing - 28 |
| 4 | Turn Right ahead - 33 |
| 5 | Speed limit (80km/h) - 5 |
| 6 | Stop - 14 |
| 7 | General Caution - 18 |
| 8 | No Entry - 17 |
| 9 | Turn Left ahead - 34 |
In [12]:
### Load the images and plot them here.
### Feel free to use as many code cells as needed.
# load test images
from skimage import io
import numpy as np
import os
images = os.listdir("testImages/")
images.sort()
num_imgs = len(images)
test_imgs = np.uint8(np.zeros((num_imgs,32,32,3)))
labels = ['?', 29, 28, 33, 5, 14, 18, 17, 34]
for i, j in enumerate(images):
image = io.imread('./testImages/'+j)
test_imgs[i] = image
# Normalize train features and test features
test_imgs = normalize(test_imgs.reshape((-1, 32, 32, 3)).astype(np.float32))
In [13]:
import matplotlib.pyplot as plt
f, ax = plt.subplots(num_imgs, 1)
for i in range(num_imgs):
ax[i].imshow(test_imgs[i])
plt.setp(ax[i].get_xticklabels(), visible=False)
plt.setp(ax[i].get_yticklabels(), visible=False)
plt.show()
test_imgs.shape
Out[13]:
Is your model able to perform equally well on captured pictures when compared to testing on the dataset? The simplest way to do this check the accuracy of the predictions. For example, if the model predicted 1 out of 5 signs correctly, it's 20% accurate.
NOTE: You could check the accuracy manually by using signnames.csv (same directory). This file has a mapping from the class id (0-42) to the corresponding sign name. So, you could take the class id the model outputs, lookup the name in signnames.csv and see if it matches the sign from the image.
Answer:
In [17]:
import tensorflow as tf
model_name = 'lenet_report'
predictions = tf.nn.softmax(logits)
def classify_images(X_data):
sess = tf.get_default_session()
pred_vals = sess.run(predictions, feed_dict={x: X_data})
return pred_vals
with tf.Session() as sess:
print ('loading '+model_name+'...')
saver.restore(sess, './models/'+model_name)
predictions = classify_images(test_imgs)
top_k = sess.run(tf.nn.top_k(predictions, 5, sorted=True))
print("Predicted Labels:", np.argmax(predictions, 1))
print("Expected Labels: ", labels)
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)
tf.nn.top_k will return the values and indices (class ids) of the top k predictions. So if k=3, for each sign, it'll return the 3 largest probabilities (out of a possible 43) and the correspoding class ids.
Take this numpy array as an example:
# (5, 6) array
a = np.array([[ 0.24879643, 0.07032244, 0.12641572, 0.34763842, 0.07893497,
0.12789202],
[ 0.28086119, 0.27569815, 0.08594638, 0.0178669 , 0.18063401,
0.15899337],
[ 0.26076848, 0.23664738, 0.08020603, 0.07001922, 0.1134371 ,
0.23892179],
[ 0.11943333, 0.29198961, 0.02605103, 0.26234032, 0.1351348 ,
0.16505091],
[ 0.09561176, 0.34396535, 0.0643941 , 0.16240774, 0.24206137,
0.09155967]])Running it through sess.run(tf.nn.top_k(tf.constant(a), k=3)) produces:
TopKV2(values=array([[ 0.34763842, 0.24879643, 0.12789202],
[ 0.28086119, 0.27569815, 0.18063401],
[ 0.26076848, 0.23892179, 0.23664738],
[ 0.29198961, 0.26234032, 0.16505091],
[ 0.34396535, 0.24206137, 0.16240774]]), indices=array([[3, 0, 5],
[0, 1, 4],
[0, 5, 1],
[1, 3, 5],
[1, 4, 3]], dtype=int32))Looking just at the first row we get [ 0.34763842, 0.24879643, 0.12789202], you can confirm these are the 3 largest probabilities in a. You'll also notice [3, 0, 5] are the corresponding indices.
Answer:
In [18]:
N = 5
ind = np.arange(N) # the x locations for the values
for i in range(5):
plt.figure(i)
values = top_k[0][i]
plt.bar(range(N), values, 0.40, color='g')
plt.ylabel('Probabilities')
plt.xlabel('Class Labels')
plt.title('Top {} Softmax Probabilities for test-image{}'.format(N, str(i+1)))
plt.xticks(ind+0.40, tuple(top_k[1][i]))
plt.show()
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.