-
Notifications
You must be signed in to change notification settings - Fork 0
/
cnn_utils.py
executable file
·180 lines (144 loc) · 6.2 KB
/
cnn_utils.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
import math
import numpy as np
import h5py
import matplotlib.pyplot as plt
import tensorflow as tf
from tensorflow.python.framework import ops
def load_happy_dataset():
train_dataset = h5py.File('datasets/train_happy.h5', "r")
train_set_x_orig = np.array(train_dataset["train_set_x"][:]) # your train set features
train_set_y_orig = np.array(train_dataset["train_set_y"][:]) # your train set labels
test_dataset = h5py.File('datasets/test_happy.h5', "r")
test_set_x_orig = np.array(test_dataset["test_set_x"][:]) # your test set features
test_set_y_orig = np.array(test_dataset["test_set_y"][:]) # your test set labels
classes = np.array(test_dataset["list_classes"][:]) # the list of classes
train_set_y_orig = train_set_y_orig.reshape((1, train_set_y_orig.shape[0]))
test_set_y_orig = test_set_y_orig.reshape((1, test_set_y_orig.shape[0]))
return train_set_x_orig, train_set_y_orig, test_set_x_orig, test_set_y_orig, classes
def load_signs_dataset():
train_dataset = h5py.File('datasets/train_signs.h5', "r")
train_set_x_orig = np.array(train_dataset["train_set_x"][:]) # your train set features
train_set_y_orig = np.array(train_dataset["train_set_y"][:]) # your train set labels
test_dataset = h5py.File('datasets/test_signs.h5', "r")
test_set_x_orig = np.array(test_dataset["test_set_x"][:]) # your test set features
test_set_y_orig = np.array(test_dataset["test_set_y"][:]) # your test set labels
classes = np.array(test_dataset["list_classes"][:]) # the list of classes
train_set_y_orig = train_set_y_orig.reshape((1, train_set_y_orig.shape[0]))
test_set_y_orig = test_set_y_orig.reshape((1, test_set_y_orig.shape[0]))
return train_set_x_orig, train_set_y_orig, test_set_x_orig, test_set_y_orig, classes
def random_mini_batches(X, Y, mini_batch_size=64, seed=0):
"""
Creates a list of random minibatches from (X, Y)
Arguments:
X -- input data, of shape (input size, number of examples) (m, Hi, Wi, Ci)
Y -- true "label" vector (containing 0 if cat, 1 if non-cat), of shape (1, number of examples) (m, n_y)
mini_batch_size - size of the mini-batches, integer
seed -- this is only for the purpose of grading, so that you're "random minibatches are the same as ours.
Returns:
mini_batches -- list of synchronous (mini_batch_X, mini_batch_Y)
"""
m = X.shape[0] # number of training examples
mini_batches = []
np.random.seed(seed)
# Step 1: Shuffle (X, Y)
permutation = list(np.random.permutation(m))
shuffled_X = X[permutation, :, :, :]
shuffled_Y = Y[permutation, :]
# Step 2: Partition (shuffled_X, shuffled_Y). Minus the end case.
# number of mini batches of size mini_batch_size in your partitionning
num_complete_minibatches = math.floor(m/mini_batch_size)
for k in range(0, num_complete_minibatches):
mini_batch_X = shuffled_X[k * mini_batch_size: k *
mini_batch_size + mini_batch_size, :, :, :]
mini_batch_Y = shuffled_Y[k * mini_batch_size: k *
mini_batch_size + mini_batch_size, :]
mini_batch = (mini_batch_X, mini_batch_Y)
mini_batches.append(mini_batch)
# Handling the end case (last mini-batch < mini_batch_size)
if m % mini_batch_size != 0:
mini_batch_X = shuffled_X[num_complete_minibatches *
mini_batch_size: m, :, :, :]
mini_batch_Y = shuffled_Y[num_complete_minibatches *
mini_batch_size: m, :]
mini_batch = (mini_batch_X, mini_batch_Y)
mini_batches.append(mini_batch)
return mini_batches
def convert_to_one_hot(Y, C):
Y = np.eye(C)[Y.reshape(-1)].T
return Y
def forward_propagation_for_predict(X, parameters):
"""
Implements the forward propagation for the model: LINEAR -> RELU -> LINEAR -> RELU -> LINEAR -> SOFTMAX
Arguments:
X -- input dataset placeholder, of shape (input size, number of examples)
parameters -- python dictionary containing your parameters "W1", "b1", "W2", "b2", "W3", "b3"
the shapes are given in initialize_parameters
Returns:
Z3 -- the output of the last LINEAR unit
"""
# Retrieve the parameters from the dictionary "parameters"
W1 = parameters['W1']
b1 = parameters['b1']
W2 = parameters['W2']
b2 = parameters['b2']
W3 = parameters['W3']
b3 = parameters['b3']
# Numpy Equivalents:
# Z1 = np.dot(W1, X) + b1
Z1 = tf.add(tf.matmul(W1, X), b1)
A1 = tf.nn.relu(Z1) # A1 = relu(Z1)
# Z2 = np.dot(W2, a1) + b2
Z2 = tf.add(tf.matmul(W2, A1), b2)
A2 = tf.nn.relu(Z2) # A2 = relu(Z2)
# Z3 = np.dot(W3,Z2) + b3
Z3 = tf.add(tf.matmul(W3, A2), b3)
return Z3
def predict(X, parameters):
W1 = tf.convert_to_tensor(parameters["W1"])
b1 = tf.convert_to_tensor(parameters["b1"])
W2 = tf.convert_to_tensor(parameters["W2"])
b2 = tf.convert_to_tensor(parameters["b2"])
W3 = tf.convert_to_tensor(parameters["W3"])
b3 = tf.convert_to_tensor(parameters["b3"])
params = {"W1": W1,
"b1": b1,
"W2": W2,
"b2": b2,
"W3": W3,
"b3": b3}
x = tf.placeholder("float", [12288, 1])
z3 = forward_propagation_for_predict(x, params)
p = tf.argmax(z3)
sess = tf.Session()
prediction = sess.run(p, feed_dict={x: X})
return prediction
# def predict(X, parameters):
#
# W1 = tf.convert_to_tensor(parameters["W1"])
# b1 = tf.convert_to_tensor(parameters["b1"])
# W2 = tf.convert_to_tensor(parameters["W2"])
# b2 = tf.convert_to_tensor(parameters["b2"])
## W3 = tf.convert_to_tensor(parameters["W3"])
## b3 = tf.convert_to_tensor(parameters["b3"])
#
# params = {"W1": W1,
# "b1": b1,
# "W2": W2,
# "b2": b2,
# "W3": W3,
# "b3": b3}
#
# params = {"W1": W1,
# "b1": b1,
# "W2": W2,
# "b2": b2}
#
# x = tf.placeholder("float", [12288, 1])
#
# z3 = forward_propagation(x, params)
# p = tf.argmax(z3)
#
# with tf.Session() as sess:
# prediction = sess.run(p, feed_dict = {x: X})
#
# return prediction