|
# Create an interactive Tensorflow session |
|
sess = tf.InteractiveSession() |
|
|
|
# These will be inputs for the model |
|
# Input pixels of images, flattened |
|
# 1296 = 36*36 which is the size of images |
|
x = tf.placeholder("float", [None, 1296]) |
|
## Known labels |
|
y_ = tf.placeholder("float", [None,2]) |
|
|
|
# Hidden layer 1 with 256 neurons |
|
num_hidden1 = 256 |
|
# Variables |
|
# W1 is for weights |
|
# b1 is for bias |
|
W1 = tf.Variable(tf.truncated_normal([1296,num_hidden1], |
|
stddev=1./math.sqrt(1296))) |
|
b1 = tf.Variable(tf.constant(0.1,shape=[num_hidden1])) |
|
# Compute the activation function of the weighted sum -> produce 128 intermediate value |
|
# Nonlinear transform functions - activation function: sigmoid |
|
h1 = tf.sigmoid(tf.matmul(x,W1) + b1) |
|
|
|
# Hidden Layer 2 |
|
num_hidden2 = 64 with 64 neurons |
|
W2 = tf.Variable(tf.truncated_normal([num_hidden1, |
|
num_hidden2],stddev=2./math.sqrt(num_hidden1))) |
|
b2 = tf.Variable(tf.constant(0.2,shape=[num_hidden2])) |
|
h2 = tf.sigmoid(tf.matmul(h1,W2) + b2) |
|
|
|
# Output Layer |
|
# Logistic regression again |
|
W3 = tf.Variable(tf.truncated_normal([num_hidden2, 2], |
|
stddev=1./math.sqrt(2))) |
|
b3 = tf.Variable(tf.constant(0.1,shape=[2])) |
|
|
|
# Just initialize |
|
sess.run(tf.global_variables_initializer()) |
|
|
|
# Define model |
|
y = tf.nn.softmax(tf.matmul(h2,W3) + b3) |
|
# Finish model specification, let us start training the model |
