def build(self, x, reuse=None):
""" TODO: define your model (2 conv layers and 2 fc layers?)
x: input image
logit: network output w/o softmax """
with tf.variable_scope('model', reuse=reuse):
W1 = tf.Variable(tf.random_normal([3, 3, 1, 32], stddev=0.01))
L1 = relu(conv2d(x, W1, strides=[1, 1, 1, 1], padding='SAME'))
L1 = max_pool(L1, ksize=[1, 2, 2, 1],
strides=[1, 2, 2, 1], padding='SAME')
W2 = tf.Variable(tf.random_normal([3, 3, 32, 64], stddev=0.01))
L2 = relu(conv2d(L1, W2, strides=[1, 1, 1, 1], padding='SAME'))
L2 = max_pool(L2, ksize=[1, 2, 2, 1],
strides=[1, 2, 2, 1], padding='SAME')
L2_flat = tf.reshape(L2, [-1, 7 * 7 * 64])
W3 = tf.get_variable("W3", shape=[7 * 7 * 64, 10],
initializer=xavier_initializer())
b = tf.Variable(tf.random_normal([10]))
logit = tf.matmul(L2_flat, W3) + b
return logit
def convolution_layer(data, nChannels, filter_size, nFilters):
kernelShape = [filter_size, filter_size, nChannels, nFilters]
weights = tensorflow.Variable(
tensorflow.truncated_normal(kernelShape, stddev=0.05))
biases = tensorflow.Variable(tensorflow.constant(0.05, shape=[nFilters]))
layer = nn.conv2d(data, weights, [1, 1, 1, 1], 'SAME')
layer = nn.bias_add(layer, biases)
layer = nn.max_pool(layer, [1, 2, 2, 1], [1, 2, 2, 1], 'SAME')
layer = nn.relu(layer)
return layer
from scipy.misc import imread, imresize
from os import listdir
from os.path import splitext
from random import seed, shuffle
from time import time
from numpy import zeros
from tensorflow import Variable, truncated_normal, constant, nn
weights = lambda shape: Variable(truncated_normal(shape, stddev=0.1))
biases = lambda shape: Variable(constant(0.1, shape=shape))
conv2d = lambda x, W: nn.conv2d(x, W, strides=[1, 2, 2, 1], padding='SAME')
max_pool = lambda x: nn.max_pool(
x, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')
def load_image(path, shape=False):
readed_img = imread(path)
if shape:
readed_img = imresize(readed_img, shape)
return readed_img
def extend_children(path, ftype=False):
allpaths = [path + '/' + child for child in listdir(path)]
if ftype != False:
# remember to include the period in ftype (ie .jpg)
# pass '' to include only folders
ret = []
for v in allpaths:
if splitext(v)[1] == ftype:
ret.append(v)
def __init__(self, h_size, env, name, LEARNING_RATE, n_step):
# The network recieves a frame from the game, flattened into an array.
# It then resizes it and processes it through four convolutional layers.
WINDOW_SIZE = env.win_size
CONV_FILTER_SIZE_X = [3, 3, 3, 3]
CONV_FILTER_SIZE_Y = [3, 3, 3, 3]
CONV_STRIDE_X = [3, 1, 1, 3]
CONV_STRIDE_Y = [3, 1, 1, 3]
CONV_LAYER_NUM = 4
CONV_FILTER_NUM = [8, 32, 32, 64]
IMAGE_SIZE = [2 * (WINDOW_SIZE + 2), 8, 3]
self.scalarInput = tf.placeholder(
shape=[None, IMAGE_SIZE[0] * IMAGE_SIZE[1] * IMAGE_SIZE[2]],
dtype=tf.float32)
self.imageIn = tf.reshape(
self.scalarInput,
shape=[-1, IMAGE_SIZE[0], IMAGE_SIZE[1], IMAGE_SIZE[2]])
depthwise_filter1 = tf.get_variable(shape=(CONV_FILTER_SIZE_X[0],
CONV_FILTER_SIZE_Y[0], 3,
1),
name=name + "_depthwise_filter1")
pointwise_filter1 = tf.get_variable(
shape=[1, 1, 3, CONV_FILTER_NUM[0]],
name=name + "_pointwise_filter1")
self.conv1 = nn.separable_conv2d(
self.imageIn,
depthwise_filter1,
pointwise_filter1,
strides=[1, CONV_STRIDE_X[0], CONV_STRIDE_Y[0], 1],
padding='SAME')
print(np.shape(self.conv1))
self.relu1 = nn.relu(self.conv1, name=name + "_relu1")
print(np.shape(self.relu1))
depthwise_filter2 = tf.get_variable(shape=(CONV_FILTER_SIZE_X[1],
CONV_FILTER_SIZE_Y[1],
CONV_FILTER_NUM[0], 1),
name=name + "_depthwise_filter2")
pointwise_filter2 = tf.get_variable(
shape=[1, 1, CONV_FILTER_NUM[0], CONV_FILTER_NUM[1]],
name=name + "_pointwise_filter2")
self.conv2 = nn.separable_conv2d(
self.relu1,
depthwise_filter2,
pointwise_filter2,
strides=[1, CONV_STRIDE_X[1], CONV_STRIDE_Y[1], 1],
padding='SAME')
print(np.shape(self.conv2))
self.relu2 = nn.relu(self.conv2, name=name + "_relu2")
print(np.shape(self.relu2))
depthwise_filter3 = tf.get_variable(shape=(CONV_FILTER_SIZE_X[2],
CONV_FILTER_SIZE_Y[2],
CONV_FILTER_NUM[1], 1),
name=name + "_depthwise_filter3")
pointwise_filter3 = tf.get_variable(
shape=[1, 1, CONV_FILTER_NUM[1], CONV_FILTER_NUM[2]],
name=name + "_pointwise_filter3")
self.conv3 = nn.separable_conv2d(
self.relu2,
depthwise_filter3,
pointwise_filter3,
strides=[1, CONV_STRIDE_X[2], CONV_STRIDE_Y[2], 1],
padding='SAME')
print(np.shape(self.conv3))
self.relu3 = nn.relu(self.conv3, name=name + "_relu3")
print(np.shape(self.relu3))
self.maxpool1 = nn.max_pool(self.relu3,
ksize=[1, 3, 1, 1],
strides=[1, 3, 1, 1],
padding='VALID')
print(np.shape(self.maxpool1))
if np.ceil(np.floor(np.ceil(2 * (WINDOW_SIZE + 2) / 3) / 3) / 3) >= 2:
conv_filter4 = tf.get_variable(
shape=(CONV_FILTER_SIZE_X[3], CONV_FILTER_SIZE_Y[3],
CONV_FILTER_NUM[2], CONV_FILTER_NUM[3]),
name=name + "_conv_filter4")
self.conv4 = nn.conv2d(
self.maxpool1,
conv_filter4,
strides=[1, CONV_STRIDE_X[3], CONV_STRIDE_Y[3], 1],
padding='SAME')
print(np.shape(self.conv4))
self.relu4 = nn.relu(self.conv4, name=name + "_relu4")
print(np.shape(self.relu4))
self.maxpool2 = nn.max_pool(self.relu4,
ksize=[1, 2, 1, 1],
strides=[1, 2, 1, 1],
padding='VALID')
LAST_CONV_FILTER = [
np.floor(
np.ceil(
np.floor(np.ceil(2 * (WINDOW_SIZE + 2) / 3) / 3) / 3) /
2), 1
]
conv_filter5 = tf.get_variable(shape=(LAST_CONV_FILTER[0],
LAST_CONV_FILTER[1],
CONV_FILTER_NUM[3], h_size),
name=name + "_conv_filter5")
self.conv5 = nn.conv2d(
self.maxpool2,
conv_filter5,
strides=[1, CONV_STRIDE_X[3], CONV_STRIDE_Y[3], 1],
padding='VALID')
print(np.shape(self.maxpool2))
else:
LAST_CONV_FILTER = [
np.floor(np.ceil(2 * (WINDOW_SIZE + 2) / 3) / 3), 3
]
conv_filter5 = tf.get_variable(shape=(LAST_CONV_FILTER[0],
LAST_CONV_FILTER[1],
CONV_FILTER_NUM[2], h_size),
name=name + "_conv_filter5")
self.conv5 = nn.conv2d(
self.maxpool1,
conv_filter5,
strides=[1, CONV_STRIDE_X[3], CONV_STRIDE_Y[3], 1],
padding='VALID')
print(np.shape(self.conv5))
self.relu5 = nn.relu(self.conv5, name=name + "_relu5")
print(np.shape(self.relu5))
# We take the output from the final convolutional layer and split it into separate advantage and value streams.
self.streamAC, self.streamVC = tf.split(self.relu5, 2, 3)
self.streamA = slim.flatten(self.streamAC)
self.streamV = slim.flatten(self.streamVC)
xavier_init = tf.contrib.layers.xavier_initializer()
self.AW = tf.Variable(xavier_init([h_size // 2, env.actions]))
self.VW = tf.Variable(xavier_init([h_size // 2, 1]))
print(self.conv5)
print(self.streamA)
print(self.AW)
self.Advantage = tf.matmul(self.streamA, self.AW)
self.Value = tf.matmul(self.streamV, self.VW)
# Then combine them together to get our final Q-values.
self.Qout = self.Value + tf.subtract(
self.Advantage,
tf.reduce_mean(self.Advantage, axis=1, keep_dims=True))
self.predict = tf.argmax(self.Qout, 1)
# Below we obtain the loss by taking the sum of squares difference between the target and prediction Q values.
self.targetQ = tf.placeholder(shape=[None], dtype=tf.float32)
self.actions = tf.placeholder(shape=[None], dtype=tf.int32)
self.actions_onehot = tf.one_hot(self.actions,
env.actions,
dtype=tf.float32)
self.Q = tf.reduce_sum(tf.multiply(self.Qout, self.actions_onehot),
axis=1)
self.td_error = tf.square(self.targetQ - self.Q)
self.loss = tf.reduce_mean(self.td_error)
self.trainer = tf.train.AdamOptimizer(learning_rate=LEARNING_RATE)
self.updateModel = self.trainer.minimize(self.loss)
def build_model(self):
with tf.name_scope('Input'):
content_img = tf.constant(self.content_img_value,
name='content_image')
style_img = tf.constant(self.style_img_value, name='style_image')
self.magical_img = tf.Variable(initial_value=content_img,
name='magical_image')
input_tensor = tf.concat([
tf.expand_dims(content_img, axis=0),
tf.expand_dims(style_img, axis=0),
tf.expand_dims(self.magical_img, axis=0)
],
axis=0)
with tf.name_scope('conv1'):
conv1_1 = relu(bias_add(
conv2d(input_tensor,
tf.constant(self.vgg16_weights['block1_conv1'][0]),
strides=[1, 1, 1, 1],
padding='SAME'), self.vgg16_weights['block1_conv1'][1]),
name='conv1_1')
conv1_2 = relu(bias_add(
conv2d(conv1_1,
tf.constant(self.vgg16_weights['block1_conv2'][0]),
strides=[1, 1, 1, 1],
padding='SAME'), self.vgg16_weights['block1_conv2'][1]),
name='conv1_2')
pool1 = max_pool(conv1_2, [1, 2, 2, 1], [1, 2, 2, 1],
'SAME',
name='pool1')
with tf.name_scope('conv2'):
conv2_1 = relu(bias_add(
conv2d(pool1,
tf.constant(self.vgg16_weights['block2_conv1'][0]),
strides=[1, 1, 1, 1],
padding='SAME'), self.vgg16_weights['block2_conv1'][1]),
name='conv2_1')
conv2_2 = relu(bias_add(
conv2d(conv2_1,
tf.constant(self.vgg16_weights['block2_conv2'][0]),
strides=[1, 1, 1, 1],
padding='SAME'), self.vgg16_weights['block2_conv2'][1]),
name='conv2_2')
pool2 = max_pool(conv2_2, [1, 2, 2, 1], [1, 2, 2, 1],
'SAME',
name='pool2')
with tf.name_scope('conv3'):
conv3_1 = relu(bias_add(
conv2d(pool2,
tf.constant(self.vgg16_weights['block3_conv1'][0]),
strides=[1, 1, 1, 1],
padding='SAME'), self.vgg16_weights['block3_conv1'][1]),
name='conv3_1')
conv3_2 = relu(bias_add(
conv2d(conv3_1,
tf.constant(self.vgg16_weights['block3_conv2'][0]),
strides=[1, 1, 1, 1],
padding='SAME'), self.vgg16_weights['block3_conv2'][1]),
name='conv3_2')
conv3_3 = relu(bias_add(
conv2d(conv3_2,
tf.constant(self.vgg16_weights['block3_conv3'][0]),
strides=[1, 1, 1, 1],
padding='SAME'), self.vgg16_weights['block3_conv3'][1]),
name='conv3_3')
pool3 = max_pool(conv3_3, [1, 2, 2, 1], [1, 2, 2, 1],
'SAME',
name='pool3')
with tf.name_scope('conv4'):
conv4_1 = relu(bias_add(
conv2d(pool3,
tf.constant(self.vgg16_weights['block4_conv1'][0]),
strides=[1, 1, 1, 1],
padding='SAME'), self.vgg16_weights['block4_conv1'][1]),
name='conv4_1')
conv4_2 = relu(bias_add(
conv2d(conv4_1,
tf.constant(self.vgg16_weights['block4_conv2'][0]),
strides=[1, 1, 1, 1],
padding='SAME'), self.vgg16_weights['block4_conv2'][1]),
name='conv4_2')
conv4_3 = relu(bias_add(
conv2d(conv4_2,
tf.constant(self.vgg16_weights['block4_conv3'][0]),
strides=[1, 1, 1, 1],
padding='SAME'), self.vgg16_weights['block4_conv3'][1]),
name='conv4_3')
pool4 = max_pool(conv4_3, [1, 2, 2, 1], [1, 2, 2, 1],
'SAME',
name='pool4')
with tf.name_scope('conv5'):
conv5_1 = relu(bias_add(
conv2d(pool4,
tf.constant(self.vgg16_weights['block5_conv1'][0]),
strides=[1, 1, 1, 1],
padding='SAME'), self.vgg16_weights['block5_conv1'][1]),
name='conv5_1')
conv5_2 = relu(bias_add(
conv2d(conv5_1,
tf.constant(self.vgg16_weights['block5_conv2'][0]),
strides=[1, 1, 1, 1],
padding='SAME'), self.vgg16_weights['block5_conv2'][1]),
name='conv5_2')
conv5_3 = relu(bias_add(
conv2d(conv5_2,
tf.constant(self.vgg16_weights['block5_conv3'][0]),
strides=[1, 1, 1, 1],
padding='SAME'), self.vgg16_weights['block5_conv3'][1]),
name='conv5_3')
pool5 = max_pool(conv5_3, [1, 2, 2, 1], [1, 2, 2, 1],
'SAME',
name='pool5')
c_loss = self.content_loss([input_tensor])
s_loss = self.style_loss([conv1_1, conv2_1, conv3_1, conv4_1, conv5_1])
self.loss = self.content_weight * c_loss + self.style_weight * s_loss
self.train_op = tf.train.AdamOptimizer(learning_rate=self.lr).minimize(
self.loss)
if self.graph_write:
writer = tf.summary.FileWriter('logs',
graph=tf.get_default_graph())
writer.flush()
writer.close()
def implement(self, x):
return nn.max_pool(x,
ksize=[1, self.size[0], self.size[1], 1],
strides=self.strides,
padding=self.padding)
def build_model(training=True):
depth = config.depth[config.versions.index(config.version)]
width = config.width[config.versions.index(config.version)]
inputs = layers.Input([config.image_size, config.image_size, 3])
x = nn.space_to_depth(inputs, 2)
x = conv(x, int(round(width * 64)), 3)
x = conv(x, int(round(width * 128)), 3, 2)
x = csp(x, int(round(width * 128)), int(round(depth * 3)))
x = conv(x, int(round(width * 256)), 3, 2)
x = csp(x, int(round(width * 256)), int(round(depth * 9)))
x1 = x
x = conv(x, int(round(width * 512)), 3, 2)
x = csp(x, int(round(width * 512)), int(round(depth * 9)))
x2 = x
x = conv(x, int(round(width * 1024)), 3, 2)
x = conv(x, int(round(width * 512)), 1, 1)
x = layers.concatenate([
x,
nn.max_pool(x, 5, 1, 'SAME'),
nn.max_pool(x, 9, 1, 'SAME'),
nn.max_pool(x, 13, 1, 'SAME')
])
x = conv(x, int(round(width * 1024)), 1, 1)
x = csp(x, int(round(width * 1024)), int(round(depth * 3)), False)
x = conv(x, int(round(width * 512)), 1)
x3 = x
x = layers.UpSampling2D()(x)
x = layers.concatenate([x, x2])
x = csp(x, int(round(width * 512)), int(round(depth * 3)), False)
x = conv(x, int(round(width * 256)), 1)
x4 = x
x = layers.UpSampling2D()(x)
x = layers.concatenate([x, x1])
x = csp(x, int(round(width * 256)), int(round(depth * 3)), False)
p3 = layers.Conv2D(3 * (len(config.class_dict) + 5),
1,
name=f'p3_{len(config.class_dict)}',
kernel_initializer=initializer,
kernel_regularizer=l2)(x)
x = conv(x, int(round(width * 256)), 3, 2)
x = layers.concatenate([x, x4])
x = csp(x, int(round(width * 512)), int(round(depth * 3)), False)
p4 = layers.Conv2D(3 * (len(config.class_dict) + 5),
1,
name=f'p4_{len(config.class_dict)}',
kernel_initializer=initializer,
kernel_regularizer=l2)(x)
x = conv(x, int(round(width * 512)), 3, 2)
x = layers.concatenate([x, x3])
x = csp(x, int(round(width * 1024)), int(round(depth * 3)), False)
p5 = layers.Conv2D(3 * (len(config.class_dict) + 5),
1,
name=f'p5_{len(config.class_dict)}',
kernel_initializer=initializer,
kernel_regularizer=l2)(x)
if training:
return tf.keras.Model(inputs, [p5, p4, p3])
else:
return tf.keras.Model(inputs, Predict()([p5, p4, p3]))
def apply_max_pool(self, x, k_size, stride_size):
return nn.max_pool(x,
k_size=[1, k_size, k_size, 1],
strides=[1, stride_size, stride_size, 1],
padding='SAME')