def inference(images, keep_conv, keep_hidden):
'''
アーキテクチャの定義、グラフのビルド
'''
# spatial transformer
reshape = tf.reshape(images, [-1, 1600])
with tf.variable_scope('spatial_transformer') as scope:
weights_loc1 = _variable_with_weight_decay('weights_loc1',
shape=[1600, 20],
stddev=0.01,
wd=0.0)
biases_loc1 = _variable_on_cpu('biases_loc1', [20],
tf.constant_initializer(0.1))
weights_loc2 = _variable_with_weight_decay('weights_loc2',
shape=[20, 6],
stddev=0.01,
wd=0.0)
initial = np.array([[1., 0, 0], [0, 1., 0]
]) # Use identity transformation as starting point
initial = initial.astype('float32')
initial = initial.flatten()
biases_loc2 = tf.Variable(initial_value=initial, name='biases_loc2')
# define the two layer localisation network
h_fc_loc1 = tf.nn.tanh(tf.matmul(reshape, weights_loc1) + biases_loc1)
# We can add dropout for regularizing and to reduce overfitting like so:
h_fc_loc1_drop = tf.nn.dropout(h_fc_loc1, keep_conv)
# Second layer
h_fc_loc2 = tf.nn.tanh(
tf.matmul(h_fc_loc1_drop, weights_loc2) + biases_loc2)
# Transformer layer
hidden_trans = spatial.transformer(images,
h_fc_loc2,
downsample_factor=1)
_activation_summary(hidden_trans)
# conv1
with tf.variable_scope('conv1') as scope:
kernel = _variable_with_weight_decay(
'weights',
shape=[3, 3, 1, 16],
stddev=0.01,
wd=0.0 # not use weight decay
)
conv = tf.nn.conv2d(hidden_trans, kernel, [1, 2, 2, 1], padding='SAME')
conv1 = tf.nn.relu(conv, name=scope.name)
_activation_summary(conv1)
# conv2
with tf.variable_scope('conv2') as scope:
kernel = _variable_with_weight_decay(
'weights',
shape=[3, 3, 16, 16],
stddev=0.01,
wd=0.0 # not use weight decay
)
conv = tf.nn.conv2d(conv1, kernel, [1, 2, 2, 1], padding='SAME')
biases = _variable_on_cpu('biases', [16], tf.constant_initializer(0.1))
bias = tf.nn.bias_add(conv, biases)
conv2 = tf.nn.relu(bias, name=scope.name)
_activation_summary(conv2)
# local3 fc
with tf.variable_scope('local3') as scope:
reshape = tf.reshape(conv2, [-1, 10 * 10 * 16])
reshape = tf.nn.dropout(reshape, keep_conv)
weights = _variable_with_weight_decay('weights',
shape=[10 * 10 * 16, 1024],
stddev=0.01,
wd=0.04)
biases = _variable_on_cpu('biases', [1024],
tf.constant_initializer(0.1))
local3 = tf.nn.relu(
tf.add(tf.matmul(reshape, weights), biases, name=scope.name))
_activation_summary(local3)
dropout3 = tf.nn.dropout(local3, keep_hidden)
# softmax
with tf.variable_scope('softmax_linear') as scope:
weights = _variable_with_weight_decay('weights', [1024, NUM_CLASSES],
stddev=0.01,
wd=0.0)
biases = _variable_on_cpu('biases', [NUM_CLASSES],
tf.constant_initializer(0.1))
softmax_linear = tf.add(tf.matmul(dropout3, weights),
biases,
name=scope.name)
_activation_summary(softmax_linear)
return softmax_linear
def inference(images, keep_conv, keep_hidden):
'''
アーキテクチャの定義、グラフのビルド
'''
# spatial transformer
reshape = tf.reshape(images, [-1, 224 * 224 * 3])
with tf.variable_scope('spatial_transformer') as scope:
# localisation net
weights_loc1 = _variable_with_weight_decay('weights_loc1',
shape=[224 * 224 * 3, 20],
stddev=0.01,
wd=0.0)
biases_loc1 = _variable_on_gpu('biases_loc1', [20],
tf.constant_initializer(0.1))
# output 6 dimentional vector to compute sampling grid
weights_loc2 = _variable_with_weight_decay('weights_loc2',
shape=[20, 6],
stddev=0.01,
wd=0.0)
# Use identity transformation as starting point
initial = np.array([[1., 0, 0], [0, 1., 0]])
initial = initial.astype('float32')
initial = initial.flatten()
biases_loc2 = tf.Variable(initial_value=initial, name='biases_loc2')
# define the two layer localisation network
h_fc_loc1 = tf.nn.tanh(tf.matmul(reshape, weights_loc1) + biases_loc1)
# We can add dropout for regularizing and to reduce overfitting like so:
h_fc_loc1_drop = tf.nn.dropout(h_fc_loc1, keep_conv)
# Second layer
h_fc_loc2 = tf.nn.tanh(
tf.matmul(h_fc_loc1_drop, weights_loc2) + biases_loc2)
# Transformer layer
hidden_trans = spatial.transformer(images,
h_fc_loc2,
downsample_factor=1)
_activation_summary(hidden_trans)
print "=" * 100
print images.get_shape()
print "=" * 100
# conv1
with tf.variable_scope('conv1') as scope:
kernel = _variable_with_weight_decay(
'weights',
shape=[11, 11, 3, 64],
stddev=0.01,
wd=0.0 # not use weight decay
)
conv = tf.nn.conv2d(hidden_trans, kernel, [1, 4, 4, 1], padding='SAME')
biases = _variable_on_gpu('biases', [64], tf.constant_initializer(0.1))
bias = tf.nn.bias_add(conv, biases)
conv1 = tf.nn.relu(bias, name=scope.name)
_activation_summary(conv1)
print "=" * 100
print conv1.get_shape()
print "=" * 100
# pool1 kernel 3x3, stride 2, output_map 27x27x64
pool1 = tf.nn.max_pool(conv1,
ksize=[1, 3, 3, 1],
strides=[1, 2, 2, 1],
padding='VALID',
name='pool1')
# norm1 kernel 5x5 stride 1, output_map 27x27x64
norm1 = tf.nn.local_response_normalization(pool1,
5,
bias=1.0,
alpha=2e-05,
beta=0.75,
name='norm1')
print "=" * 100
print norm1.get_shape()
print "=" * 100
# conv2 kernel 5x5, stride 1, output_map 27x27x192, af ReLu
with tf.variable_scope('conv2') as scope:
kernel = _variable_with_weight_decay(
'weights',
shape=[5, 5, 64, 192],
stddev=0.01,
wd=0.0 # not use weight decay
)
conv = tf.nn.conv2d(norm1, kernel, [1, 1, 1, 1], padding='SAME')
biases = _variable_on_gpu('biases', [192],
tf.constant_initializer(0.1))
bias = tf.nn.bias_add(conv, biases)
conv2 = tf.nn.relu(bias, name=scope.name)
_activation_summary(conv2)
print "=" * 100
print conv2.get_shape()
print "=" * 100
# pool2 kernel 3x3, stride 2, output_map 13x13x256
pool2 = tf.nn.max_pool(conv2,
ksize=[1, 3, 3, 1],
strides=[1, 2, 2, 1],
padding='VALID',
name='pool2')
# norm2 kernel 5x5, stride 1, output_map 13x13x256
norm2 = tf.nn.local_response_normalization(pool2,
5,
bias=1.0,
alpha=2e-05,
beta=0.75,
name='norm2')
# conv3 kernel 3x3, stride 1, output_map 13x13x384
with tf.variable_scope('conv3') as scope:
kernel = _variable_with_weight_decay('weights',
shape=[3, 3, 192, 384],
stddev=1e-4,
wd=0.0)
conv = tf.nn.conv2d(norm2, kernel, [1, 1, 1, 1], padding='SAME')
biases = _variable_on_gpu('biases', [384],
tf.constant_initializer(0.1))
bias = tf.nn.bias_add(conv, biases)
conv3 = tf.nn.relu(bias, name=scope.name)
_activation_summary(conv3)
# conv4 kernel 3x3, stride 1, output_map 13x13x384
with tf.variable_scope('conv4') as scope:
kernel = _variable_with_weight_decay('weights',
shape=[3, 3, 384, 384],
stddev=1e-4,
wd=0.0)
conv = tf.nn.conv2d(conv3, kernel, [1, 1, 1, 1], padding='SAME')
biases = _variable_on_gpu('biases', [384],
tf.constant_initializer(0.1))
bias = tf.nn.bias_add(conv, biases)
conv4 = tf.nn.relu(bias, name=scope.name)
_activation_summary(conv4)
# conv5 kernel 3x3, stride 1, output_map 13x13x256
with tf.variable_scope('conv5') as scope:
kernel = _variable_with_weight_decay('weights',
shape=[3, 3, 384, 256],
stddev=1e-4,
wd=0.0)
conv = tf.nn.conv2d(conv4, kernel, [1, 1, 1, 1], padding='SAME')
biases = _variable_on_gpu('biases', [256],
tf.constant_initializer(0.1))
bias = tf.nn.bias_add(conv, biases)
conv5 = tf.nn.relu(bias, name=scope.name)
_activation_summary(conv5)
print "=" * 100
print conv5.get_shape()
print "=" * 100
# pool5 kernel 3x3, stride 2, output_map 6x6x256
pool5 = tf.nn.max_pool(conv5,
ksize=[1, 3, 3, 1],
strides=[1, 2, 2, 1],
padding='VALID',
name='pool5')
# fc6 output_map 1x1x4096
with tf.variable_scope('fc6'):
input_shape = pool5.get_shape()
pool5_flat = tf.reshape(pool5, [-1, 6 * 6 * 256])
weights = _variable_with_weight_decay('weights', [6 * 6 * 256, 4096],
stddev=0.01,
wd=0.04)
biases = _variable_on_gpu('biases', 4096, tf.constant_initializer(0.1))
fc6 = tf.nn.relu_layer(pool5_flat, weights, biases, name=scope.name)
_activation_summary(fc6)
# fc6_dropout dropout
fc6_dropout = tf.nn.dropout(fc6, keep_hidden)
# fc7 output_map 1x1x4096
with tf.variable_scope('fc7'):
input_shape = fc6_dropout.get_shape()
inputs_fc7, dim = (fc6_dropout, int(input_shape[-1]))
weights = _variable_with_weight_decay('weights', [4096, 4096],
stddev=0.01,
wd=0.04)
biases = _variable_on_gpu('biases', 4096, tf.constant_initializer(0.1))
fc7 = tf.nn.relu_layer(inputs_fc7, weights, biases, name=scope.name)
_activation_summary(fc7)
# fc7_dropout dropout
fc7_dropout = tf.nn.dropout(fc7, keep_hidden)
# fc8(softmax) output_map 1x1xNUM_CLASSES
with tf.variable_scope('softmax_linear') as scope:
weights = _variable_with_weight_decay('weights', [4096, NUM_CLASSES],
stddev=0.01,
wd=0.04)
biases = _variable_on_gpu('biases', [NUM_CLASSES],
tf.constant_initializer(0.1))
softmax_linear = tf.nn.xw_plus_b(fc7_dropout,
weights,
biases,
name=scope.name)
_activation_summary(softmax_linear)
return softmax_linear, hidden_trans
def inference(images, keep_conv, keep_hidden):
'''
アーキテクチャの定義、グラフのビルド
'''
# spatial transformer
reshape = tf.reshape(images, [-1, 224*224*3])
with tf.variable_scope('spatial_transformer') as scope:
# localisation net
weights_loc1 = _variable_with_weight_decay(
'weights_loc1',
shape=[224*224*3, 20],
stddev=0.01,
wd=0.0
)
biases_loc1 = _variable_on_gpu('biases_loc1', [20], tf.constant_initializer(0.1))
# output 6 dimentional vector to compute sampling grid
weights_loc2 = _variable_with_weight_decay(
'weights_loc2',
shape=[20, 6],
stddev=0.01,
wd=0.0
)
# Use identity transformation as starting point
initial = np.array([[1., 0, 0], [0, 1., 0]])
initial = initial.astype('float32')
initial = initial.flatten()
biases_loc2 = tf.Variable(initial_value=initial, name='biases_loc2')
# define the two layer localisation network
h_fc_loc1 = tf.nn.tanh(tf.matmul(reshape, weights_loc1) + biases_loc1)
# We can add dropout for regularizing and to reduce overfitting like so:
h_fc_loc1_drop = tf.nn.dropout(h_fc_loc1, keep_conv)
# Second layer
h_fc_loc2 = tf.nn.tanh(tf.matmul(h_fc_loc1_drop, weights_loc2) + biases_loc2)
# Transformer layer
hidden_trans = spatial.transformer(images, h_fc_loc2, downsample_factor=1)
_activation_summary(hidden_trans)
print "="*100
print images.get_shape()
print "="*100
# conv1
with tf.variable_scope('conv1') as scope:
kernel = _variable_with_weight_decay(
'weights',
shape=[11, 11, 3, 64],
stddev=0.01,
wd=0.0 # not use weight decay
)
conv = tf.nn.conv2d(hidden_trans, kernel, [1, 4, 4, 1], padding='SAME')
biases = _variable_on_gpu('biases', [64], tf.constant_initializer(0.1))
bias = tf.nn.bias_add(conv, biases)
conv1 = tf.nn.relu(bias, name=scope.name)
_activation_summary(conv1)
print "="*100
print conv1.get_shape()
print "="*100
# pool1 kernel 3x3, stride 2, output_map 27x27x64
pool1 = tf.nn.max_pool(conv1, ksize=[1, 3, 3, 1], strides=[1, 2, 2, 1], padding='VALID', name='pool1')
# norm1 kernel 5x5 stride 1, output_map 27x27x64
norm1 = tf.nn.local_response_normalization(pool1, 5, bias=1.0, alpha=2e-05, beta=0.75, name='norm1')
print "="*100
print norm1.get_shape()
print "="*100
# conv2 kernel 5x5, stride 1, output_map 27x27x192, af ReLu
with tf.variable_scope('conv2') as scope:
kernel = _variable_with_weight_decay(
'weights',
shape=[5, 5, 64, 192],
stddev=0.01,
wd=0.0 # not use weight decay
)
conv = tf.nn.conv2d(norm1, kernel, [1, 1, 1, 1], padding='SAME')
biases = _variable_on_gpu('biases', [192], tf.constant_initializer(0.1))
bias = tf.nn.bias_add(conv, biases)
conv2 = tf.nn.relu(bias, name=scope.name)
_activation_summary(conv2)
print "="*100
print conv2.get_shape()
print "="*100
# pool2 kernel 3x3, stride 2, output_map 13x13x256
pool2 = tf.nn.max_pool(conv2, ksize=[1, 3, 3, 1], strides=[1, 2, 2, 1], padding='VALID', name='pool2')
# norm2 kernel 5x5, stride 1, output_map 13x13x256
norm2 = tf.nn.local_response_normalization(pool2, 5, bias=1.0, alpha=2e-05, beta=0.75, name='norm2')
# conv3 kernel 3x3, stride 1, output_map 13x13x384
with tf.variable_scope('conv3') as scope:
kernel = _variable_with_weight_decay(
'weights',
shape=[3, 3, 192, 384],
stddev=1e-4,
wd=0.0)
conv = tf.nn.conv2d(norm2, kernel, [1, 1, 1, 1], padding='SAME')
biases = _variable_on_gpu('biases', [384], tf.constant_initializer(0.1))
bias = tf.nn.bias_add(conv, biases)
conv3 = tf.nn.relu(bias, name=scope.name)
_activation_summary(conv3)
# conv4 kernel 3x3, stride 1, output_map 13x13x384
with tf.variable_scope('conv4') as scope:
kernel = _variable_with_weight_decay(
'weights',
shape=[3, 3, 384, 384],
stddev=1e-4,
wd=0.0)
conv = tf.nn.conv2d(conv3, kernel, [1, 1, 1, 1], padding='SAME')
biases = _variable_on_gpu('biases', [384], tf.constant_initializer(0.1))
bias = tf.nn.bias_add(conv, biases)
conv4 = tf.nn.relu(bias, name=scope.name)
_activation_summary(conv4)
# conv5 kernel 3x3, stride 1, output_map 13x13x256
with tf.variable_scope('conv5') as scope:
kernel = _variable_with_weight_decay(
'weights',
shape=[3, 3, 384, 256],
stddev=1e-4,
wd=0.0)
conv = tf.nn.conv2d(conv4, kernel, [1, 1, 1, 1], padding='SAME')
biases = _variable_on_gpu('biases', [256], tf.constant_initializer(0.1))
bias = tf.nn.bias_add(conv, biases)
conv5 = tf.nn.relu(bias, name=scope.name)
_activation_summary(conv5)
print "="*100
print conv5.get_shape()
print "="*100
# pool5 kernel 3x3, stride 2, output_map 6x6x256
pool5 = tf.nn.max_pool(conv5, ksize=[1, 3, 3, 1], strides=[1, 2, 2, 1], padding='VALID', name='pool5')
# fc6 output_map 1x1x4096
with tf.variable_scope('fc6'):
input_shape = pool5.get_shape()
pool5_flat = tf.reshape(pool5, [-1, 6*6*256])
weights = _variable_with_weight_decay(
'weights',
[6*6*256, 4096],
stddev=0.01,
wd=0.04)
biases = _variable_on_gpu('biases', 4096, tf.constant_initializer(0.1))
fc6 = tf.nn.relu_layer(pool5_flat, weights, biases, name=scope.name)
_activation_summary(fc6)
# fc6_dropout dropout
fc6_dropout = tf.nn.dropout(fc6, keep_hidden)
# fc7 output_map 1x1x4096
with tf.variable_scope('fc7'):
input_shape = fc6_dropout.get_shape()
inputs_fc7, dim = (fc6_dropout, int(input_shape[-1]))
weights = _variable_with_weight_decay(
'weights',
[4096, 4096],
stddev=0.01,
wd=0.04)
biases = _variable_on_gpu('biases', 4096, tf.constant_initializer(0.1))
fc7 = tf.nn.relu_layer(inputs_fc7, weights, biases, name=scope.name)
_activation_summary(fc7)
# fc7_dropout dropout
fc7_dropout = tf.nn.dropout(fc7, keep_hidden)
# fc8(softmax) output_map 1x1xNUM_CLASSES
with tf.variable_scope('softmax_linear') as scope:
weights = _variable_with_weight_decay(
'weights',
[4096, NUM_CLASSES],
stddev=0.01,
wd=0.04)
biases = _variable_on_gpu('biases', [NUM_CLASSES], tf.constant_initializer(0.1))
softmax_linear = tf.nn.xw_plus_b(fc7_dropout, weights, biases, name=scope.name)
_activation_summary(softmax_linear)
return softmax_linear, hidden_trans
def inference(images, keep_conv, keep_hidden):
'''
アーキテクチャの定義、グラフのビルド
'''
# spatial transformer
reshape = tf.reshape(images, [-1, 1600])
with tf.variable_scope('spatial_transformer') as scope:
weights_loc1 = _variable_with_weight_decay(
'weights_loc1',
shape=[1600, 20],
stddev=0.01,
wd=0.0
)
biases_loc1 = _variable_on_cpu('biases_loc1', [20], tf.constant_initializer(0.1))
weights_loc2 = _variable_with_weight_decay(
'weights_loc2',
shape=[20, 6],
stddev=0.01,
wd=0.0
)
initial = np.array([[1., 0, 0], [0, 1., 0]]) # Use identity transformation as starting point
initial = initial.astype('float32')
initial = initial.flatten()
biases_loc2 = tf.Variable(initial_value=initial, name='biases_loc2')
# define the two layer localisation network
h_fc_loc1 = tf.nn.tanh(tf.matmul(reshape, weights_loc1) + biases_loc1)
# We can add dropout for regularizing and to reduce overfitting like so:
h_fc_loc1_drop = tf.nn.dropout(h_fc_loc1, keep_conv)
# Second layer
h_fc_loc2 = tf.nn.tanh(tf.matmul(h_fc_loc1_drop, weights_loc2) + biases_loc2)
# Transformer layer
hidden_trans = spatial.transformer(images, h_fc_loc2, downsample_factor=1)
_activation_summary(hidden_trans)
# conv1
with tf.variable_scope('conv1') as scope:
kernel = _variable_with_weight_decay(
'weights',
shape=[3, 3, 1, 16],
stddev=0.01,
wd=0.0 # not use weight decay
)
conv = tf.nn.conv2d(hidden_trans, kernel, [1, 2, 2, 1], padding='SAME')
conv1 = tf.nn.relu(conv, name=scope.name)
_activation_summary(conv1)
# conv2
with tf.variable_scope('conv2') as scope:
kernel = _variable_with_weight_decay(
'weights',
shape=[3, 3, 16, 16],
stddev=0.01,
wd=0.0 # not use weight decay
)
conv = tf.nn.conv2d(conv1, kernel, [1, 2, 2, 1], padding='SAME')
biases = _variable_on_cpu('biases', [16], tf.constant_initializer(0.1))
bias = tf.nn.bias_add(conv, biases)
conv2 = tf.nn.relu(bias, name=scope.name)
_activation_summary(conv2)
# local3 fc
with tf.variable_scope('local3') as scope:
reshape = tf.reshape(conv2, [-1, 10*10*16])
reshape = tf.nn.dropout(reshape, keep_conv)
weights = _variable_with_weight_decay(
'weights',
shape=[10*10*16, 1024],
stddev=0.01,
wd=0.04
)
biases = _variable_on_cpu('biases', [1024], tf.constant_initializer(0.1))
local3 = tf.nn.relu(tf.add(tf.matmul(reshape, weights), biases, name=scope.name))
_activation_summary(local3)
dropout3 = tf.nn.dropout(local3, keep_hidden)
# softmax
with tf.variable_scope('softmax_linear') as scope:
weights = _variable_with_weight_decay(
'weights',
[1024, NUM_CLASSES],
stddev=0.01,
wd=0.0
)
biases = _variable_on_cpu('biases', [NUM_CLASSES], tf.constant_initializer(0.1))
softmax_linear = tf.add(tf.matmul(dropout3, weights), biases, name=scope.name)
_activation_summary(softmax_linear)
return softmax_linear