def testCreateAvgPoolStrideSAME(self):
height, width = 3, 3
with self.test_session():
images = tf.random_uniform((5, height, width, 3), seed=1)
output = ops.avg_pool(images, [3, 3], stride=1, padding='SAME')
self.assertListEqual(output.get_shape().as_list(),
[5, height, width, 3])
def testCreateSquareAvgPool(self):
height, width = 3, 3
with self.test_session():
images = tf.random_uniform((5, height, width, 3), seed=1)
output = ops.avg_pool(images, 3)
self.assertEquals(output.op.name, 'AvgPool/AvgPool')
self.assertListEqual(output.get_shape().as_list(), [5, 1, 1, 3])
def _pool_layer(self, inputs, scope):
# self.layer_list.append("pool")
return ops.avg_pool( #try avg pool
inputs=inputs,
pool_size=self.pool_size,
padding=self.padding,
scope=scope + '/pool',
data_format=self.data_format)
def inception_v3(inputs,
dropout_keep_prob=0.8,
num_classes=1000,
is_training=True,
restore_logits=True,
scope=''):
"""Latest Inception from http://arxiv.org/abs/1512.00567.
"Rethinking the Inception Architecture for Computer Vision"
Christian Szegedy, Vincent Vanhoucke, Sergey Ioffe, Jonathon Shlens,
Zbigniew Wojna
Args:
inputs: a tensor of size [batch_size, height, width, channels].
dropout_keep_prob: dropout keep_prob.
num_classes: number of predicted classes.
is_training: whether is training or not.
restore_logits: whether or not the logits layers should be restored.
Useful for fine-tuning a model with different num_classes.
scope: Optional scope for name_scope.
Returns:
a list containing 'logits', 'aux_logits' Tensors.
"""
# end_points will collect relevant activations for external use, for example
# summaries or losses.
end_points = {}
with tf.name_scope(scope, 'inception_v3', [inputs]):
with scopes.arg_scope([ops.conv2d, ops.fc, ops.batch_norm, ops.dropout],
is_training=is_training):
with scopes.arg_scope([ops.conv2d, ops.max_pool, ops.avg_pool],
stride=1, padding='VALID'):
# 299 x 299 x 3
end_points['conv0'] = ops.conv2d(inputs, 32, [3, 3], stride=2,
scope='conv0')
# 149 x 149 x 32
end_points['conv1'] = ops.conv2d(end_points['conv0'], 32, [3, 3],
scope='conv1')
# 147 x 147 x 32
end_points['conv2'] = ops.conv2d(end_points['conv1'], 64, [3, 3],
padding='SAME', scope='conv2')
# 147 x 147 x 64
end_points['pool1'] = ops.max_pool(end_points['conv2'], [3, 3],
stride=2, scope='pool1')
# 73 x 73 x 64
end_points['conv3'] = ops.conv2d(end_points['pool1'], 80, [1, 1],
scope='conv3')
# 73 x 73 x 80.
end_points['conv4'] = ops.conv2d(end_points['conv3'], 192, [3, 3],
scope='conv4')
# 71 x 71 x 192.
end_points['pool2'] = ops.max_pool(end_points['conv4'], [3, 3],
stride=2, scope='pool2')
# 35 x 35 x 192.
net = end_points['pool2']
# Inception blocks
with scopes.arg_scope([ops.conv2d, ops.max_pool, ops.avg_pool],
stride=1, padding='SAME'):
# mixed: 35 x 35 x 256.
with tf.variable_scope('mixed_35x35x256a'):
with tf.variable_scope('branch1x1'):
branch1x1 = ops.conv2d(net, 64, [1, 1])
with tf.variable_scope('branch5x5'):
branch5x5 = ops.conv2d(net, 48, [1, 1])
branch5x5 = ops.conv2d(branch5x5, 64, [5, 5])
with tf.variable_scope('branch3x3dbl'):
branch3x3dbl = ops.conv2d(net, 64, [1, 1])
branch3x3dbl = ops.conv2d(branch3x3dbl, 96, [3, 3])
branch3x3dbl = ops.conv2d(branch3x3dbl, 96, [3, 3])
with tf.variable_scope('branch_pool'):
branch_pool = ops.avg_pool(net, [3, 3])
branch_pool = ops.conv2d(branch_pool, 32, [1, 1])
net = tf.concat(axis=3, values=[branch1x1, branch5x5, branch3x3dbl, branch_pool])
end_points['mixed_35x35x256a'] = net
# mixed_1: 35 x 35 x 288.
with tf.variable_scope('mixed_35x35x288a'):
with tf.variable_scope('branch1x1'):
branch1x1 = ops.conv2d(net, 64, [1, 1])
with tf.variable_scope('branch5x5'):
branch5x5 = ops.conv2d(net, 48, [1, 1])
branch5x5 = ops.conv2d(branch5x5, 64, [5, 5])
with tf.variable_scope('branch3x3dbl'):
branch3x3dbl = ops.conv2d(net, 64, [1, 1])
branch3x3dbl = ops.conv2d(branch3x3dbl, 96, [3, 3])
branch3x3dbl = ops.conv2d(branch3x3dbl, 96, [3, 3])
with tf.variable_scope('branch_pool'):
branch_pool = ops.avg_pool(net, [3, 3])
branch_pool = ops.conv2d(branch_pool, 64, [1, 1])
net = tf.concat(axis=3, values=[branch1x1, branch5x5, branch3x3dbl, branch_pool])
end_points['mixed_35x35x288a'] = net
# mixed_2: 35 x 35 x 288.
with tf.variable_scope('mixed_35x35x288b'):
with tf.variable_scope('branch1x1'):
branch1x1 = ops.conv2d(net, 64, [1, 1])
with tf.variable_scope('branch5x5'):
branch5x5 = ops.conv2d(net, 48, [1, 1])
branch5x5 = ops.conv2d(branch5x5, 64, [5, 5])
with tf.variable_scope('branch3x3dbl'):
branch3x3dbl = ops.conv2d(net, 64, [1, 1])
branch3x3dbl = ops.conv2d(branch3x3dbl, 96, [3, 3])
branch3x3dbl = ops.conv2d(branch3x3dbl, 96, [3, 3])
with tf.variable_scope('branch_pool'):
branch_pool = ops.avg_pool(net, [3, 3])
branch_pool = ops.conv2d(branch_pool, 64, [1, 1])
net = tf.concat(axis=3, values=[branch1x1, branch5x5, branch3x3dbl, branch_pool])
end_points['mixed_35x35x288b'] = net
# mixed_3: 17 x 17 x 768.
with tf.variable_scope('mixed_17x17x768a'):
with tf.variable_scope('branch3x3'):
branch3x3 = ops.conv2d(net, 384, [3, 3], stride=2, padding='VALID')
with tf.variable_scope('branch3x3dbl'):
branch3x3dbl = ops.conv2d(net, 64, [1, 1])
branch3x3dbl = ops.conv2d(branch3x3dbl, 96, [3, 3])
branch3x3dbl = ops.conv2d(branch3x3dbl, 96, [3, 3],
stride=2, padding='VALID')
with tf.variable_scope('branch_pool'):
branch_pool = ops.max_pool(net, [3, 3], stride=2, padding='VALID')
net = tf.concat(axis=3, values=[branch3x3, branch3x3dbl, branch_pool])
end_points['mixed_17x17x768a'] = net
# mixed4: 17 x 17 x 768.
with tf.variable_scope('mixed_17x17x768b'):
with tf.variable_scope('branch1x1'):
branch1x1 = ops.conv2d(net, 192, [1, 1])
with tf.variable_scope('branch7x7'):
branch7x7 = ops.conv2d(net, 128, [1, 1])
branch7x7 = ops.conv2d(branch7x7, 128, [1, 7])
branch7x7 = ops.conv2d(branch7x7, 192, [7, 1])
with tf.variable_scope('branch7x7dbl'):
branch7x7dbl = ops.conv2d(net, 128, [1, 1])
branch7x7dbl = ops.conv2d(branch7x7dbl, 128, [7, 1])
branch7x7dbl = ops.conv2d(branch7x7dbl, 128, [1, 7])
branch7x7dbl = ops.conv2d(branch7x7dbl, 128, [7, 1])
branch7x7dbl = ops.conv2d(branch7x7dbl, 192, [1, 7])
with tf.variable_scope('branch_pool'):
branch_pool = ops.avg_pool(net, [3, 3])
branch_pool = ops.conv2d(branch_pool, 192, [1, 1])
net = tf.concat(axis=3, values=[branch1x1, branch7x7, branch7x7dbl, branch_pool])
end_points['mixed_17x17x768b'] = net
# mixed_5: 17 x 17 x 768.
with tf.variable_scope('mixed_17x17x768c'):
with tf.variable_scope('branch1x1'):
branch1x1 = ops.conv2d(net, 192, [1, 1])
with tf.variable_scope('branch7x7'):
branch7x7 = ops.conv2d(net, 160, [1, 1])
branch7x7 = ops.conv2d(branch7x7, 160, [1, 7])
branch7x7 = ops.conv2d(branch7x7, 192, [7, 1])
with tf.variable_scope('branch7x7dbl'):
branch7x7dbl = ops.conv2d(net, 160, [1, 1])
branch7x7dbl = ops.conv2d(branch7x7dbl, 160, [7, 1])
branch7x7dbl = ops.conv2d(branch7x7dbl, 160, [1, 7])
branch7x7dbl = ops.conv2d(branch7x7dbl, 160, [7, 1])
branch7x7dbl = ops.conv2d(branch7x7dbl, 192, [1, 7])
with tf.variable_scope('branch_pool'):
branch_pool = ops.avg_pool(net, [3, 3])
branch_pool = ops.conv2d(branch_pool, 192, [1, 1])
net = tf.concat(axis=3, values=[branch1x1, branch7x7, branch7x7dbl, branch_pool])
end_points['mixed_17x17x768c'] = net
# mixed_6: 17 x 17 x 768.
with tf.variable_scope('mixed_17x17x768d'):
with tf.variable_scope('branch1x1'):
branch1x1 = ops.conv2d(net, 192, [1, 1])
with tf.variable_scope('branch7x7'):
branch7x7 = ops.conv2d(net, 160, [1, 1])
branch7x7 = ops.conv2d(branch7x7, 160, [1, 7])
branch7x7 = ops.conv2d(branch7x7, 192, [7, 1])
with tf.variable_scope('branch7x7dbl'):
branch7x7dbl = ops.conv2d(net, 160, [1, 1])
branch7x7dbl = ops.conv2d(branch7x7dbl, 160, [7, 1])
branch7x7dbl = ops.conv2d(branch7x7dbl, 160, [1, 7])
branch7x7dbl = ops.conv2d(branch7x7dbl, 160, [7, 1])
branch7x7dbl = ops.conv2d(branch7x7dbl, 192, [1, 7])
with tf.variable_scope('branch_pool'):
branch_pool = ops.avg_pool(net, [3, 3])
branch_pool = ops.conv2d(branch_pool, 192, [1, 1])
net = tf.concat(axis=3, values=[branch1x1, branch7x7, branch7x7dbl, branch_pool])
end_points['mixed_17x17x768d'] = net
# mixed_7: 17 x 17 x 768.
with tf.variable_scope('mixed_17x17x768e'):
with tf.variable_scope('branch1x1'):
branch1x1 = ops.conv2d(net, 192, [1, 1])
with tf.variable_scope('branch7x7'):
branch7x7 = ops.conv2d(net, 192, [1, 1])
branch7x7 = ops.conv2d(branch7x7, 192, [1, 7])
branch7x7 = ops.conv2d(branch7x7, 192, [7, 1])
with tf.variable_scope('branch7x7dbl'):
branch7x7dbl = ops.conv2d(net, 192, [1, 1])
branch7x7dbl = ops.conv2d(branch7x7dbl, 192, [7, 1])
branch7x7dbl = ops.conv2d(branch7x7dbl, 192, [1, 7])
branch7x7dbl = ops.conv2d(branch7x7dbl, 192, [7, 1])
branch7x7dbl = ops.conv2d(branch7x7dbl, 192, [1, 7])
with tf.variable_scope('branch_pool'):
branch_pool = ops.avg_pool(net, [3, 3])
branch_pool = ops.conv2d(branch_pool, 192, [1, 1])
net = tf.concat(axis=3, values=[branch1x1, branch7x7, branch7x7dbl, branch_pool])
end_points['mixed_17x17x768e'] = net
# Auxiliary Head logits
aux_logits = tf.identity(end_points['mixed_17x17x768e'])
with tf.variable_scope('aux_logits'):
aux_logits = ops.avg_pool(aux_logits, [5, 5], stride=3,
padding='VALID')
aux_logits = ops.conv2d(aux_logits, 128, [1, 1], scope='proj')
# Shape of feature map before the final layer.
shape = aux_logits.get_shape()
aux_logits = ops.conv2d(aux_logits, 768, shape[1:3], stddev=0.01,
padding='VALID')
aux_logits = ops.flatten(aux_logits)
aux_logits = ops.fc(aux_logits, num_classes, activation=None,
stddev=0.001, restore=restore_logits)
end_points['aux_logits'] = aux_logits
# mixed_8: 8 x 8 x 1280.
# Note that the scope below is not changed to not void previous
# checkpoints.
# (TODO) Fix the scope when appropriate.
with tf.variable_scope('mixed_17x17x1280a'):
with tf.variable_scope('branch3x3'):
branch3x3 = ops.conv2d(net, 192, [1, 1])
branch3x3 = ops.conv2d(branch3x3, 320, [3, 3], stride=2,
padding='VALID')
with tf.variable_scope('branch7x7x3'):
branch7x7x3 = ops.conv2d(net, 192, [1, 1])
branch7x7x3 = ops.conv2d(branch7x7x3, 192, [1, 7])
branch7x7x3 = ops.conv2d(branch7x7x3, 192, [7, 1])
branch7x7x3 = ops.conv2d(branch7x7x3, 192, [3, 3],
stride=2, padding='VALID')
with tf.variable_scope('branch_pool'):
branch_pool = ops.max_pool(net, [3, 3], stride=2, padding='VALID')
net = tf.concat(axis=3, values=[branch3x3, branch7x7x3, branch_pool])
end_points['mixed_17x17x1280a'] = net
# mixed_9: 8 x 8 x 2048.
with tf.variable_scope('mixed_8x8x2048a'):
with tf.variable_scope('branch1x1'):
branch1x1 = ops.conv2d(net, 320, [1, 1])
with tf.variable_scope('branch3x3'):
branch3x3 = ops.conv2d(net, 384, [1, 1])
branch3x3 = tf.concat(axis=3, values=[ops.conv2d(branch3x3, 384, [1, 3]),
ops.conv2d(branch3x3, 384, [3, 1])])
with tf.variable_scope('branch3x3dbl'):
branch3x3dbl = ops.conv2d(net, 448, [1, 1])
branch3x3dbl = ops.conv2d(branch3x3dbl, 384, [3, 3])
branch3x3dbl = tf.concat(axis=3, values=[ops.conv2d(branch3x3dbl, 384, [1, 3]),
ops.conv2d(branch3x3dbl, 384, [3, 1])])
with tf.variable_scope('branch_pool'):
branch_pool = ops.avg_pool(net, [3, 3])
branch_pool = ops.conv2d(branch_pool, 192, [1, 1])
net = tf.concat(axis=3, values=[branch1x1, branch3x3, branch3x3dbl, branch_pool])
end_points['mixed_8x8x2048a'] = net
# mixed_10: 8 x 8 x 2048.
with tf.variable_scope('mixed_8x8x2048b'):
with tf.variable_scope('branch1x1'):
branch1x1 = ops.conv2d(net, 320, [1, 1])
with tf.variable_scope('branch3x3'):
branch3x3 = ops.conv2d(net, 384, [1, 1])
branch3x3 = tf.concat(axis=3, values=[ops.conv2d(branch3x3, 384, [1, 3]),
ops.conv2d(branch3x3, 384, [3, 1])])
with tf.variable_scope('branch3x3dbl'):
branch3x3dbl = ops.conv2d(net, 448, [1, 1])
branch3x3dbl = ops.conv2d(branch3x3dbl, 384, [3, 3])
branch3x3dbl = tf.concat(axis=3, values=[ops.conv2d(branch3x3dbl, 384, [1, 3]),
ops.conv2d(branch3x3dbl, 384, [3, 1])])
with tf.variable_scope('branch_pool'):
branch_pool = ops.avg_pool(net, [3, 3])
branch_pool = ops.conv2d(branch_pool, 192, [1, 1])
net = tf.concat(axis=3, values=[branch1x1, branch3x3, branch3x3dbl, branch_pool])
end_points['mixed_8x8x2048b'] = net
# Final pooling and prediction
with tf.variable_scope('logits'):
shape = net.get_shape()
net = ops.avg_pool(net, shape[1:3], padding='VALID', scope='pool')
# 1 x 1 x 2048
net = ops.dropout(net, dropout_keep_prob, scope='dropout')
net = ops.flatten(net, scope='flatten')
# 2048
logits = ops.fc(net, num_classes, activation=None, scope='logits',
restore=restore_logits)
# 1000
end_points['logits'] = logits
end_points['predictions'] = tf.nn.softmax(logits, name='predictions')
return logits, end_points
def create_network(X, h, keep_prob, numClasses):
num_channels = X.get_shape().as_list()[-1]
res1 = new_conv_layer(inputs=X,
layer_name='res1',
stride=2,
num_inChannel=num_channels,
filter_size=4,
num_filters=32,
batch_norm=True,
use_relu=True)
#res1 = max_pool(res1, ksize=2, stride=2, name='res1_max_pool')
print('---------------------')
print('Res1')
print(res1.get_shape())
print('---------------------')
# Res2
with tf.variable_scope('Res2'):
res2a = bottleneck_block(res1,
32,
block_name='res2a',
s1=1,
k1=1,
nf1=32,
name1='res2a_branch2a',
s2=1,
k2=3,
nf2=32,
name2='res2a_branch2b',
s3=1,
k3=1,
nf3=64,
name3='res2a_branch2c',
s4=1,
k4=1,
name4='res2a_branch1',
first_block=True)
print('Res2a')
print(res2a.get_shape())
print('---------------------')
res2b = bottleneck_block(res2a,
64,
block_name='res2b',
s1=1,
k1=1,
nf1=32,
name1='res2b_branch2a',
s2=1,
k2=3,
nf2=32,
name2='res2b_branch2b',
s3=1,
k3=1,
nf3=64,
name3='res2b_branch2c',
s4=1,
k4=1,
name4='res2b_branch1',
first_block=False)
print('Res2b')
print(res2b.get_shape())
print('---------------------')
res2c = bottleneck_block(res2b,
64,
block_name='res2c',
s1=1,
k1=1,
nf1=32,
name1='res2c_branch2a',
s2=1,
k2=3,
nf2=32,
name2='res2c_branch2b',
s3=1,
k3=1,
nf3=64,
name3='res2c_branch2c',
s4=1,
k4=1,
name4='res2c_branch1',
first_block=False)
print('Res2c')
print(res2c.get_shape())
print('---------------------')
# Res3
with tf.variable_scope('Res3'):
res3a = bottleneck_block(res2c,
64,
block_name='res3a',
s1=2,
k1=1,
nf1=48,
name1='res3a_branch2a',
s2=1,
k2=3,
nf2=48,
name2='res3a_branch2b',
s3=1,
k3=1,
nf3=128,
name3='res3a_branch2c',
s4=2,
k4=1,
name4='res3a_branch1',
first_block=True)
print('Res3a')
print(res3a.get_shape())
print('---------------------')
res3b = bottleneck_block(res3a,
128,
block_name='res3b',
s1=1,
k1=1,
nf1=48,
name1='res3b_branch2a',
s2=1,
k2=3,
nf2=48,
name2='res3b_branch2b',
s3=1,
k3=1,
nf3=128,
name3='res3b_branch2c',
s4=1,
k4=1,
name4='res2b_branch1',
first_block=False)
print('Res3b')
print(res3b.get_shape())
print('---------------------')
res3c = bottleneck_block(res3b,
128,
block_name='res3c',
s1=1,
k1=1,
nf1=48,
name1='res3c_branch2a',
s2=1,
k2=3,
nf2=48,
name2='res3c_branch2b',
s3=1,
k3=1,
nf3=128,
name3='res3c_branch2c',
s4=1,
k4=1,
name4='res3c_branch1',
first_block=False)
print('Res3c')
print(res3c.get_shape())
print('---------------------')
res3d = bottleneck_block(res3c,
128,
block_name='res3d',
s1=1,
k1=1,
nf1=48,
name1='res3d_branch2a',
s2=1,
k2=3,
nf2=48,
name2='res3d_branch2b',
s3=1,
k3=1,
nf3=128,
name3='res3d_branch2c',
s4=1,
k4=1,
name4='res3d_branch1',
first_block=False)
print('Res3d')
print(res3d.get_shape())
print('---------------------')
# Res4
with tf.variable_scope('Res4'):
res4a = bottleneck_block(res3d,
128,
block_name='res4a',
s1=2,
k1=1,
nf1=64,
name1='res4a_branch2a',
s2=1,
k2=3,
nf2=64,
name2='res4a_branch2b',
s3=1,
k3=1,
nf3=256,
name3='res4a_branch2c',
s4=2,
k4=1,
name4='res4a_branch1',
first_block=True)
print('---------------------')
print('Res4a')
print(res4a.get_shape())
print('---------------------')
res4b = bottleneck_block(res4a,
256,
block_name='res4b',
s1=1,
k1=1,
nf1=64,
name1='res4b_branch2a',
s2=1,
k2=3,
nf2=64,
name2='res4b_branch2b',
s3=1,
k3=1,
nf3=256,
name3='res4b_branch2c',
s4=1,
k4=1,
name4='res4b_branch1',
first_block=False)
print('Res4b')
print(res4b.get_shape())
print('---------------------')
res4c = bottleneck_block(res4b,
256,
block_name='res4c',
s1=1,
k1=1,
nf1=64,
name1='res4c_branch2a',
s2=1,
k2=3,
nf2=64,
name2='res4c_branch2b',
s3=1,
k3=1,
nf3=256,
name3='res4c_branch2c',
s4=1,
k4=1,
name4='res4c_branch1',
first_block=False)
print('Res4c')
print(res4c.get_shape())
print('---------------------')
res4d = bottleneck_block(res4c,
256,
block_name='res4d',
s1=1,
k1=1,
nf1=64,
name1='res4d_branch2a',
s2=1,
k2=3,
nf2=64,
name2='res4d_branch2b',
s3=1,
k3=1,
nf3=256,
name3='res4d_branch2c',
s4=1,
k4=1,
name4='res4d_branch1',
first_block=False)
print('Res4d')
print(res4d.get_shape())
print('---------------------')
res4e = bottleneck_block(res4d,
256,
block_name='res4e',
s1=1,
k1=1,
nf1=64,
name1='res4e_branch2a',
s2=1,
k2=3,
nf2=64,
name2='res4e_branch2b',
s3=1,
k3=1,
nf3=256,
name3='res4e_branch2c',
s4=1,
k4=1,
name4='res4e_branch1',
first_block=False)
print('Res4e')
print(res4e.get_shape())
print('---------------------')
res4f = bottleneck_block(res4e,
256,
block_name='res4f',
s1=1,
k1=1,
nf1=64,
name1='res4f_branch2a',
s2=1,
k2=3,
nf2=64,
name2='res4f_branch2b',
s3=1,
k3=1,
nf3=256,
name3='res4f_branch2c',
s4=1,
k4=1,
name4='res4f_branch1',
first_block=False)
print('Res4f')
print(res4f.get_shape())
print('---------------------')
# Res5
with tf.variable_scope('Res5'):
res5a = bottleneck_block(res4f,
256,
block_name='res5a',
s1=1,
k1=1,
nf1=128,
name1='res5a_branch2a',
s2=1,
k2=3,
nf2=128,
name2='res5a_branch2b',
s3=1,
k3=1,
nf3=512,
name3='res5a_branch2c',
s4=1,
k4=1,
name4='res5a_branch1',
first_block=True)
print('---------------------')
print('Res5a')
print(res5a.get_shape())
print('---------------------')
res5b = bottleneck_block(res5a,
512,
block_name='res5b',
s1=1,
k1=1,
nf1=128,
name1='res5b_branch2a',
s2=1,
k2=3,
nf2=128,
name2='res5b_branch2b',
s3=1,
k3=1,
nf3=512,
name3='res5b_branch2c',
s4=1,
k4=1,
name4='res5b_branch1',
first_block=False)
print('Res5b')
print(res5b.get_shape())
print('---------------------')
res5c = bottleneck_block(res5b,
512,
block_name='res5c',
s1=1,
k1=1,
nf1=128,
name1='res5c_branch2a',
s2=1,
k2=3,
nf2=128,
name2='res5c_branch2b',
s3=1,
k3=1,
nf3=512,
name3='res5c_branch2c',
s4=1,
k4=1,
name4='res5c_branch1',
first_block=False)
print('Res5c')
print(res5c.get_shape())
res5c = avg_pool(res5c, ksize=4, stride=1, name='res5_avg_pool')
print('---------------------')
print('Res5c after AVG_POOL')
print(res5c.get_shape())
print('---------------------')
net_flatten, _ = flatten_layer(res5c)
print('---------------------')
print('Matrix dimension to the first FC layer')
print(net_flatten.get_shape())
print('---------------------')
net = fc_layer(net_flatten,
h,
'FC1',
batch_norm=True,
add_reg=True,
use_relu=True)
net = dropout(net, keep_prob)
net = fc_layer(net,
numClasses,
'FC2',
batch_norm=True,
add_reg=True,
use_relu=False)
return net
def create_network(X, numClasses, is_train):
"""
Building the Residual Network with 50 layer
:param X: input
:param h: number of units in the fully connected layer
:param keep_prob: dropout rate
:param numClasses: number of classes
:param is_train: to be used by batch normalization
:return:
"""
res1 = conv_2d(X,
layer_name='res1',
stride=2,
filter_size=7,
num_filters=64,
is_train=is_train,
batch_norm=True,
use_relu=True)
print('---------------------')
print('Res1')
print(res1.get_shape())
print('---------------------')
res1 = max_pool(res1, ksize=3, stride=2, name='res1_max_pool')
print('---------------------')
print('Res1')
print(res1.get_shape())
print('---------------------')
# Res2
with tf.variable_scope('Res2'):
res2a = bottleneck_block(res1,
is_train,
block_name='res2a',
s1=1,
k1=1,
nf1=64,
name1='res2a_branch2a',
s2=1,
k2=3,
nf2=64,
name2='res2a_branch2b',
s3=1,
k3=1,
nf3=256,
name3='res2a_branch2c',
s4=1,
k4=1,
name4='res2a_branch1',
first_block=True)
print('Res2a')
print(res2a.get_shape())
print('---------------------')
res2b = bottleneck_block(res2a,
is_train,
block_name='res2b',
s1=1,
k1=1,
nf1=64,
name1='res2b_branch2a',
s2=1,
k2=3,
nf2=64,
name2='res2b_branch2b',
s3=1,
k3=1,
nf3=256,
name3='res2b_branch2c',
s4=1,
k4=1,
name4='res2b_branch1',
first_block=False)
print('Res2b')
print(res2b.get_shape())
print('---------------------')
res2c = bottleneck_block(res2b,
is_train,
block_name='res2c',
s1=1,
k1=1,
nf1=64,
name1='res2c_branch2a',
s2=1,
k2=3,
nf2=64,
name2='res2c_branch2b',
s3=1,
k3=1,
nf3=256,
name3='res2c_branch2c',
s4=1,
k4=1,
name4='res2c_branch1',
first_block=False)
print('Res2c')
print(res2c.get_shape())
print('---------------------')
# Res3
with tf.variable_scope('Res3'):
res3a = bottleneck_block(res2c,
is_train,
block_name='res3a',
s1=2,
k1=1,
nf1=128,
name1='res3a_branch2a',
s2=1,
k2=3,
nf2=128,
name2='res3a_branch2b',
s3=1,
k3=1,
nf3=512,
name3='res3a_branch2c',
s4=2,
k4=1,
name4='res3a_branch1',
first_block=True)
print('Res3a')
print(res3a.get_shape())
print('---------------------')
res3b = bottleneck_block(res3a,
is_train,
block_name='res3b',
s1=1,
k1=1,
nf1=128,
name1='res3b_branch2a',
s2=1,
k2=3,
nf2=128,
name2='res3b_branch2b',
s3=1,
k3=1,
nf3=512,
name3='res3b_branch2c',
s4=1,
k4=1,
name4='res2b_branch1',
first_block=False)
print('Res3b')
print(res3b.get_shape())
print('---------------------')
res3c = bottleneck_block(res3b,
is_train,
block_name='res3c',
s1=1,
k1=1,
nf1=128,
name1='res3c_branch2a',
s2=1,
k2=3,
nf2=128,
name2='res3c_branch2b',
s3=1,
k3=1,
nf3=512,
name3='res3c_branch2c',
s4=1,
k4=1,
name4='res3c_branch1',
first_block=False)
print('Res3c')
print(res3c.get_shape())
print('---------------------')
res3d = bottleneck_block(res3c,
is_train,
block_name='res3d',
s1=1,
k1=1,
nf1=128,
name1='res3d_branch2a',
s2=1,
k2=3,
nf2=128,
name2='res3d_branch2b',
s3=1,
k3=1,
nf3=512,
name3='res3d_branch2c',
s4=1,
k4=1,
name4='res3d_branch1',
first_block=False)
print('Res3d')
print(res3d.get_shape())
print('---------------------')
# Res4
with tf.variable_scope('Res4'):
res4a = bottleneck_block(res3d,
is_train,
block_name='res4a',
s1=2,
k1=1,
nf1=256,
name1='res4a_branch2a',
s2=1,
k2=3,
nf2=256,
name2='res4a_branch2b',
s3=1,
k3=1,
nf3=1024,
name3='res4a_branch2c',
s4=2,
k4=1,
name4='res4a_branch1',
first_block=True)
print('---------------------')
print('Res4a')
print(res4a.get_shape())
print('---------------------')
res4b = bottleneck_block(res4a,
is_train,
block_name='res4b',
s1=1,
k1=1,
nf1=256,
name1='res4b_branch2a',
s2=1,
k2=3,
nf2=256,
name2='res4b_branch2b',
s3=1,
k3=1,
nf3=1024,
name3='res4b_branch2c',
s4=1,
k4=1,
name4='res4b_branch1',
first_block=False)
print('Res4b')
print(res4b.get_shape())
print('---------------------')
res4c = bottleneck_block(res4b,
is_train,
block_name='res4c',
s1=1,
k1=1,
nf1=256,
name1='res4c_branch2a',
s2=1,
k2=3,
nf2=256,
name2='res4c_branch2b',
s3=1,
k3=1,
nf3=1024,
name3='res4c_branch2c',
s4=1,
k4=1,
name4='res4c_branch1',
first_block=False)
print('Res4c')
print(res4c.get_shape())
print('---------------------')
res4d = bottleneck_block(res4c,
is_train,
block_name='res4d',
s1=1,
k1=1,
nf1=256,
name1='res4d_branch2a',
s2=1,
k2=3,
nf2=256,
name2='res4d_branch2b',
s3=1,
k3=1,
nf3=1024,
name3='res4d_branch2c',
s4=1,
k4=1,
name4='res4d_branch1',
first_block=False)
print('Res4d')
print(res4d.get_shape())
print('---------------------')
res4e = bottleneck_block(res4d,
is_train,
block_name='res4e',
s1=1,
k1=1,
nf1=256,
name1='res4e_branch2a',
s2=1,
k2=3,
nf2=256,
name2='res4e_branch2b',
s3=1,
k3=1,
nf3=1024,
name3='res4e_branch2c',
s4=1,
k4=1,
name4='res4e_branch1',
first_block=False)
print('Res4e')
print(res4e.get_shape())
print('---------------------')
res4f = bottleneck_block(res4e,
is_train,
block_name='res4f',
s1=1,
k1=1,
nf1=256,
name1='res4f_branch2a',
s2=1,
k2=3,
nf2=256,
name2='res4f_branch2b',
s3=1,
k3=1,
nf3=1024,
name3='res4f_branch2c',
s4=1,
k4=1,
name4='res4f_branch1',
first_block=False)
print('Res4f')
print(res4f.get_shape())
print('---------------------')
# Res5
with tf.variable_scope('Res5'):
res5a = bottleneck_block(res4f,
is_train,
block_name='res5a',
s1=2,
k1=1,
nf1=512,
name1='res5a_branch2a',
s2=1,
k2=3,
nf2=512,
name2='res5a_branch2b',
s3=1,
k3=1,
nf3=2048,
name3='res5a_branch2c',
s4=2,
k4=1,
name4='res5a_branch1',
first_block=True)
print('---------------------')
print('Res5a')
print(res5a.get_shape())
print('---------------------')
res5b = bottleneck_block(res5a,
is_train,
block_name='res5b',
s1=1,
k1=1,
nf1=512,
name1='res5b_branch2a',
s2=1,
k2=3,
nf2=512,
name2='res5b_branch2b',
s3=1,
k3=1,
nf3=2048,
name3='res5b_branch2c',
s4=1,
k4=1,
name4='res5b_branch1',
first_block=False)
print('Res5b')
print(res5b.get_shape())
print('---------------------')
res5c = bottleneck_block(res5b,
is_train,
block_name='res5c',
s1=1,
k1=1,
nf1=512,
name1='res5c_branch2a',
s2=1,
k2=3,
nf2=512,
name2='res5c_branch2b',
s3=1,
k3=1,
nf3=2048,
name3='res5c_branch2c',
s4=1,
k4=1,
name4='res5c_branch1',
first_block=False)
# res5c: [batch_size, 8, 8, 2048]
print('Res5c')
print(res5c.get_shape())
k_size = res5c.get_shape().as_list()[1]
num_filters = res5c.get_shape().as_list()[-1]
f_map = tf.reshape(res5c, [-1, k_size * k_size, num_filters],
name='reshape_fmaps')
# [batch_size, 64, 2048]
res5c_gap = avg_pool(res5c,
ksize=k_size,
stride=1,
name='res5_avg_pool')
# [batch_size, 1, 1, 2048]
print('---------------------')
print('Res5c after AVG_POOL')
print(res5c.get_shape())
print('---------------------')
net_flatten = flatten_layer(res5c_gap)
# [batch_size, 2048]
print('---------------------')
print('Matrix dimension to the first FC layer')
print(net_flatten.get_shape())
print('---------------------')
net, W = fc_layer(net_flatten,
numClasses,
'FC1',
is_train=is_train,
batch_norm=True,
add_reg=True,
use_relu=False)
# W: [2048, 14]
W_tiled = tf.tile(tf.expand_dims(W, axis=0), [args.val_batch_size, 1, 1])
# [2048, 14] -> [1, 2048, 14] -> [batch_size, 2048, 14]
heat_map_list = tf.unstack(tf.matmul(f_map, W_tiled), axis=0)
# [batch_size, 64, 14]
# list of heat-maps of length batch_size, each element: [64, 14]
cls_act_map_list = [
tf.nn.softmax(heat_map, dim=0) for heat_map in heat_map_list
]
cls_act_map = tf.stack(cls_act_map_list, axis=0)
# [batch_size, 64, 14]
return net, net_flatten, res5c, cls_act_map
def testGlobalAvgPool(self):
height, width = 3, 3
with self.test_session():
images = tf.random_uniform((5, height, width, 3), seed=1)
output = ops.avg_pool(images, images.get_shape()[1:3], stride=1)
self.assertListEqual(output.get_shape().as_list(), [5, 1, 1, 3])
def testCreateAvgPoolWithScope(self):
height, width = 3, 3
with self.test_session():
images = tf.random_uniform((5, height, width, 3), seed=1)
output = ops.avg_pool(images, [3, 3], scope='pool1')
self.assertEquals(output.op.name, 'pool1/AvgPool')
def densenet(self, x, is_training, no_of_blocks=3, block_layers=7, first_conv_op_channel=16, block_op_channel=12,
kernal_size=3):
strides = {'1': [1, 1, 1, 1], '2': [1, 2, 2, 1], '3': [1, 3, 3, 1], '4': [1, 4, 4, 1], '8': [1, 8, 8, 1]}
pool_win_size = {'1': [1, 1, 1, 1], '2': [1, 2, 2, 1], '3': [1, 3, 3, 1], '4': [1, 4, 4, 1], '8': [1, 8, 8, 1]}
x_shape = x.get_shape().as_list()[1:]
kernel = [kernal_size, kernal_size, x_shape[2], first_conv_op_channel]
conv = ops.conv2d(x, kernel, strides['1'], 'SAME', initial='xavier', with_bias=False)
if isinstance(block_layers, int):
with tf.variable_scope('Dense_Block_1') as scope:
kernel = [kernal_size, kernal_size, first_conv_op_channel, block_op_channel]
conv = ops.conv2d_dense_block(conv,'Dense_Block_1', is_training, kernel, layers=block_layers,dropout_rate=self.dropout_rate)
op_channel = first_conv_op_channel + block_layers * block_op_channel
for _ in range(1, no_of_blocks):
with tf.variable_scope('transition_layer_' + str(_ - 1)) as scope:
conv = tf.contrib.layers.batch_norm(conv, scale=True, is_training=is_training,
updates_collections=None)
conv = tf.nn.relu(conv)
kernel = [kernal_size, kernal_size, op_channel, op_channel]
conv = ops.conv2d(conv,'transition_layer_' + str(_ - 1), kernel, strides=[1, 1, 1, 1], padding='SAME', initial='xavier',
with_bias=False)
conv = tf.nn.dropout(conv, self.dropout_rate)
conv = ops.avg_pool(conv, pool_win_size['2'], strides['2'], 'VALID')
with tf.variable_scope('Dense_Block_' + str(_)) as scope:
kernel = [kernal_size, kernal_size, op_channel, block_op_channel]
conv = ops.conv2d_dense_block(conv,'Dense_Block_'+str(_),is_training, kernel, layers=block_layers,dropout_rate=self.dropout_rate)
op_channel += block_layers * block_op_channel
elif isinstance(block_layers, list):
no_of_blocks = len(block_layers)
with tf.variable_scope('Dense_Block_1') as scope:
kernel = [kernal_size, kernal_size, first_conv_op_channel, block_op_channel]
conv = ops.conv2d_dense_block(conv,'Dense_Block_1', is_training, kernel, layers=block_layers[0],dropout_rate=self.dropout_rate)
op_channel = first_conv_op_channel + block_layers[0] * block_op_channel
for _ in range(1, no_of_blocks):
with tf.variable_scope('transition_layer_' + str(_)) as scope:
conv = tf.contrib.layers.batch_norm(conv, scale=True, is_training=is_training,
updates_collections=None)
conv = tf.nn.relu(conv)
kernel = [kernal_size, kernal_size, op_channel, op_channel]
conv = ops.conv2d(conv,'transition_layer_' + str(_), kernel, strides=[1, 1, 1, 1], padding='SAME', initial='xavier',
with_bias=False)
conv = tf.nn.dropout(conv, self.dropout_rate)
conv = ops.avg_pool(conv, pool_win_size['2'], strides['2'], 'VALID')
with tf.variable_scope('Dense_Block_' + str(_ + 1)) as scope:
kernel = [kernal_size, kernal_size, op_channel, block_op_channel]
conv = ops.conv2d_dense_block(conv,'Dense_Block_'+str(_), is_training, kernel, layers=block_layers[_],dropout_rate=self.dropout_rate)
op_channel += block_layers[_] * block_op_channel
with tf.variable_scope('Global_Average_Pooling') as scope:
conv = tf.contrib.layers.batch_norm(conv, scale=True, is_training=is_training, updates_collections=None)
conv = tf.nn.relu(conv)
conv = ops.avg_pool(conv, pool_win_size['8'], strides['8'], 'VALID')
with tf.variable_scope('Flatten_layer') as scope:
conv= ops.flatten(conv)
with tf.variable_scope('Output_layer') as scope:
conv = ops.get_hidden_layer(conv,'output_layer',self.no_of_classes, activation='none', initializer='xavier')
return conv
