def build_shake_shake_model(images, num_classes, hparams, is_training):
"""Builds the Shake-Shake model.
Build the Shake-Shake model from https://arxiv.org/abs/1705.07485.
Args:
images: Tensor of images that will be fed into the Wide ResNet Model.
num_classes: Number of classed that the model needs to predict.
hparams: tf.HParams object that contains additional hparams needed to
construct the model. In this case it is the `shake_shake_widen_factor`
that is used to determine how many filters the model has.
is_training: Is the model training or not.
Returns:
The logits of the Shake-Shake model.
"""
depth = 26
k = hparams.shake_shake_widen_factor # The widen factor
n = int((depth - 2) / 6)
x = images
x = ops.conv2d(x, 16, 3, scope='init_conv')
x = ops.batch_norm(x, scope='init_bn')
with tf.variable_scope('L1'):
x = _shake_shake_layer(x, 16 * k, n, 1, is_training)
with tf.variable_scope('L2'):
x = _shake_shake_layer(x, 32 * k, n, 2, is_training)
with tf.variable_scope('L3'):
x = _shake_shake_layer(x, 64 * k, n, 2, is_training)
x = tf.nn.relu(x)
x = ops.global_avg_pool(x)
# Fully connected
logits = ops.fc(x, num_classes)
return logits
def build_wrn_model(images, num_classes, wrn_size, update_bn=True):
"""Builds the WRN model.
Build the Wide ResNet model from https://arxiv.org/abs/1605.07146.
Args:
images: Tensor of images that will be fed into the Wide ResNet Model.
num_classes: Number of classed that the model needs to predict.
wrn_size: Parameter that scales the number of filters in the Wide ResNet
model.
Returns:
The logits of the Wide ResNet model.
"""
# wrn_size = 16 * widening factor k
kernel_size = wrn_size
filter_size = 3
# depth = num_blocks_per_resnet * 6 + 4 = 28
num_blocks_per_resnet = 4
filters = [
min(kernel_size, 16), kernel_size, kernel_size * 2, kernel_size * 4
]
strides = [1, 2, 2] # stride for each resblock
# Run the first conv
with tf.variable_scope('init'):
x = images
output_filters = filters[0]
x = ops.conv2d(x, output_filters, filter_size, scope='init_conv')
first_x = x # Res from the beginning
orig_x = x # Res from previous block
for block_num in range(1, 4):
with tf.variable_scope('unit_{}_0'.format(block_num)):
activate_before_residual = True if block_num == 1 else False
x = residual_block(
x,
filters[block_num - 1],
filters[block_num],
strides[block_num - 1],
update_bn=update_bn,
activate_before_residual=activate_before_residual)
for i in range(1, num_blocks_per_resnet):
with tf.variable_scope('unit_{}_{}'.format(block_num, i)):
x = residual_block(
x,
filters[block_num],
filters[block_num],
1,
update_bn=update_bn,
activate_before_residual=False)
x, orig_x = _res_add(filters[block_num - 1], filters[block_num],
strides[block_num - 1], x, orig_x)
final_stride_val = np.prod(strides)
x, _ = _res_add(filters[0], filters[3], final_stride_val, x, first_x)
with tf.variable_scope('unit_last'):
x = ops.batch_norm(x, scope='final_bn')
x = tf.nn.relu(x)
x = ops.global_avg_pool(x)
logits = ops.fc(x, num_classes)
return logits
def build_shake_drop_model(images, num_classes, is_training):
"""Builds the PyramidNet Shake-Drop model.
Build the PyramidNet Shake-Drop model from https://arxiv.org/abs/1802.02375.
Args:
images: Tensor of images that will be fed into the Wide ResNet Model.
num_classes: Number of classed that the model needs to predict.
is_training: Is the model training or not.
Returns:
The logits of the PyramidNet Shake-Drop model.
"""
is_training = is_training
# ShakeDrop Hparams
p_l = 0.5
alpha_shake = [-1, 1]
beta_shake = [0, 1]
# PyramidNet Hparams
alpha = 200
depth = 272
# This is for the bottleneck architecture specifically
n = int((depth - 2) / 9)
start_channel = 16
add_channel = alpha / (3 * n)
# Building the models
x = images
x = ops.conv2d(x, 16, 3, scope='init_conv')
x = ops.batch_norm(x, scope='init_bn')
layer_num = 1
total_layers = n * 3
start_channel += add_channel
prob = calc_prob(layer_num, total_layers, p_l)
x = bottleneck_layer(x, round_int(start_channel), 1, prob, is_training,
alpha_shake, beta_shake)
layer_num += 1
for _ in range(1, n):
start_channel += add_channel
prob = calc_prob(layer_num, total_layers, p_l)
x = bottleneck_layer(x, round_int(start_channel), 1, prob, is_training,
alpha_shake, beta_shake)
layer_num += 1
start_channel += add_channel
prob = calc_prob(layer_num, total_layers, p_l)
x = bottleneck_layer(x, round_int(start_channel), 2, prob, is_training,
alpha_shake, beta_shake)
layer_num += 1
for _ in range(1, n):
start_channel += add_channel
prob = calc_prob(layer_num, total_layers, p_l)
x = bottleneck_layer(x, round_int(start_channel), 1, prob, is_training,
alpha_shake, beta_shake)
layer_num += 1
start_channel += add_channel
prob = calc_prob(layer_num, total_layers, p_l)
x = bottleneck_layer(x, round_int(start_channel), 2, prob, is_training,
alpha_shake, beta_shake)
layer_num += 1
for _ in range(1, n):
start_channel += add_channel
prob = calc_prob(layer_num, total_layers, p_l)
x = bottleneck_layer(x, round_int(start_channel), 1, prob, is_training,
alpha_shake, beta_shake)
layer_num += 1
assert layer_num - 1 == total_layers
x = ops.batch_norm(x, scope='final_bn')
x = tf.nn.relu(x)
x = ops.global_avg_pool(x)
# Fully connected
logits = ops.fc(x, num_classes)
return logits