def model(is_training, reuse, dropout_keep_prob=0.5):
common_args = common_layer_args(is_training, reuse)
conv_args = make_args(batch_norm=True, activation=prelu, w_init=initz.he_normal(
scale=1), untie_biases=False, **common_args)
pool_args = make_args(padding='SAME', **common_args)
inputs = input((None, crop_size[1], crop_size[0], 3), **common_args)
with tf.variable_scope('squeezenet', values=[inputs]):
net = conv2d(inputs, 96, stride=(2, 2), name='conv1', **conv_args)
net = max_pool(net, name='maxpool1', **pool_args)
net = fire_module(net, 16, 64, name='fire2', **conv_args)
net = fire_module(net, 16, 64, name='fire3', **conv_args)
net = fire_module(net, 32, 128, name='fire4', **conv_args)
net = max_pool(net, name='maxpool4', **pool_args)
net = fire_module(net, 32, 128, name='fire5', **conv_args)
net = fire_module(net, 48, 192, name='fire6', **conv_args)
net = fire_module(net, 48, 192, name='fire7', **conv_args)
net = fire_module(net, 64, 256, name='fire8', **conv_args)
net = max_pool(net, name='maxpool8', **pool_args)
net = fire_module(net, 64, 256, name='fire9', **conv_args)
# Reversed avg and conv layers per 'Network in Network'
net = dropout(net, drop_p=1 - dropout_keep_prob,
name='dropout6', **common_args)
net = conv2d(net, 10, filter_size=(1, 1), name='conv10', **conv_args)
logits = global_avg_pool(net, name='logits', **pool_args)
predictions = softmax(logits, name='predictions', **common_args)
return end_points(is_training)
def model(is_training, resue, num_classes=5):
common_args = common_layer_args(is_training, reuse)
conv_args = make_args(
untie_biases=True, batch_norm=batch_norm, **common_args)
logit_args = make_args(activation=prelu, **common_args)
inputs = input((None, crop_size[1], crop_size[0], 3), **common_args)
net = conv2d(inputs, 32, filter_size=(3, 3), stride=(
2, 2), name='conv1', **conv_params)
net = conv2d(net, 64, name='conv2', **conv_params)
net = bottleneck_v1(net, num_unit=128, name='block_v1_1', **conv_args)
net = bottleneck_v1(net, num_unit=256, name='block_v1_2', **conv_args)
net = bottleneck_v1(net, num_unit=728, name='block_v1_3', **conv_args)
for i in range(8):
prefix = 'block_v2_' + str(i + 5)
net = bottleneck_v2(net, num_unit=728, name=prefix, **kwargs)
net = bottleneck_v1(net, num_unit=1024, name='block_v1_4', **conv_args)
net = separable_conv2d(net, 1536, filter_size=(3, 3), stride=(1, 1),
name='sconv1', **kwargs)
net = separable_conv2d(net, 2048, filter_size=(3, 3), stride=(1, 1),
name='sconv2', **kwargs)
with tf.variable_scope('Logits'):
net = avg_pool_2d(net, net.get_shape()[1:3], name='AvgPool_1a')
net = dropout(
net, is_training, drop_p=1 - dropout_keep_prob, name='Dropout_1b')
logits = fully_connected(net, num_classes,
name='logits', **logit_args)
predictions = softmax(logits, name='predictions', **common_args)
return end_points(is_training)
def model(x, is_training, reuse):
common_args = common_layer_args(is_training, reuse)
fc_args = make_args(activation=relu, **common_args)
logit_args = make_args(activation=None, **common_args)
x = embedding(x, 10000, 128, reuse)
x = lstm(x, 34, reuse, is_training)
logits = fc(x, 2, name='logits', **logit_args)
predictions = softmax(logits, name='predictions', **common_args)
return end_points(is_training)
def generator(z_shape, is_training, reuse, batch_size=32):
common_args = common_layer_args(is_training, reuse)
conv_args = make_args(batch_norm=True,
activation=lrelu,
w_init=initz.he_normal(scale=1),
untie_biases=False,
**common_args)
conv_args_1st = make_args(batch_norm=None,
activation=lrelu,
w_init=initz.he_normal(scale=1),
untie_biases=False,
**common_args)
fc_args = make_args(activation=lrelu,
w_init=initz.he_normal(scale=1),
**common_args)
pool_args = make_args(padding='SAME', **common_args)
# project `z` and reshape
# TODO think about phase again
end_points = {}
z = get_z(z_shape, reuse)
end_points['z'] = z
z_fc = fully_connected(z, 4 * 4 * 512, name="g_fc", **fc_args)
end_points['g_fc'] = z_fc
x = tf.reshape(z_fc, [batch_size, 4, 4, 512])
end_points['g_reshaped'] = x
x = upsample2d(x, [batch_size, 8, 8, 256],
name="g_deconv2d_1",
**conv_args)
end_points['g_deconv2d_1'] = x
x = upsample2d(x, [batch_size, 16, 16, 128],
name="g_deconv2d_2",
**conv_args)
end_points['g_deconv2d_2'] = x
# x = upsample2d(x, [batch_size, 32, 32, 16 * 3],
# name="g_deconv2d_3", **conv_args)
# end_points['g_deconv2d_3'] = x
# for now lets examine cifar
# x = subpixel2d(x, 4, name='z_subpixel1')
# x shape[batch_size, 128, 128, 3]
# end_points['subpixel1'] = x
x = upsample2d(x, [batch_size, 32, 32, 64],
name="g_deconv2d_3",
**conv_args)
end_points['g_deconv2d_3'] = x
x = upsample2d(x, [batch_size, 64, 64, 32],
name="g_deconv2d_4",
**conv_args)
end_points['g_deconv2d_4'] = x
x = upsample2d(x, [batch_size, 128, 128, 3],
name="g_deconv2d_5",
**conv_args_1st)
end_points['g_deconv2d_5'] = x
end_points['softmax'] = tf.nn.tanh(x)
return end_points
def model(inputs, is_training, reuse, num_classes=10, dropout_keep_prob=0.5):
common_args = common_layer_args(is_training, reuse)
conv_args = make_args(batch_norm=True,
activation=prelu,
w_init=initz.he_normal(scale=1),
untie_biases=False,
**common_args)
conv_args_fm = make_args(w_init=initz.he_normal(scale=1),
untie_biases=False,
**common_args)
pool_args = make_args(padding='SAME', **common_args)
with tf.variable_scope('squeezenet', values=[inputs]):
net = separable_conv2d(inputs,
256,
stride=(2, 2),
name='conv1',
**conv_args)
# net = conv2d(inputs, 96, stride=(2, 2), name='conv1', **conv_args)
net = max_pool(net, name='maxpool1', **pool_args)
net = fire_module(net, 16, 64, name='fire2', **conv_args_fm)
net = bottleneck_simple(net, 16, 64, name='fire3', **conv_args_fm)
net = batch_norm(net,
activation_fn=tf.nn.relu,
name='fire3_bn',
is_training=is_training,
reuse=reuse)
net = fire_module(net, 32, 128, name='fire4', **conv_args_fm)
net = max_pool(net, name='maxpool4', **pool_args)
net = bottleneck_simple(net, 32, 128, name='fire5', **conv_args_fm)
net = batch_norm(net,
activation_fn=tf.nn.relu,
name='fire5_bn',
is_training=is_training,
reuse=reuse)
net = fire_module(net, 48, 192, name='fire6', **conv_args_fm)
net = bottleneck_simple(net, 48, 192, name='fire7', **conv_args_fm)
net = batch_norm(net,
activation_fn=tf.nn.relu,
name='fire7_bn',
is_training=is_training,
reuse=reuse)
net = fire_module(net, 64, 256, name='fire8', **conv_args_fm)
net = max_pool(net, name='maxpool8', **pool_args)
net = dropout(net,
drop_p=1 - dropout_keep_prob,
name='dropout6',
**common_args)
net = conv2d(net,
num_classes,
filter_size=(1, 1),
name='conv10',
**conv_args_fm)
logits = global_avg_pool(net, name='logits', **pool_args)
predictions = softmax(logits, name='predictions', **common_args)
return end_points(is_training)
def model(x, is_training, reuse, num_classes=2, **kwargs):
common_args = common_layer_args(is_training, reuse)
fc_args = make_args(activation=relu, **common_args)
logit_args = make_args(activation=None, **common_args)
x = embedding(x, 10000, 128, reuse)
x = bidirectional_rnn(x, LSTMCell(128, reuse), LSTMCell(128, reuse),
**common_args)
logits = fc(x, num_classes, name='logits', **logit_args)
predictions = softmax(logits, name='predictions', **common_args)
return end_points(is_training)
def model(is_training, reuse):
common_args = common_layer_args(is_training, reuse)
fc_args = make_args(activation=relu, **common_args)
logit_args = make_args(activation=None, **common_args)
x = input((None, height * width), **common_args)
x = fully_connected(x, n_output=100, name='fc1', **fc_args)
logits = fully_connected(x, n_output=10, name="logits", **logit_args)
predictions = softmax(logits, name='predictions', **common_args)
return end_points(is_training)
def encoder(inputs, is_training, reuse, z_dim=512):
common_args = common_layer_args(is_training, reuse)
conv_args = make_args(batch_norm=True,
activation=lrelu,
w_init=initz.he_normal(scale=1),
untie_biases=False,
**common_args)
conv_args_1st = make_args(batch_norm=None,
activation=lrelu,
w_init=initz.he_normal(scale=1),
untie_biases=False,
**common_args)
logits_args = make_args(activation=None,
w_init=initz.he_normal(scale=1),
**common_args)
pool_args = make_args(padding='SAME', **common_args)
end_points = {}
x = inputs
end_points['inputs'] = x
x = dropout(x, drop_p=0.2, name="input_dropout1", **common_args)
x = conv2d(x,
96,
filter_size=(5, 5),
stride=(2, 2),
name="e_conv1_1",
**conv_args_1st)
end_points['e_conv1_1'] = x
x = conv2d(x, 96, name="e_conv1_2", **conv_args)
end_points['e_conv1_2'] = x
x = conv2d(x, 96, stride=(2, 2), name="e_conv1_3", **conv_args)
end_points['e_conv1_3'] = x
x = dropout(x, drop_p=0.2, name="dropout1", **common_args)
x = conv2d(x, 192, name="e_conv2_1", **conv_args)
end_points['e_conv2_1'] = x
x = conv2d(x, 192, name="e_conv2_2", **conv_args)
end_points['e_conv2_2'] = x
# x = conv2d(x, 192, stride=(2, 2), name="e_conv2_3", **conv_args)
# end_points['e_conv2_3'] = x
x = dropout(x, drop_p=0.2, name="dropout2", **common_args)
# x = conv2d(x, 192, stride=(2, 2), name="e_conv3_1", **conv_args)
# end_points['e_conv3_1'] = x
x = conv2d(x, 192, filter_size=(1, 1), name="e_conv4_1", **conv_args)
end_points['e_conv4_1'] = x
x = conv2d(x, 192, filter_size=(1, 1), name="e_conv4_2", **conv_args)
end_points['e_conv4_2'] = x
x = global_avg_pool(x, name="global_pool")
end_points['global_pool'] = x
logits1 = fully_connected(x, z_dim, name="e_logits1", **logits_args)
logits2 = fully_connected(x, z_dim, name="e_logits2", **logits_args)
logits2 = tf.tanh(logits2, name='e_logits2_tanh')
end_points['e_logits1'] = logits1
end_points['e_logits2'] = logits2
return end_points
def discriminator(inputs, is_training, reuse, num_classes=1):
common_args = common_layer_args(is_training, reuse)
conv_args = make_args(batch_norm=True,
activation=lrelu,
w_init=initz.he_normal(scale=1),
untie_biases=False,
**common_args)
conv_args_1st = make_args(batch_norm=None,
activation=lrelu,
w_init=initz.he_normal(scale=1),
untie_biases=False,
**common_args)
logits_args = make_args(activation=None,
w_init=initz.he_normal(scale=1),
**common_args)
pool_args = make_args(padding='SAME', **common_args)
end_points = {}
x = inputs
end_points['inputs'] = x
x = dropout(x, drop_p=0.2, name="input_dropout1", **common_args)
x = conv2d(x,
96,
filter_size=(5, 5),
stride=(2, 2),
name="d_conv1_1",
**conv_args_1st)
end_points['d_conv1_1'] = x
x = conv2d(x, 96, name="d_conv1_2", **conv_args)
end_points['d_conv1_2'] = x
x = conv2d(x, 96, stride=(2, 2), name="d_conv1_3", **conv_args)
end_points['d_conv1_3'] = x
x = dropout(x, drop_p=0.2, name="dropout1", **common_args)
x = conv2d(x, 192, name="d_conv2_1", **conv_args)
end_points['d_conv2_1'] = x
x = conv2d(x, 192, name="d_conv2_2", **conv_args)
end_points['d_conv2_2'] = x
# x = conv2d(x, 192, stride=(2, 2), name="d_conv2_3", **conv_args)
# end_points['d_conv2_3'] = x
x = dropout(x, drop_p=0.2, name="dropout2", **common_args)
# x = conv2d(x, 192, stride=(2, 2), name="d_conv3_1", **conv_args)
# end_points['d_conv3_1'] = x
x = conv2d(x, 192, filter_size=(1, 1), name="d_conv4_1", **conv_args)
end_points['d_conv4_1'] = x
x = conv2d(x, 192, filter_size=(1, 1), name="d_conv4_2", **conv_args)
end_points['d_conv4_2'] = x
x = global_avg_pool(x, name="global_pool")
end_points['global_pool'] = x
logits = fully_connected(x, num_classes, name="d_logits", **logits_args)
end_points['logits'] = logits
end_points['predictions'] = softmax(logits,
name='predictions',
**common_args)
return end_points
def model(x, is_training, reuse, num_classes=10, **kwargs):
common_args = common_layer_args(is_training, reuse)
fc_args = make_args(activation=relu, **common_args)
logit_args = make_args(activation=None, **common_args)
x = fully_connected(x, n_output=100, name='fc1', **fc_args)
logits = fully_connected(x,
n_output=num_classes,
name="logits",
**logit_args)
predictions = softmax(logits, name='predictions', **common_args)
return end_points(is_training)
def bottleneck(inputs,
depth,
depth_bottleneck,
stride,
rate=1,
scope=None,
**common_args):
conv_args_common = make_args(use_bias=False,
batch_norm=batch_norm_tf,
batch_norm_args=batch_norm_params,
**common_args)
conv_args_relu = make_args(activation=relu, **conv_args_common)
conv_args_none = make_args(activation=None, **conv_args_common)
with tf.variable_scope(scope, 'bottleneck_v1', [inputs]) as sc:
depth_in = utils.last_dimension(inputs.get_shape(), min_rank=4)
if depth == depth_in:
shortcut = subsample(inputs, stride, 'shortcut', **common_args)
else:
shortcut = conv2d(inputs,
depth,
filter_size=(1, 1),
stride=(stride, stride),
name='shortcut',
**conv_args_none)
residual = conv2d(inputs,
depth_bottleneck,
filter_size=(1, 1),
stride=(1, 1),
name='conv1',
**conv_args_relu)
residual = conv2d_same(residual,
depth_bottleneck,
3,
stride,
rate=rate,
scope='conv2',
**conv_args_relu)
residual = conv2d(residual,
depth,
filter_size=(1, 1),
stride=(1, 1),
name='conv3',
**conv_args_none)
# not in endpoints. does that matter?
output = tf.nn.relu(shortcut + residual)
return _collect_named_outputs(common_args['outputs_collections'],
sc.name, output)
def model(x, is_training, reuse, num_classes=2, **kwargs):
common_args = common_layer_args(is_training, reuse)
fc_args = make_args(activation=relu, **common_args)
logit_args = make_args(activation=None, **common_args)
x = embedding(x, 10000, 128, reuse)
x1 = conv1d(x, 128, name='conv1_1', **common_args)
x2 = conv1d(x, 128, filter_size=4, name='conv1_2', **common_args)
x3 = conv1d(x, 128, filter_size=5, name='conv1_3', **common_args)
x = merge([x1, x2, x3], 'concat', axis=1)
x = lstm(x, 384, reuse, is_training)
x = dropout(x, drop_p=0.3, **common_args)
logits = fc(x, num_classes, name='logits', **logit_args)
predictions = softmax(logits, name='predictions', **common_args)
return end_points(is_training)
def model(x, is_training, reuse):
common_args = common_layer_args(is_training, reuse)
fc_args = make_args(activation=relu, **common_args)
logit_args = make_args(activation=None, **common_args)
x = embedding(x, 10000, 128, reuse)
x1 = conv1d(x, 128, name='conv1_1', **common_args)
x2 = conv1d(x, 128, filter_size=4, name='conv1_2', **common_args)
x3 = conv1d(x, 128, filter_size=5, name='conv1_3', **common_args)
x = merge([x1, x2, x3], 'concat', axis=1)
x = tf.expand_dims(x, 2)
x = global_max_pool(x)
x = dropout(x, drop_p=0.3, **common_args)
logits = fc(x, 2, name='logits', **logit_args)
predictions = softmax(logits, name='predictions', **common_args)
return end_points(is_training)
def model(inputs,
is_training,
reuse,
input_size=image_size[0],
drop_p_conv=0.0,
drop_p_trans=0.0,
n_filters=64,
n_layers=[1, 2, 2, 3],
num_classes=5, **kwargs):
common_args = common_layer_args(is_training, reuse)
conv_args = make_args(
batch_norm=True,
activation=prelu,
w_init=initz.he_normal(scale=1),
untie_biases=True,
**common_args)
fc_args = make_args(activation=prelu, w_init=initz.he_normal(scale=1), **common_args)
logit_args = make_args(activation=None, w_init=initz.he_normal(scale=1), **common_args)
pred_args = make_args(activation=prelu, w_init=initz.he_normal(scale=1), **common_args)
pool_args = make_args(padding='SAME', filter_size=(2, 2), stride=(2, 2), **common_args)
x = conv2d(inputs, 48, filter_size=(7, 7), name="conv1", **conv_args)
x = max_pool(x, name='pool1', **pool_args)
x = conv2d(x, 64, name="conv2_1", **conv_args)
x = conv2d(x, 64, name="conv2_2", **conv_args)
x = max_pool(x, name='pool2', **pool_args)
# 112
for block_idx in range(3):
x, n_filters = dense_block(
x,
n_filters,
num_layers=n_layers[block_idx],
drop_p=drop_p_conv,
block_name='dense_' + str(block_idx),
**conv_args)
x = trans_block(
x, n_filters, drop_p=drop_p_trans, block_name='trans_' + str(block_idx), **conv_args)
x, n_filters = dense_block(
x, n_filters, num_layers=n_layers[3], drop_p=drop_p_trans, block_name='dense_3', **conv_args)
# 8
x = global_avg_pool(x, name='avgpool_1a_8x8')
logits = fully_connected(x, n_output=num_classes, name="logits", **logit_args)
predictions = softmax(logits, name='predictions', **common_args)
return end_points(is_training)
def model(is_training, reuse):
common_args = common_layer_args(is_training, reuse)
conv_args = make_args(batch_norm=None, activation=prelu, **common_args)
fc_args = make_args(activation=prelu, **common_args)
logit_args = make_args(activation=None, **common_args)
x = input((None, crop_size[1], crop_size[0], 1), **common_args)
x = conv2d(x, 32, name='conv1_1', **conv_args)
x = conv2d(x, 32, name='conv1_2', **conv_args)
x = max_pool(x, name='pool1', **common_args)
x = dropout(x, drop_p=0.25, name='dropout1', **common_args)
x = fully_connected(x, n_output=128, name='fc1', **fc_args)
x = dropout(x, drop_p=0.5, name='dropout2', **common_args)
logits = fully_connected(x, n_output=36, name="logits", **logit_args)
predictions = softmax(logits, name='predictions', **common_args)
return end_points(is_training)
def model(is_training, reuse):
common_args = common_layer_args(is_training, reuse)
conv_args = make_args(activation=relu, **common_args)
pool_args = make_args(filter_size=(2, 2), **common_args)
fc_args = make_args(activation=relu, **common_args)
logit_args = make_args(activation=None, **common_args)
x = input((None, crop_size[1], crop_size[0], 3), **common_args)
x = conv2d(x, 64, name='conv1_1', **conv_args)
x = conv2d(x, 64, name='conv1_2', **conv_args)
x = max_pool(x, name='maxpool1', **pool_args)
x = conv2d(x, 128, name='conv2_1', **conv_args)
x = conv2d(x, 128, name='conv2_2', **conv_args)
x = max_pool(x, name='maxpool2', **pool_args)
x = conv2d(x, 256, name='conv3_1', **conv_args)
x = conv2d(x, 256, name='conv3_2', **conv_args)
x = conv2d(x, 256, name='conv3_3', **conv_args)
x = max_pool(x, name='maxpool3', **pool_args)
x = conv2d(x, 512, name='conv4_1', **conv_args)
x = conv2d(x, 512, name='conv4_2', **conv_args)
x = conv2d(x, 512, name='conv4_3', **conv_args)
x = max_pool(x, name='maxpool4', **pool_args)
x = conv2d(x, 512, name='conv5_1', **conv_args)
x = conv2d(x, 512, name='conv5_2', **conv_args)
x = conv2d(x, 512, name='conv5_3', **conv_args)
x = max_pool(x, name='maxpool5', **pool_args)
x = fully_connected(x, n_output=4096, name='fc6', **fc_args)
x = dropout(x, drop_p=0.5, name='dropout1', **common_args)
x = fully_connected(x, n_output=4096, name='fc7', **fc_args)
x = dropout(x, drop_p=0.5, name='dropout2', **common_args)
logits = fully_connected(x, n_output=1000, name="logits", **logit_args)
predictions = softmax(logits, name='predictions', **common_args)
return end_points(is_training)
def create_training_iters(cnf, data_set, crop_size, epoch, parallel):
standardizer = cnf.get('standardizer', NoOpStandardizer())
balancing = 'balance_ratio' in cnf
if parallel:
if balancing:
training_iterator_maker = iterator.BalancingDAIterator
else:
training_iterator_maker = iterator.ParallelDAIterator
validation_iterator_maker = iterator.ParallelDAIterator
logger.info('Using parallel training iterator')
else:
if balancing:
training_iterator_maker = iterator.BalancingQueuedDAIterator
else:
training_iterator_maker = iterator.QueuedDAIterator
validation_iterator_maker = iterator.ParallelDAIterator
# validation_iterator_maker = iterator.QueuedDAIterator
logger.info('Using queued training iterator')
preprocessor = None
if balancing:
balancing_args = make_args(
balance_weights=data_set.balance_weights(),
final_balance_weights=cnf['final_balance_weights'],
balance_ratio=cnf['balance_ratio'],
balance_epoch_count=epoch - 1,
)
else:
balancing_args = {}
training_iterator = training_iterator_maker(
batch_size=cnf['batch_size_train'],
shuffle=True,
preprocessor=preprocessor,
crop_size=crop_size,
is_training=True,
aug_params=cnf.get('aug_params', data.no_augmentation_params),
standardizer=standardizer,
fill_mode='constant',
# save_to_dir=da_training_preview_dir,
**balancing_args)
validation_iterator = validation_iterator_maker(
batch_size=cnf['batch_size_test'],
shuffle=True,
preprocessor=preprocessor,
crop_size=crop_size,
is_training=False,
standardizer=standardizer,
fill_mode='constant')
return training_iterator, validation_iterator
def model(x, is_training, reuse, num_classes=10, **config):
common_args = common_layer_args(is_training, reuse)
logit_args = make_args(activation=None, **common_args)
if config['max_conv_layers']>0:
for i in range(1, config['n_conv_layers']+1):
activation, size, maxpool = layer_config(config, i, layer_type='conv')
conv_args = make_args(batch_norm=bool(config['batch_norm']), activation=prelu, **common_args)
x = conv2d(x, size, name='conv{}'.format(i), **conv_args)
if maxpool:
x = max_pool(x, name='pool{}'.format(i), **common_args)
if config['max_fc_layers']>0:
for i in range(1, config['n_fc_layers']+1):
activation, size, _dropout = layer_config(config, i, layer_type='fc')
fc_args = make_args(activation=prelu, **common_args)
x = fully_connected(x, n_output=size, name='fc{}'.format(i), **fc_args)
x = dropout(x, drop_p=np.round(_dropout, 2), name='dropout{}'.format(i), **common_args)
logits = fully_connected(x, n_output=num_classes, name="logits", **logit_args)
predictions = softmax(logits, name='predictions', **common_args)
return end_points(is_training)
def resnet_v1(inputs,
blocks,
num_classes=None,
global_pool=True,
output_stride=None,
include_root_block=True,
scope=None,
**common_args):
conv_args = make_args(use_bias=False,
activation=relu,
batch_norm=batch_norm_tf,
batch_norm_args=batch_norm_params,
**common_args)
with tf.variable_scope(scope,
'resnet_v1', [inputs],
reuse=common_args['reuse']) as sc:
net = inputs
if include_root_block:
if output_stride is not None:
if output_stride % 4 != 0:
raise ValueError(
'The output_stride needs to be a multiple of 4.')
output_stride /= 4
net = conv2d_same(net, 64, 7, stride=2, scope='conv1', **conv_args)
net = max_pool(net,
filter_size=(3, 3),
stride=(2, 2),
padding='SAME',
name='pool1')
net = stack_blocks_dense(net, blocks, output_stride, **common_args)
if global_pool:
# Global average pooling.
net = tf.reduce_mean(net, [1, 2], name='pool5', keep_dims=True)
if num_classes is not None:
net = conv2d(net,
num_classes,
filter_size=(1, 1),
activation=None,
name='logits',
**common_args)
predictions = softmax(net, name='predictions', **common_args)
return end_points(common_args['is_training'])
def model(is_training, reuse, inputs=None):
common_trainable_args = common_layer_args(is_training,
reuse,
trainable=True)
common_frozen_args = common_layer_args(is_training, reuse, trainable=False)
conv_args = make_conv_args(activation=relu, **common_frozen_args)
logit_args = make_args(activation=None, **common_trainable_args)
common_args = common_frozen_args
# move this down to train only a few layers
common_args = common_trainable_args
if inputs is None:
net = input((None, crop_size[1], crop_size[0], 3), **common_args)
else:
net = inputs
with tf.variable_scope('resnet_v1_50', reuse=reuse):
mean_rgb = tf.get_variable(name='mean_rgb',
initializer=tf.truncated_normal(shape=[3]),
trainable=False)
net = net - mean_rgb
net = conv2d_same(net,
64,
filter_size=(7, 7),
stride=(2, 2),
name='conv1',
**conv_args)
net = max_pool(net,
filter_size=(3, 3),
stride=(2, 2),
padding='SAME',
name='pool1')
with tf.variable_scope('block1') as sc:
with tf.variable_scope('unit_1'):
net = bottleneck(net, 256, 64, 1, **common_args)
with tf.variable_scope('unit_2'):
net = bottleneck(net, 256, 64, 1, **common_args)
with tf.variable_scope('unit_3'):
net = bottleneck(net, 256, 64, 2, **common_args)
net = collect_named_outputs(common_args['outputs_collections'],
sc.name, net)
with tf.variable_scope('block2') as sc:
with tf.variable_scope('unit_1'):
net = bottleneck(net, 512, 128, 1, **common_args)
with tf.variable_scope('unit_2'):
net = bottleneck(net, 512, 128, 1, **common_args)
with tf.variable_scope('unit_3'):
net = bottleneck(net, 512, 128, 1, **common_args)
with tf.variable_scope('unit_4'):
net = bottleneck(net, 512, 128, 2, **common_args)
net = collect_named_outputs(common_args['outputs_collections'],
sc.name, net)
with tf.variable_scope('block3') as sc:
with tf.variable_scope('unit_1'):
net = bottleneck(net, 1024, 256, 1, **common_args)
with tf.variable_scope('unit_2'):
net = bottleneck(net, 1024, 256, 1, **common_args)
with tf.variable_scope('unit_3'):
net = bottleneck(net, 1024, 256, 1, **common_args)
with tf.variable_scope('unit_4'):
net = bottleneck(net, 1024, 256, 1, **common_args)
with tf.variable_scope('unit_5'):
net = bottleneck(net, 1024, 256, 1, **common_args)
with tf.variable_scope('unit_6'):
net = bottleneck(net, 1024, 256, 2, **common_args)
net = collect_named_outputs(common_args['outputs_collections'],
sc.name, net)
with tf.variable_scope('block4') as sc:
with tf.variable_scope('unit_1'):
net = bottleneck(net, 2048, 512, 1, **common_args)
with tf.variable_scope('unit_2'):
net = bottleneck(net, 2048, 512, 1, **common_args)
with tf.variable_scope('unit_3'):
net = bottleneck(net, 2048, 512, 1, **common_args)
net = collect_named_outputs(common_args['outputs_collections'],
sc.name, net)
net = tf.reduce_mean(net, [1, 2], name='pool5', keep_dims=True)
net = conv2d(net,
1000,
filter_size=(1, 1),
name='logits',
**logit_args)
logits = squeeze(net, axis=[1, 2], name='logits', **common_args)
predictions = softmax(logits, name='predictions', **common_args)
return end_points(common_args['is_training'])
def model(height,
width,
num_actions,
is_training=False,
reuse=None,
name=None):
common_args = common_layer_args(is_training, reuse)
conv_args = make_args(batch_norm=True,
activation=prelu,
w_init=initz.he_normal(scale=1),
untie_biases=False,
**common_args)
logits_args = make_args(activation=None,
w_init=initz.he_normal(scale=1),
**common_args)
fc_args = make_args(activation=prelu,
w_init=initz.he_normal(scale=1),
**common_args)
pool_args = make_args(padding='SAME', **common_args)
with tf.variable_scope(name):
state = register_to_collections(tf.placeholder(
shape=[None, 4, height, width], dtype=tf.float32, name='state'),
name='state',
**common_args)
state_perm = tf.transpose(state, perm=[0, 2, 3, 1])
summary_ops = [
tf.summary.image("states",
state[:, 0, :, :][..., tf.newaxis],
max_outputs=10,
collections='train')
]
conv1_0 = conv2d(state_perm,
32,
filter_size=8,
stride=(1, 1),
name="conv1_0",
**conv_args)
conv1_1 = conv2d(conv1_0,
64,
filter_size=8,
stride=(2, 2),
name="conv1_1",
**conv_args)
pool = max_pool(conv1_1, filter_size=2, name="maxpool", **pool_args)
conv2_0 = conv2d(pool,
128,
filter_size=4,
stride=2,
name="conv2_0",
**conv_args)
conv2_1 = conv2d(conv2_0,
256,
filter_size=3,
stride=(2, 2),
name="conv2_1",
**conv_args)
conv3_0 = conv2d(conv2_1,
256,
filter_size=4,
stride=1,
name="conv3_0",
**conv_args)
conv3_1 = conv2d(conv3_0,
512,
filter_size=4,
stride=2,
name="conv3_1",
**conv_args)
# Dueling
value_hid = fc(conv3_1, 512, name="value_hid", **fc_args)
adv_hid = fc(conv3_1, 512, name="adv_hid", **fc_args)
value = fc(value_hid, 1, name="value", **logits_args)
advantage = fc(adv_hid, num_actions, name="advantage", **logits_args)
# Average Dueling
Qs = value + (advantage -
tf.reduce_mean(advantage, axis=1, keep_dims=True))
# action with highest Q values
a = register_to_collections(tf.argmax(Qs, 1), name='a', **common_args)
# Q value belonging to selected action
Q = register_to_collections(tf.reduce_max(Qs, 1),
name='Q',
**common_args)
summary_ops.append(tf.summary.histogram("Q", Q, collections='train'))
# For training
Q_target = register_to_collections(tf.placeholder(shape=[None],
dtype=tf.float32),
name='Q_target',
**common_args)
actions = register_to_collections(tf.placeholder(shape=[None],
dtype=tf.int32),
name='actions',
**common_args)
actions_onehot = tf.one_hot(actions,
num_actions,
on_value=1.,
off_value=0.,
axis=1,
dtype=tf.float32)
Q_tmp = tf.reduce_sum(tf.multiply(Qs, actions_onehot), axis=1)
loss = register_to_collections(tf.reduce_mean(
tf.square(Q_target - Q_tmp)),
name='loss',
**common_args)
summary_ops.append(tf.summary.scalar("loss", loss,
collections='train'))
register_to_collections(summary_ops, name='summary_ops', **common_args)
return end_points(is_training)
def resnet_v1(inputs,
is_training,
reuse,
blocks,
num_classes=None,
global_pool=True,
output_stride=None,
include_root_block=True,
name=None):
"""Generator for v2 (preactivation) ResNet models.
This function generates a family of ResNet v2 models. See the resnet_v2_*()
methods for specific model instantiations, obtained by selecting different
block instantiations that produce ResNets of various depths.
Training for image classification on Imagenet is usually done with [224, 224]
inputs, resulting in [7, 7] feature maps at the output of the last ResNet
block for the ResNets defined in [1] that have nominal stride equal to 32.
However, for dense prediction tasks we advise that one uses inputs with
spatial dimensions that are multiples of 32 plus 1, e.g., [321, 321]. In
this case the feature maps at the ResNet output will have spatial shape
[(height - 1) / output_stride + 1, (width - 1) / output_stride + 1]
and corners exactly aligned with the input image corners, which greatly
facilitates alignment of the features to the image. Using as input [225, 225]
images results in [8, 8] feature maps at the output of the last ResNet block.
For dense prediction tasks, the ResNet needs to run in fully-convolutional
(FCN) mode and global_pool needs to be set to False. The ResNets in [1, 2] all
have nominal stride equal to 32 and a good choice in FCN mode is to use
output_stride=16 in order to increase the density of the computed features at
small computational and memory overhead, cf. http://arxiv.org/abs/1606.00915.
Args:
inputs: A tensor of size [batch, height_in, width_in, channels].
blocks: A list of length equal to the number of ResNet blocks. Each element
is a resnet_utils.Block object describing the units in the block.
num_classes: Number of predicted classes for classification tasks. If None
we return the features before the logit layer.
is_training: whether is training or not.
global_pool: If True, we perform global average pooling before computing the
logits. Set to True for image classification, False for dense prediction.
output_stride: If None, then the output will be computed at the nominal
network stride. If output_stride is not None, it specifies the requested
ratio of input to output spatial resolution.
include_root_block: If True, include the initial convolution followed by
max-pooling, if False excludes it. If excluded, `inputs` should be the
results of an activation-less convolution.
reuse: whether or not the network and its variables should be reused. To be
able to reuse 'scope' must be given.
name: Optional variable_scope.
Returns:
net: A rank-4 tensor of size [batch, height_out, width_out, channels_out].
If global_pool is False, then height_out and width_out are reduced by a
factor of output_stride compared to the respective height_in and width_in,
else both height_out and width_out equal one. If num_classes is None, then
net is the output of the last ResNet block, potentially after global
average pooling. If num_classes is not None, net contains the pre-softmax
activations.
end_points: A dictionary from components of the network to the corresponding
activation.
Raises:
ValueError: If the target output_stride is not valid.
"""
common_args = common_layer_args(is_training, reuse)
conv_args = make_args(batch_norm=True,
activation=prelu,
w_init=initz.he_normal(scale=1),
untie_biases=False,
**common_args)
logits_args = make_args(activation=None,
w_init=initz.he_normal(scale=1),
**common_args)
pred_args = make_args(activation=prelu,
w_init=initz.he_normal(scale=1),
**common_args)
pool_args = make_args(padding='SAME', **common_args)
with tf.variable_scope(name, 'resnet_v2', [inputs], reuse=reuse):
net = inputs
if include_root_block:
if output_stride is not None:
if output_stride % 4 != 0:
raise ValueError(
'The output_stride needs to be a multiple of 4.')
output_stride /= 4
# We do not include batch normalization or activation functions in
# conv1 because the first ResNet unit will perform these. Cf.
# Appendix of [2].
net = resnet_utils.conv2d_same(net,
64,
7,
stride=2,
name='conv1',
**common_args)
net = max_pool(net, name='pool1', **pool_args)
net = resnet_utils.stack_blocks_dense(net, blocks, output_stride,
**conv_args)
# This is needed because the pre-activation variant does not have batch
# normalization or activation functions in the residual unit output. See
# Appendix of [2].
net = batch_norm(net,
activation=tf.nn.relu,
name='postnorm',
is_training=is_training,
reuse=reuse)
if global_pool:
# Global average pooling.
net = tf.reduce_mean(net, [1, 2], name='pool5', keep_dims=True)
if num_classes is not None:
net = conv2d(net,
num_classes,
filter_size=(1, 1),
name='logits',
**logits_args)
if num_classes is not None:
predictions = softmax(net, name='predictions', **pred_args)
return end_points(is_training)
def model(is_training, reuse, flexi_inputs=False):
common_args = common_layer_args(is_training, reuse)
conv_args = make_args(activation=relu, **common_args)
pool_args = make_args(filter_size=(2, 2), **common_args)
logit_args = make_args(activation=None, **common_args)
if flexi_inputs:
inputs_shape = (None, None, None, 3)
else:
inputs_shape = (None, crop_size[1], crop_size[0], 3)
net_inputs = input(inputs_shape, **common_args)
x = net_inputs
with tf.variable_scope('vgg_16', reuse=reuse):
mean_rgb = tf.get_variable(name='mean_rgb',
initializer=tf.truncated_normal(shape=[3]),
trainable=False)
x = x - mean_rgb
with tf.variable_scope('conv1'):
x = conv2d(x, 64, name='conv1_1', **conv_args)
x = conv2d(x, 64, name='conv1_2', **conv_args)
x = max_pool(x, name='maxpool1', **pool_args)
with tf.variable_scope('conv2'):
x = conv2d(x, 128, name='conv2_1', **conv_args)
x = conv2d(x, 128, name='conv2_2', **conv_args)
x = max_pool(x, name='maxpool2', **pool_args)
with tf.variable_scope('conv3'):
x = conv2d(x, 256, name='conv3_1', **conv_args)
x = conv2d(x, 256, name='conv3_2', **conv_args)
x = conv2d(x, 256, name='conv3_3', **conv_args)
x = max_pool(x, name='maxpool3', **pool_args)
with tf.variable_scope('conv4'):
x = conv2d(x, 512, name='conv4_1', **conv_args)
x = conv2d(x, 512, name='conv4_2', **conv_args)
x = conv2d(x, 512, name='conv4_3', **conv_args)
x = max_pool(x, name='maxpool4', **pool_args)
with tf.variable_scope('conv5'):
x = conv2d(x, 512, name='conv5_1', **conv_args)
x = conv2d(x, 512, name='conv5_2', **conv_args)
x = conv2d(x, 512, name='conv5_3', **conv_args)
x = max_pool(x, name='maxpool5', **pool_args)
x = conv2d(x,
4096,
name='fc6',
filter_size=(7, 7),
padding='VALID',
**conv_args)
x = dropout(x, drop_p=0.5, name='dropout6', **common_args)
x = conv2d(x, 4096, name='fc7', filter_size=(1, 1), **conv_args)
x = dropout(x, drop_p=0.5, name='dropout7', **common_args)
x = conv2d(x, 1000, name='fc8', filter_size=(1, 1), **logit_args)
if flexi_inputs:
logits = alias(x, name='logits', **common_args)
else:
logits = squeeze(x, axis=[1, 2], name='logits', **common_args)
predictions = softmax(logits, name='predictions', **common_args)
return end_points(is_training)
def model(inputs, is_training, reuse, num_classes=21, batch_size=1):
common_args = common_layer_args(is_training, reuse)
conv_args = make_args(batch_norm=True, activation=lrelu, w_init=initz.he_normal(
scale=1), untie_biases=False, **common_args)
upsample_args = make_args(
batch_norm=False, activation=lrelu, use_bias=False, **common_args)
logits_args = make_args(
activation=None, **common_args)
pool_args = make_args(padding='SAME', **common_args)
conv1_1 = conv2d(inputs, 64, name="vgg_19/conv1/conv1_1", **conv_args)
conv1_2 = conv2d(conv1_1, 64, name="vgg_19/conv1/conv1_2", **conv_args)
pool1 = max_pool(conv1_2, stride=2, name='pool1', **pool_args)
conv2_1 = conv2d(pool1, 128, name="vgg_19/conv2/conv2_1", **conv_args)
conv2_2 = conv2d(conv2_1, 128, name="vgg_19/conv2/conv2_2", **conv_args)
pool2 = max_pool(conv2_2, stride=2, name='pool2', **pool_args)
conv3_1 = conv2d(pool2, 256, name="vgg_19/conv3/conv3_1", **conv_args)
conv3_2 = conv2d(conv3_1, 256, name="vgg_19/conv3/conv3_2", **conv_args)
conv3_3 = conv2d(conv3_2, 256, name="vgg_19/conv3/conv3_3", **conv_args)
conv3_4 = conv2d(conv3_3, 256, name="vgg_19/conv3/conv3_4", **conv_args)
pool3 = max_pool(conv3_4, stride=2, name='pool3', **pool_args)
conv4_1 = conv2d(pool3, 512, name="vgg_19/conv4/conv4_1", **conv_args)
conv4_2 = conv2d(conv4_1, 512, name="vgg_19/conv4/conv4_2", **conv_args)
conv4_3 = conv2d(conv4_2, 512, name="vgg_19/conv4/conv4_3", **conv_args)
conv4_4 = conv2d(conv4_3, 512, name="vgg_19/conv4/conv4_4", **conv_args)
pool4 = max_pool(conv4_4, stride=2, name='pool4', **pool_args)
conv5_1 = conv2d(pool4, 512, name="vgg_19/conv5/conv5_1", **conv_args)
conv5_2 = conv2d(conv5_1, 512, name="vgg_19/conv5/conv5_2", **conv_args)
conv5_3 = conv2d(conv5_2, 512, name="vgg_19/conv5/conv5_3", **conv_args)
conv5_4 = conv2d(conv5_3, 512, name="vgg_19/conv5/conv5_4", **conv_args)
pool5 = max_pool(conv5_4, stride=2, name='pool5', **pool_args)
fc6 = conv2d(pool5, 4096, filter_size=(7, 7),
name="vgg_19/fc6", **conv_args)
fc6 = dropout(fc6, **common_args)
fc7 = conv2d(fc6, 4096, filter_size=(1, 1), name="vgg_19/fc7", **conv_args)
fc7 = dropout(fc7, **common_args)
score_fr = conv2d(fc7, num_classes, filter_size=(1, 1),
name="score_fr", **conv_args)
pred = tf.argmax(score_fr, axis=3)
pool4_shape = pool4.get_shape().as_list()
upscore2 = upsample2d(score_fr, [batch_size, pool4_shape[1], pool4_shape[2], num_classes], filter_size=(4, 4), stride=(2, 2),
name="deconv2d_1", w_init=initz.bilinear((4, 4, num_classes, num_classes)), **upsample_args)
score_pool4 = conv2d(pool4, num_classes, filter_size=(1, 1),
name="score_pool4", **conv_args)
fuse_pool4 = tf.add(upscore2, score_pool4)
pool3_shape = pool3.get_shape().as_list()
upscore4 = upsample2d(fuse_pool4, [batch_size, pool3_shape[1], pool3_shape[2], num_classes], filter_size=(4, 4), stride=(2, 2),
name="deconv2d_2", w_init=initz.bilinear((4, 4, num_classes, num_classes)), **upsample_args)
score_pool3 = conv2d(pool3, num_classes, filter_size=(1, 1),
name="score_pool3", **conv_args)
fuse_pool3 = tf.add(upscore4, score_pool3)
input_shape = inputs.get_shape().as_list()
upscore32 = upsample2d(fuse_pool3, [batch_size, input_shape[1], input_shape[2], num_classes], filter_size=(16, 16), stride=(8, 8),
name="deconv2d_3", w_init=initz.bilinear((16, 16, num_classes, num_classes)), **logits_args)
logits = register_to_collections(tf.reshape(
upscore32, shape=(-1, num_classes)), name='logits', **common_args)
pred_up = tf.argmax(upscore32, axis=3)
pred_up = register_to_collections(
pred_up, name='final_prediction_map', **common_args)
predictions = softmax(logits, name='predictions', **common_args)
return end_points(is_training)
def make_conv_args(activation, **common_args):
return make_args(use_bias=False,
batch_norm=batch_norm_tf,
batch_norm_args=batch_norm_params,
activation=activation,
**common_args)
def discriminator(inputs, is_training, reuse, num_classes=11, batch_size=32):
common_args = common_layer_args(is_training, reuse)
conv_args = make_args(batch_norm=True,
activation=lrelu,
w_init=initz.he_normal(scale=1),
untie_biases=False,
**common_args)
conv_args_1st = make_args(batch_norm=None,
activation=lrelu,
w_init=initz.he_normal(scale=1),
untie_biases=False,
**common_args)
logits_args = make_args(activation=None,
w_init=initz.he_normal(scale=1),
**common_args)
pool_args = make_args(padding='SAME', **common_args)
end_points = {}
x = inputs
end_points['inputs'] = x
x = dropout(x, drop_p=0.2, name="input_dropout1", **common_args)
x = conv2d(x,
96,
filter_size=(5, 5),
stride=(2, 2),
name="d_conv1_1",
**conv_args_1st)
end_points['d_conv1_1'] = x
x = conv2d(x, 96, name="d_conv1_2", **conv_args)
end_points['d_conv1_2'] = x
x = conv2d(x, 96, stride=(2, 2), name="d_conv1_3", **conv_args)
end_points['d_conv1_3'] = x
x = dropout(x, drop_p=0.2, name="dropout1", **common_args)
x = conv2d(x, 192, name="d_conv2_1", **conv_args)
end_points['d_conv2_1'] = x
x = conv2d(x, 192, name="d_conv2_2", **conv_args)
end_points['d_conv2_2'] = x
x = conv2d(x, 192, stride=(2, 2), name="d_conv2_3", **conv_args)
end_points['d_conv2_3'] = x
x = dropout(x, drop_p=0.2, name="dropout2", **common_args)
x = conv2d(x, 192, stride=(2, 2), name="d_conv3_1", **conv_args)
end_points['d_conv3_1'] = x
x = conv2d(x, 192, filter_size=(1, 1), name="d_conv4_1", **conv_args)
end_points['d_conv4_1'] = x
x = conv2d(x, 192, filter_size=(1, 1), name="d_conv4_2", **conv_args)
end_points['d_conv4_2'] = x
x = global_avg_pool(x, name="global_pool")
end_points['global_pool'] = x
logits = fully_connected(x, num_classes, name="d_logits", **logits_args)
end_points['logits'] = logits
end_points['predictions'] = softmax(logits,
name='predictions',
**common_args)
if is_training:
batch_size = 2 * batch_size
generated_class_logits = tf.squeeze(
tf.slice(logits, [0, num_classes - 1], [batch_size, 1]))
end_points['generated_class_logits'] = generated_class_logits
positive_class_logits = tf.slice(logits, [0, 0],
[batch_size, num_classes - 1])
end_points['positive_class_logits'] = positive_class_logits
max_ = tf.reduce_max(positive_class_logits, 1, keep_dims=True)
safe_pos_class_logits = positive_class_logits - max_
end_points['safe_pos_class_logits'] = safe_pos_class_logits
gan_logits = tf.log(
tf.reduce_sum(tf.exp(safe_pos_class_logits),
1)) + tf.squeeze(max_) - generated_class_logits
end_points['gan_logits'] = gan_logits
assert len(gan_logits.get_shape()) == 1
probs = tf.nn.sigmoid(gan_logits)
end_points['probs'] = probs
class_logits = tf.slice(logits, [0, 0], [batch_size / 2, num_classes])
end_points['class_logits'] = class_logits
D_on_data = tf.slice(probs, [0], [batch_size / 2])
end_points['D_on_data'] = D_on_data
D_on_data_logits = tf.slice(gan_logits, [0], [batch_size / 2])
end_points['D_on_data_logits'] = D_on_data_logits
D_on_G = tf.slice(probs, [batch_size / 2], [batch_size / 2])
end_points['D_on_G'] = D_on_G
D_on_G_logits = tf.slice(gan_logits, [batch_size / 2],
[batch_size / 2])
end_points['D_on_G_logits'] = D_on_G_logits
return end_points
else:
return end_points
def model(inputs,
is_training,
reuse,
num_classes=5,
dropout_keep_prob=0.5,
spatial_squeeze=True,
name='alexnet_v2',
**kwargs):
"""AlexNet version 2.
Described in: http://arxiv.org/pdf/1404.5997v2.pdf
Parameters from:
github.com/akrizhevsky/cuda-convnet2/blob/master/layers/
layers-imagenet-1gpu.cfg
Note: All the fully_connected layers have been transformed to conv2d layers.
To use in classification mode, resize input to 224x224. To use in fully
convolutional mode, set spatial_squeeze to false.
The LRN layers have been removed and change the initializers from
random_normal_initializer to xavier_initializer.
Args:
inputs: a tensor of size [batch_size, height, width, channels].
num_classes: number of predicted classes.
is_training: whether or not the model is being trained.
dropout_keep_prob: the probability that activations are kept in the dropout
layers during training.
spatial_squeeze: whether or not should squeeze the spatial dimensions of the
outputs. Useful to remove unnecessary dimensions for classification.
name: Optional name for the variables.
Returns:
the last op containing the log predictions and end_points dict.
"""
common_args = common_layer_args(is_training, reuse)
conv_args = make_args(batch_norm=True,
activation=prelu,
w_init=initz.he_normal(scale=1),
untie_biases=False,
**common_args)
logit_args = make_args(activation=None,
w_init=initz.he_normal(scale=1),
**common_args)
pred_args = make_args(activation=prelu,
w_init=initz.he_normal(scale=1),
**common_args)
pool_args = make_args(padding='SAME', **common_args)
# inputs = input((None, crop_size[1], crop_size[0], 3), **common_args)
with tf.variable_scope(name, 'alexnet_v2', [inputs]):
net = conv2d(inputs,
64,
filter_size=(11, 11),
stride=(4, 4),
name='conv1',
**conv_args)
net = max_pool(net, stride=(2, 2), name='pool1', **pool_args)
net = conv2d(net, 192, filter_size=(5, 5), name='conv2', **conv_args)
net = max_pool(net, stride=(2, 2), name='pool2', **pool_args)
net = conv2d(net, 384, name='conv3', **conv_args)
net = conv2d(net, 384, name='conv4', **conv_args)
net = conv2d(net, 256, name='conv5', **conv_args)
net = max_pool(net, stride=(2, 2), name='pool5', **pool_args)
# Use conv2d instead of fully_connected layers.
net = conv2d(net, 4096, filter_size=(5, 5), name='fc6', **conv_args)
net = dropout(net,
drop_p=1 - dropout_keep_prob,
name='dropout6',
**common_args)
net = conv2d(net, 4096, filter_size=(1, 1), name='fc7', **conv_args)
net = dropout(net,
drop_p=1 - dropout_keep_prob,
name='dropout7',
**common_args)
net = global_avg_pool(net)
logits = fc(net, num_classes, name='logits', **logit_args)
predictions = softmax(logits, name='predictions', **common_args)
return end_points(is_training)
def model(inputs,
is_training,
reuse,
num_classes=5,
drop_prob=0.2,
name='InceptionResnetV2'):
common_args = common_layer_args(is_training, reuse)
rest_conv_params = make_args(use_bias=False,
batch_norm=batch_norm,
activation=relu,
**common_args)
conv_params_no_bias = make_args(use_bias=False,
batch_norm=batch_norm,
activation=relu,
**common_args)
conv_params = make_args(use_bias=True,
batch_norm=batch_norm,
activation=None,
**common_args)
rest_logit_params = make_args(activation=None, **common_args)
rest_pool_params = make_args(padding='SAME', **common_args)
rest_dropout_params = make_args(drop_p=drop_prob, **common_args)
# inputs = input((None, crop_size[1], crop_size[0], 3), **common_args)
with tf.variable_scope(name, 'InceptionResnetV2'):
net = conv2d(inputs,
32,
stride=(2, 2),
name='Conv2d_1a_3x3',
**conv_params_no_bias)
net = conv2d(net, 32, name='Conv2d_2a_3x3', **conv_params_no_bias)
# 112 x 112
net = conv2d(net, 64, name='Conv2d_2b_3x3', **rest_conv_params)
# 112 x 112
net = max_pool(net, name='MaxPool_3a_3x3', **rest_pool_params)
# 64 x 64
net = conv2d(net,
80,
filter_size=(1, 1),
name='Conv2d_3b_1x1',
**rest_conv_params)
# 64 x 64
net = conv2d(net, 192, name='Conv2d_4a_3x3', **rest_conv_params)
# 64 x 64
net = max_pool(net,
stride=(2, 2),
name='maxpool_5a_3x3',
**rest_pool_params)
# 32 x 32
with tf.variable_scope('Mixed_5b'):
with tf.variable_scope('Branch_0'):
tower_conv = conv2d(net,
96,
filter_size=(1, 1),
name='Conv2d_1x1',
**rest_conv_params)
with tf.variable_scope('Branch_1'):
tower_conv1_0 = conv2d(net,
48,
filter_size=(1, 1),
name='Conv2d_0a_1x1',
**rest_conv_params)
tower_conv1_1 = conv2d(tower_conv1_0,
64,
filter_size=(5, 5),
name='Conv2d_0b_5x5',
**rest_conv_params)
with tf.variable_scope('Branch_2'):
tower_conv2_0 = conv2d(net,
64,
filter_size=(1, 1),
name='Conv2d_0a_1x1',
**rest_conv_params)
tower_conv2_1 = conv2d(tower_conv2_0,
96,
name='Conv2d_0b_3x3',
**rest_conv_params)
tower_conv2_2 = conv2d(tower_conv2_1,
96,
name='Conv2d_0c_3x3',
**rest_conv_params)
with tf.variable_scope('Branch_3'):
tower_pool = avg_pool_2d(net,
stride=(1, 1),
name='avgpool_0a_3x3',
**rest_pool_params)
tower_pool_1 = conv2d(tower_pool,
64,
filter_size=(1, 1),
name='Conv2d_0b_1x1',
**rest_conv_params)
net = tf.concat(
[tower_conv, tower_conv1_1, tower_conv2_2, tower_pool_1], 3)
with tf.variable_scope('Repeat'):
for i in range(1, 11):
net = block35(net,
name='block35_' + str(i),
scale=0.17,
**conv_params_no_bias)
# 32 x 32
with tf.variable_scope('Mixed_6a'):
with tf.variable_scope('Branch_0'):
tower_conv = conv2d(net,
384,
stride=(2, 2),
name='Conv2d_1a_3x3',
**rest_conv_params)
with tf.variable_scope('Branch_1'):
tower_conv1_0 = conv2d(net,
256,
filter_size=(1, 1),
name='Conv2d_0a_1x1',
**rest_conv_params)
tower_conv1_1 = conv2d(tower_conv1_0,
256,
name='Conv2d_0b_3x3',
**rest_conv_params)
tower_conv1_2 = conv2d(tower_conv1_1,
384,
stride=(2, 2),
name='Conv2d_1a_3x3',
**rest_conv_params)
with tf.variable_scope('Branch_2'):
tower_pool = max_pool(net,
name='maxpool_1a_3x3',
**rest_pool_params)
net = tf.concat([tower_conv, tower_conv1_2, tower_pool], 3)
with tf.variable_scope('Repeat_1'):
for i in range(1, 21):
net = block17(net,
name='block17_' + str(i),
scale=0.10,
**conv_params_no_bias)
with tf.variable_scope('Mixed_7a'):
with tf.variable_scope('Branch_0'):
tower_conv = conv2d(net,
256,
filter_size=(1, 1),
name='Conv2d_0a_1x1',
**rest_conv_params)
tower_conv_1 = conv2d(tower_conv,
384,
stride=(2, 2),
name='Conv2d_1a_3x3',
**rest_conv_params)
with tf.variable_scope('Branch_1'):
tower_conv1 = conv2d(net,
256,
filter_size=(1, 1),
name='Conv2d_0a_1x1',
**rest_conv_params)
tower_conv1_1 = conv2d(tower_conv1,
288,
stride=(2, 2),
name='Conv2d_1a_3x3',
**rest_conv_params)
with tf.variable_scope('Branch_2'):
tower_conv2 = conv2d(net,
256,
filter_size=(1, 1),
name='Conv2d_0a_1x1',
**rest_conv_params)
tower_conv2_1 = conv2d(tower_conv2,
288,
name='Conv2d_0b_3x3',
**rest_conv_params)
tower_conv2_2 = conv2d(tower_conv2_1,
320,
stride=(2, 2),
name='Conv2d_1a_3x3',
**rest_conv_params)
with tf.variable_scope('Branch_3'):
tower_pool = max_pool(net,
name='maxpool_1a_3x3',
**rest_pool_params)
net = tf.concat(
[tower_conv_1, tower_conv1_1, tower_conv2_2, tower_pool], 3)
# 8 x 8
with tf.variable_scope('Repeat_2'):
for i in range(1, 10):
net = block8(net,
name='block8_' + str(i),
scale=0.20,
**conv_params_no_bias)
net = block8(net, name='Block8', **conv_params_no_bias)
net = conv2d(net,
1536,
filter_size=(1, 1),
name='Conv2d_7b_1x1',
**rest_conv_params)
with tf.variable_scope('Logits'):
net = global_avg_pool(net, name='avgpool_1a_8x8')
net = dropout(net, name='dropout', **rest_dropout_params)
logits = fully_connected(net,
num_classes,
name='Logits',
**rest_logit_params)
predictions = softmax(logits, name='Predictions', **common_args)
return end_points(is_training)
def vgg_16(is_training, reuse,
num_classes=1000,
dropout_keep_prob=0.5,
spatial_squeeze=True,
name='vgg_16'):
"""Oxford Net VGG 16-Layers version D Example.
Note: All the fully_connected layers have been transformed to conv2d layers.
To use in classification mode, resize input to 224x224.
Args:
inputs: a tensor of size [batch_size, height, width, channels].
num_classes: number of predicted classes.
is_training: whether or not the model is being trained.
dropout_keep_prob: the probability that activations are kept in the dropout
layers during training.
spatial_squeeze: whether or not should squeeze the spatial dimensions of the
outputs. Useful to remove unnecessary dimensions for classification.
name: Optional name for the variables.
Returns:
the last op containing the log predictions and end_points dict.
"""
common_args = common_layer_args(is_training, reuse)
conv_args = make_args(batch_norm=True, activation=prelu, w_init=initz.he_normal(
scale=1), untie_biases=False, **common_args)
logit_args = make_args(
activation=None, w_init=initz.he_normal(scale=1), **common_args)
pred_args = make_args(
activation=prelu, w_init=initz.he_normal(scale=1), **common_args)
pool_args = make_args(padding='SAME', **common_args)
inputs = input((None, crop_size[1], crop_size[0], 3), **common_args)
with tf.variable_scope(name, 'vgg_16', [inputs]):
net = repeat(inputs, 2, conv2d,
64, filter_size=(3, 3), name='conv1', **conv_args)
net = max_pool(net, name='pool1', **pool_args)
net = repeat(net, 2, conv2d, 128, filter_size=(
3, 3), name='conv2', **conv_args)
net = max_pool(net, name='pool2', **pool_args)
net = repeat(net, 3, conv2d, 256, filter_size=(
3, 3), name='conv3', **conv_args)
net = max_pool(net, name='pool3', **pool_args)
net = repeat(net, 3, conv2d, 512, filter_size=(
3, 3), name='conv4', **conv_args)
net = max_pool(net, name='pool4', **pool_args)
net = repeat(net, 3, conv2d, 512, filter_size=(
3, 3), name='conv5', **conv_args)
net = max_pool(net, name='pool5', **pool_args)
# Use conv2d instead of fully_connected layers.
net = conv2d(net, 4096, filter_size=(7, 7), name='fc6', **conv_args)
net = dropout(net, drop_p=1 - dropout_keep_prob, is_training=is_training,
name='dropout6', **common_args)
net = conv2d(net, 4096, filter_size=(1, 1), name='fc7', **conv_args)
net = dropout(net, drop_p=1 - dropout_keep_prob, is_training=is_training,
name='dropout7', **common_args)
logits = conv2d(net, num_classes, filter_size=(1, 1),
activation=None,
name='logits', **logit_args)
# Convert end_points_collection into a end_point dict.
if spatial_squeeze:
logits = tf.squeeze(logits, [1, 2], name='logits/squeezed')
predictions = softmax(logits, name='predictions', **pred_args)
return end_points(is_training)
