def classify(inputs,
num_classes,
dropout_keep_prob=0.5,
scope='cnn_v4',
reuse=None,
is_training=True):
"""
model used to make predictions
input: x -> shape=[None,bands,frames,num_channels]
output: logits -> shape=[None,num_labels]
"""
with slim.arg_scope(simple_arg_scope()):
#with slim.arg_scope(batchnorm_arg_scope()):
with slim.arg_scope([slim.batch_norm, slim.dropout],
is_training=is_training):
with tf.variable_scope(scope, [inputs], reuse=reuse) as scope:
net = tf.expand_dims(
inputs, -1
) #input needs to be in the format NHWC!! if there is only one channel, expand it by 1 dimension
print('model input shape: %s' % net.get_shape())
net = slim.repeat(net,
2,
slim.conv2d,
64, [3, 9],
scope='conv1')
net = slim.max_pool2d(net, [2, 2], scope='pool1')
net = slim.repeat(net,
3,
slim.conv2d,
128, [3, 5],
scope='conv2')
net = slim.max_pool2d(net, [2, 2], scope='pool2')
net = slim.repeat(net,
3,
slim.conv2d,
256, [3, 3],
scope='conv3')
net = slim.max_pool2d(net, [2, 2], scope='pool3')
net = slim.flatten(net)
net = slim.fully_connected(net, 4096, scope='fc1')
net = slim.dropout(net,
dropout_keep_prob,
is_training=is_training,
scope='dropout1')
net = slim.fully_connected(net, 4096, scope='fc2')
net = slim.dropout(net,
dropout_keep_prob,
is_training=is_training,
scope='dropout2')
logits = slim.fully_connected(net,
num_classes,
scope='fc3',
activation_fn=None)
return logits
def classify(inputs,
num_estimator,
num_classes,
dropout_keep_prob=0.5,
middle_size=3,
gamma_decay=1e-6,
weight_decay=0.,
scope=None,
reuse=None,
is_training=True):
"""
model used to make predictions
input: x -> shape=[None,bands,frames,num_channels]
output: logits -> shape=[None,num_labels]
"""
with slim.arg_scope(simple_arg_scope(weight_decay=weight_decay)):
#with slim.arg_scope(batchnorm_arg_scope()):
with slim.arg_scope([slim.batch_norm, slim.dropout],
is_training=is_training):
with tf.variable_scope(scope, 'model_v1', [inputs],
reuse=reuse) as scope:
net = tf.expand_dims(
inputs, -1
) #input needs to be in the format NHWC!! if there is only one channel, expand it by 1 dimension
with tf.variable_scope('bottom'):
net = slim.conv2d(net, 32, [3, 3], rate=2, scope='convB1')
net = slim.max_pool2d(net, [2, 2], scope='poolB1')
#random block
with tf.variable_scope('middle'):
net = slim.repeat(net,
middle_size,
slim.conv2d,
32, [3, 3],
scope='convM') #, reuse=i>0
net = slim.max_pool2d(net, [2, 1], scope='poolM')
# Use conv2d instead of fully_connected layers.
with tf.variable_scope('top'):
net = slim.flatten(net)
net = slim.fully_connected(net, 64, scope='fc1')
net = slim.dropout(net,
dropout_keep_prob,
is_training=is_training,
scope='dropout1')
logits = slim.fully_connected(net,
num_classes,
scope='fc2',
activation_fn=None)
gamma = tf.Variable(1. / (num_estimator), name='gamma')
tf.losses.add_loss(
tf.nn.l2_loss(gamma),
loss_collection=tf.GraphKeys.REGULARIZATION_LOSSES)
return logits, gamma
def classify(x,
num_classes,
num_filter,
dropout_keep_prob=0.5,
weight_decay=5e-4,
scope='model_v1',
reuse=None,
route=3,
is_training=True):
"""
model used to make predictions
input: x -> shape=[None,bands,frames,num_channels]
output: logits -> shape=[None,num_labels]
"""
with slim.arg_scope(simple_arg_scope(weight_decay=weight_decay)):
#with slim.arg_scope(batchnorm_arg_scope()):
with slim.arg_scope([slim.batch_norm, slim.dropout],
is_training=is_training):
with tf.variable_scope(scope, [x], reuse=reuse) as sc:
net = tf.expand_dims(
x, -1
) #input needs to be in the format NHWC!! if there is only one channel, expand it by 1 dimension
with tf.variable_scope('stump'):
net = slim.conv2d(net, 16, [1, 7], scope='conv1x7')
net = slim.max_pool2d(net, [1, 2],
stride=[1, 2],
scope='pool1')
net = slim.conv2d(net, num_filter, [1, 5], scope='conv1x5')
with tf.variable_scope('middle'):
for i in range(route):
net = slim.max_pool2d(net, [1, 2],
stride=[1, 2],
scope='pool%d' % (i + 2))
net = slim.conv2d(net,
num_filter, [3, 3],
scope='conv3x3_%d' % (i + 2))
#net = tf.reduce_max(net, 2)
with tf.variable_scope('top'):
net = slim.flatten(net)
net = slim.dropout(net,
dropout_keep_prob,
is_training=is_training,
scope='dropout1')
logits = slim.fully_connected(net,
num_classes,
scope='fc2',
activation_fn=None)
return logits
def classify(inputs,
num_estimator,
num_classes,
dropout_keep_prob=0.5,
middle_size=6,
gamma_decay=1e-6,
weight_decay=0.,
scope=None,
reuse=None,
is_training=True):
"""
model used to make predictions
input: x -> shape=[None,bands,frames,num_channels]
output: logits -> shape=[None,num_labels]
"""
with slim.arg_scope(simple_arg_scope(weight_decay=weight_decay)):
#with slim.arg_scope(batchnorm_arg_scope()):
with slim.arg_scope([slim.batch_norm, slim.dropout],
is_training=is_training):
with tf.variable_scope(scope, 'model_v1', [inputs],
reuse=reuse) as scope:
net = tf.expand_dims(
inputs, -1
) #input needs to be in the format NHWC!! if there is only one channel, expand it by 1 dimension
net = slim.conv2d(net, 64, [3, 9], scope='conv1')
net = slim.max_pool2d(net, [1, 2], scope='pool1')
net = slim.conv2d(net, 128, [3, 5], scope='conv2')
net = slim.max_pool2d(net, [1, 2], scope='pool2')
net = slim.flatten(net)
net = slim.fully_connected(net, 256, scope='fc1')
net = slim.dropout(net,
dropout_keep_prob,
is_training=is_training,
scope='dropout1')
logits = slim.fully_connected(net,
num_classes,
scope='fc2',
activation_fn=None)
return logits
def classify(inputs,
num_classes,
dropout_keep_prob=0.5,
middle_size=1,
bottom_size=1,
weight_decay=1e-5,
fc_size=16,
num_filter=16,
scope=None,
reuse=None,
is_training=True):
"""
model used to make predictions
input: x -> shape=[None,bands,frames,num_channels]
output: logits -> shape=[None,num_labels]
"""
with slim.arg_scope(simple_arg_scope(weight_decay=weight_decay)):
#with slim.arg_scope(batchnorm_arg_scope()):
with slim.arg_scope([slim.batch_norm, slim.dropout],
is_training=is_training):
with tf.variable_scope(scope, 'model_v1', [inputs],
reuse=reuse) as scope:
net = tf.expand_dims(
inputs, -1
) #input needs to be in the format NHWC!! if there is only one channel, expand it by 1 dimension
with tf.variable_scope('bottom'):
#net = slim.conv2d(net, num_filter, [4, 4], rate=2, scope='convB1')
net = slim.repeat(net,
bottom_size,
slim.conv2d,
num_filter, [3, 9],
scope='convB2')
net = slim.max_pool2d(net, [1, 2],
stride=[1, 2],
scope='poolB1')
#random block
with tf.variable_scope('middle'):
net = slim.repeat(net,
middle_size,
slim.conv2d,
num_filter, [3, 5],
scope='convM1') #, reuse=i>0
net = slim.max_pool2d(net, [1, 2],
stride=[1, 2],
scope='poolM')
net = slim.repeat(net,
middle_size,
slim.conv2d,
num_filter, [3, 3],
scope='convM2') #, reuse=i>0
net = slim.max_pool2d(net, [1, 2],
stride=[1, 2],
scope='poolM')
net = slim.repeat(net,
middle_size,
slim.conv2d,
num_filter, [3, 3],
scope='convM3') #, reuse=i>0
net = slim.max_pool2d(net, [1, 2],
stride=[1, 2],
scope='poolM')
#net = slim.repeat(net, middle_size, slim.conv2d, num_filter, [3, 3], scope='convM4') #, reuse=i>0
#net = slim.max_pool2d(net, [1, 2], stride=[1, 2], scope='poolM')
# Use conv2d instead of fully_connected layers.
with tf.variable_scope('top'):
net = slim.flatten(net)
net = slim.fully_connected(net, fc_size, scope='fc1')
net = slim.dropout(net,
dropout_keep_prob,
is_training=is_training,
scope='dropout1')
logits = slim.fully_connected(net,
num_classes,
scope='fc2',
activation_fn=None)
return logits
def classify(
x,
num_classes,
num_layers=[2, 2, 2], #,2],
scope='resnet_18_v1',
reuse=None,
is_training=True):
"""
resnet-18 used to make predictions
"""
with slim.arg_scope(simple_arg_scope()):
with slim.arg_scope(batchnorm_arg_scope()):
with slim.arg_scope([slim.batch_norm, slim.dropout],
is_training=is_training):
with slim.arg_scope(
[slim.conv2d],
weights_initializer=slim.variance_scaling_initializer(
seed=0)):
with tf.variable_scope(scope, [x], reuse=reuse) as sc:
x = tf.expand_dims(
x, -1
) #input needs to be in the format NHWC!! if there is only one channel, expand it by 1 dimension
num_blocks = len(num_layers)
stride = 1
# initial convolution
with tf.variable_scope('bottom', [x]):
shortcut = x = slim.conv2d(x,
64, [3, 7],
scope='convInit')
#shortcut = x = slim.avg_pool2d(x, [1,2], 2)
#resnet blocks
for i in range(num_blocks):
with tf.variable_scope("block%d" % i):
depth = 2**(i + 6) #64,128,256,512
for j in range(num_layers[i]):
residual = slim.conv2d(x,
depth, [3, 3],
stride,
scope='convA%d.%d' %
(i, j))
residual = slim.conv2d(residual,
depth, [3, 3],
activation_fn=None,
scope='convB%d.%d' %
(i, j))
shortcut = x = tf.nn.relu(shortcut +
residual)
stride = 1
if i + 1 < num_blocks:
shortcut = slim.conv2d(x,
2**(i + 6 + 1),
1,
stride=2,
scope='convS.%d' %
i)
stride = 2
#print (x.get_shape())
# initial convolution
with tf.variable_scope('top', [x]):
x = tf.reduce_mean(x, [1, 2], name='global_pool')
logits = slim.fully_connected(x,
num_classes,
scope='logits',
activation_fn=None)
return logits
