def inference(inputs,
num_classes,
routing_ites=4,
remake=False,
training=False,
name='capsnet_1d'):
"""
:param inputs:
:param num_classes:
:param routing_ites:
:param remake:
:param name:
:return:
"""
with tf.variable_scope(name) as scope:
inputs_shape = inputs.get_shape()
batch_size = inputs_shape[0].value
image_height = inputs_shape[2].value
image_width = inputs_shape[3].value
# ReLU Conv1
# Images shape (b, 1, 24, 56) -> conv 5x5 filters, 32 output channels, strides 2 with padding, ReLU
# nets -> (b, 256, 16, 48)
print('inputs shape: %s' % inputs.get_shape())
inputs = tf.check_numerics(inputs, message="nan or inf from: inputs")
conv1 = conv2d(inputs,
kernel=3,
out_channels=32,
stride=1,
padding='SAME',
activation_fn=tf.nn.relu,
normalizer_fn=tf.contrib.layers.batch_norm,
name='relu_conv1')
print('conv1 shape: %s' % conv1.get_shape())
pool1 = tf.nn.max_pool(conv1,
ksize=[1, 1, 2, 2],
strides=[1, 1, 2, 2],
padding='VALID',
data_format='NCHW',
name='pool1')
print('pool1 shape: %s' % pool1.get_shape())
conv2 = conv2d(pool1,
kernel=3,
out_channels=64,
stride=1,
padding='SAME',
activation_fn=tf.nn.relu,
normalizer_fn=tf.contrib.layers.batch_norm,
name='relu_conv2')
print('conv2 shape: %s' % conv2.get_shape())
pool2 = tf.nn.max_pool(conv2,
ksize=[1, 1, 2, 2],
strides=[1, 1, 2, 2],
padding='VALID',
data_format='NCHW',
name='pool2')
print('pool2 shape: %s' % pool2.get_shape())
pool2_dropout = tf.layers.dropout(pool2,
0.5,
training=training,
name='pool2_dropout')
# conv3 = conv2d(
# pool2,
# kernel=3, out_channels=128, stride=1, padding='SAME',
# activation_fn=tf.nn.relu, normalizer_fn=tf.contrib.layers.batch_norm,
# name='relu_conv3'
# )
# print('conv3 shape: %s' % conv3.get_shape())
# pool3 = tf.nn.max_pool(
# conv3,
# ksize=[1, 1, 2, 2], strides=[1, 1, 2, 2],
# padding='VALID', data_format='NCHW', name='pool3'
# )
# print('pool3 shape: %s' % pool3.get_shape())
print("\nprimary layer:")
primary_out_capsules = 32
primary_caps_activations, conv_primary = primary_caps1d(
pool2_dropout,
kernel_size=3,
out_capsules=primary_out_capsules,
stride=1,
padding='VALID',
activation_length=8,
name='primary_caps') # (b, 32, 4, 20, 8)
print("\nclass capsule layer:")
class_caps_activations, class_coupling_coeffs = class_caps1d(
primary_caps_activations,
num_classes=num_classes,
activation_length=16,
routing_ites=routing_ites,
batch_size=batch_size,
name='class_capsules')
# class_coupling_coeffs = tf.Print(class_coupling_coeffs, [class_coupling_coeffs], summarize=50)
# class_caps_activations = tf.check_numerics(class_caps_activations, message="nan or inf from: class_caps_activations")
print('class_coupling_coeffs shape: %s' %
class_coupling_coeffs.get_shape())
print('class_caps_activations shape: %s' %
class_caps_activations.get_shape())
if remake:
remakes_flatten = _remake(class_caps_activations,
image_height * image_width)
else:
remakes_flatten = None
print("\ndecode layers:")
label_logits = _decode(primary_caps_activations,
primary_out_capsules,
coupling_coeffs=class_coupling_coeffs,
num_classes=num_classes,
batch_size=batch_size,
pool1=pool1,
pool2=pool2,
training=training)
# label_logits = tf.Print(label_logits, [tf.constant("label_logits"), label_logits[0]], summarize=100)
# label_logits = tf.check_numerics(label_logits, message="nan or inf from: label_logits")
labels2d = tf.argmax(label_logits, axis=3)
labels2d_expanded = tf.expand_dims(labels2d, -1)
tf.summary.image('labels', tf.cast(labels2d_expanded, tf.uint8))
return class_caps_activations, remakes_flatten, label_logits
def inference(inputs,
num_classes,
routing_ites=3,
remake=False,
training=False,
name='capsnet_1d'):
"""
:param inputs:
:param num_classes:
:param routing_ites:
:param remake:
:param name:
:return:
"""
with tf.variable_scope(name) as scope:
inputs_shape = inputs.get_shape()
batch_size = inputs_shape[0].value
image_height = inputs_shape[2].value
image_width = inputs_shape[3].value
# ReLU Conv1
# Images shape (b, 1, 24, 56) -> conv 5x5 filters, 32 output channels, strides 2 with padding, ReLU
# nets -> (b, 256, 16, 48)
print('inputs shape: %s' % inputs.get_shape())
inputs = tf.check_numerics(inputs, message="nan or inf from: inputs")
print("\nconv1 layer:")
conv1 = conv2d(inputs,
kernel=9,
out_channels=256,
stride=1,
padding='VALID',
activation_fn=tf.nn.relu,
name='relu_conv1')
# conv1 = tf.check_numerics(conv1, message="nan or inf from: conv1")
print('conv1 shape: %s' % conv1.get_shape())
# print("\nconv2 layer:")
# conv2 = conv2d(
# conv1,
# kernel=5, out_channels=256, stride=1, padding='VALID',
# activation_fn=tf.nn.relu, name='relu_conv2'
# )
# # conv2 = tf.check_numerics(conv2, message="nan or inf from: conv2")
# print('conv2 shape: %s' % conv2.get_shape())
# PrimaryCaps
# (b, 256, 16, 48) -> capsule 1x1 filter, 32 output capsule, strides 1 without padding
# nets -> activations (?, 14, 14, 32))
print("\nprimary layer:")
primary_out_capsules = 24
primary_caps_activations, conv2 = primary_caps1d(
conv1,
kernel_size=7,
out_capsules=primary_out_capsules,
stride=2,
padding='VALID',
activation_length=8,
name='primary_caps') # (b, 32, 4, 20, 8)
# (b, 32, 4, 20, 8) -> # (b, 32*4*20, 2*64)
print("\nclass capsule layer:")
class_caps_activations, class_coupling_coeffs = class_caps1d(
primary_caps_activations,
num_classes=num_classes,
activation_length=16,
routing_ites=routing_ites,
batch_size=batch_size,
name='class_capsules')
# class_coupling_coeffs = tf.Print(class_coupling_coeffs, [class_coupling_coeffs], summarize=50)
# class_caps_activations = tf.check_numerics(class_caps_activations, message="nan or inf from: class_caps_activations")
print('class_coupling_coeffs shape: %s' %
class_coupling_coeffs.get_shape())
print('class_caps_activations shape: %s' %
class_caps_activations.get_shape())
if remake:
remakes_flatten = _remake(class_caps_activations,
image_height * image_width)
else:
remakes_flatten = None
print("\ndecode layers:")
label_logits = _decode(primary_caps_activations,
primary_out_capsules,
coupling_coeffs=class_coupling_coeffs,
num_classes=num_classes,
batch_size=batch_size,
conv1=conv1,
conv2=conv2)
# label_logits = tf.Print(label_logits, [tf.constant("label_logits"), label_logits[0]], summarize=100)
# label_logits = tf.check_numerics(label_logits, message="nan or inf from: label_logits")
labels2d = tf.argmax(label_logits, axis=3)
labels2d_expanded = tf.expand_dims(labels2d, -1)
tf.summary.image('labels', tf.cast(labels2d_expanded, tf.uint8))
return class_caps_activations, remakes_flatten, label_logits
def inference(inputs, num_classes, routing_ites=3, remake=False, training=False, name='capsnet_1d'):
"""
:param inputs:
:param num_classes:
:param routing_ites:
:param remake:
:param name:
:return:
"""
with tf.variable_scope(name) as scope:
inputs_shape = inputs.get_shape()
batch_size = inputs_shape[0].value
image_height = inputs_shape[2].value
image_width = inputs_shape[3].value
# ReLU Conv1
# Images shape (b, 1, 24, 56) -> conv 5x5 filters, 32 output channels, strides 2 with padding, ReLU
# nets -> (b, 256, 16, 48)
print('inputs shape: %s' % inputs.get_shape())
inputs = tf.check_numerics(inputs, message="nan or inf from: inputs")
conv1 = conv2d(
inputs,
kernel=3, out_channels=32, stride=1, padding='SAME',
activation_fn=tf.nn.relu, normalizer_fn=tf.contrib.layers.batch_norm,
name='relu_conv1'
)
print('conv1 shape: %s' % conv1.get_shape())
pool1 = tf.nn.max_pool(
conv1,
ksize=[1, 1, 2, 2], strides=[1, 1, 2, 2],
padding='VALID', data_format='NCHW', name='pool1'
)
print('pool1 shape: %s' % pool1.get_shape())
# pool1_dropout = tf.layers.dropout(pool1, 0.5, training=training, name='pool1_dropout')
# conv2 = conv2d(
# pool1,
# kernel=3, out_channels=64, stride=1, padding='VALID',
# activation_fn=tf.nn.relu, normalizer_fn=tf.contrib.layers.batch_norm,
# name='relu_conv2'
# )
# print('conv2 shape: %s' % conv2.get_shape())
# pool2 = tf.nn.max_pool(
# conv2,
# ksize=[1, 1, 2, 2], strides=[1, 1, 2, 2],
# padding='VALID', data_format='NCHW', name='pool2'
# )
# print('pool2 shape: %s' % pool2.get_shape())
# pool2_dropout = tf.layers.dropout(pool2, 0.5, training=training, name='pool2_dropout')
# conv3 = conv2d(
# pool2,
# kernel=3, out_channels=128, stride=1, padding='SAME',
# activation_fn=tf.nn.relu, normalizer_fn=tf.contrib.layers.batch_norm,
# name='relu_conv3'
# )
# print('conv3 shape: %s' % conv3.get_shape())
# pool3 = tf.nn.max_pool(
# conv3,
# ksize=[1, 1, 2, 2], strides=[1, 1, 2, 2],
# padding='VALID', data_format='NCHW', name='pool3'
# )
# print('pool3 shape: %s' % pool3.get_shape())
print("\nprimary layer:")
primary_out_capsules = 64
primary_caps_activations, _ = primary_caps1d(
pool1,
kernel_size=3, out_capsules=primary_out_capsules, stride=1,
padding='VALID', activation_length=3, name='primary_caps'
) # (b, 32, 4, 20, 8)
# primary_caps_activations = tf.check_numerics(primary_caps_activations,
# message="nan or inf from: primary_caps_activations")
print("\nconvolutional capsule layer 1:")
conv_out_capsules_1 = 32
conv_kernel_size_1, conv_stride_1 = 4, 2
conv_caps_activations_1, conv_coupling_coeffs_1 = conv_capsule1d(
primary_caps_activations,
kernel_size=conv_kernel_size_1, stride=conv_stride_1, routing_ites=3,
in_capsules=primary_out_capsules, out_capsules=conv_out_capsules_1,
activation_length=4, training=training, name="conv_caps_1"
) # (b, 32, 6, 6, 8), (b*6*6, 32*9, 32)
conv_caps_activations_1 = tf.check_numerics(conv_caps_activations_1,
message="nan or inf from: conv_caps_activations_1")
print("\nconvolutional capsule layer 2:")
conv_out_capsules_2 = 24
conv_kernel_size_2, conv_stride_2 = 3, 1
conv_caps_activations_2, conv_coupling_coeffs_2 = conv_capsule1d(
conv_caps_activations_1,
kernel_size=conv_kernel_size_2, stride=conv_stride_2, routing_ites=3,
in_capsules=conv_out_capsules_1, out_capsules=conv_out_capsules_2,
activation_length=8, training=training, name="conv_caps_2"
) # (b, 32, 6, 6, 8), (b*6*6, 32*9, 32)
conv_caps_activations_2 = tf.check_numerics(conv_caps_activations_2,
message="nan or inf from: conv_caps_activations_2")
print("\nclass capsule layer:")
class_caps_activations, class_coupling_coeffs = class_caps1d(
conv_caps_activations_2,
num_classes=num_classes, activation_length=16, routing_ites=routing_ites,
batch_size=batch_size, training=training, name='class_capsules')
# class_coupling_coeffs = tf.Print(class_coupling_coeffs, [class_coupling_coeffs], summarize=50)
class_caps_activations = tf.check_numerics(class_caps_activations,
message="nan or inf from: class_caps_activations")
print('class_coupling_coeffs shape: %s' % class_coupling_coeffs.get_shape())
print('class_caps_activations shape: %s' % class_caps_activations.get_shape())
if remake:
remakes_flatten = _remake(class_caps_activations, image_height * image_width)
else:
remakes_flatten = None
print("\ntraceback layer 1:")
conv_activations_2_shape = conv_caps_activations_2.get_shape() # (b, 32, 4, 20, 8),
conv_height_2, conv_width_2 = conv_activations_2_shape[2].value, conv_activations_2_shape[3].value
conv_1_cond_prob = trace_conv_cond_prob(class_coupling_coeffs, conv_coupling_coeffs_2,
conv_height_2, conv_width_2, conv_kernel_size_2, conv_stride_2,
conv_out_capsules_2, conv_out_capsules_1)
print("\ntraceback layer 2:")
conv_activations_1_shape = conv_caps_activations_1.get_shape() # (b, 32, 4, 20, 8),
conv_height_1, conv_width_1 = conv_activations_1_shape[2].value, conv_activations_1_shape[3].value
primary_cond_prob = trace_conv_cond_prob(conv_1_cond_prob, conv_coupling_coeffs_1,
conv_height_1, conv_width_1, conv_kernel_size_1, conv_stride_1,
conv_out_capsules_1, primary_out_capsules)
primary_labels = trace_labels(primary_caps_activations, primary_cond_prob, num_classes)
print('primary_caps_labels shape: %s' % primary_labels.get_shape())
# class_labels = tf.Print(class_labels, [tf.constant("class_labels"), class_labels])
# class_labels = tf.check_numerics(class_labels, message="nan or inf from: class_labels")
# primary_labels = tf.reduce_sum(caps_probs_tiled, 1)
print("\ndeconv layers:")
primary_conv = conv2d(
tf.transpose(primary_labels, perm=[0, 3, 1, 2]),
kernel=3, out_channels=256, stride=1, padding='SAME',
activation_fn=tf.nn.relu, name='primary_conv'
)
print('primary_conv shape: %s' % primary_conv.get_shape())
deconv1 = deconv(
primary_conv,
kernel=3, out_channels=128, stride=1, data_format='NCHW',
activation_fn=tf.nn.relu, normalizer_fn=tf.contrib.layers.batch_norm,
name='deconv1'
)
print('deconv2 shape: %s' % deconv1.get_shape())
concat1 = tf.concat([pool1, deconv1], axis=1, name='concat1')
# dropout2 = tf.layers.dropout(concat2, 0.5, training=training, name='dropout2')
concat1_conv = conv2d(
concat1,
kernel=3, out_channels=128, stride=1, padding='SAME',
activation_fn=tf.nn.relu, normalizer_fn=tf.contrib.layers.batch_norm,
name='concat1_conv'
)
print('deconv1_conv shape: %s' % concat1_conv.get_shape())
deconv2 = deconv(
concat1_conv,
kernel=4, out_channels=128, stride=2, data_format='NCHW',
activation_fn=tf.nn.relu, normalizer_fn=tf.contrib.layers.batch_norm,
name='deconv2'
)
print('deconv2 shape: %s' % deconv2.get_shape())
class_conv = conv2d(
deconv2,
kernel=3, out_channels=num_classes, stride=1, padding='VALID',
name='class_conv'
)
print('class_conv shape: %s' % class_conv.get_shape())
label_logits = tf.transpose(class_conv, perm=[0, 2, 3, 1])
print('label_logits shape: %s' % label_logits.get_shape())
# label_logits = tf.Print(label_logits, [tf.constant("label_logits"), label_logits])
labels2d = tf.argmax(label_logits, axis=3)
labels2d_expanded = tf.expand_dims(labels2d, -1)
tf.summary.image('labels', tf.cast(labels2d_expanded, tf.uint8))
return class_caps_activations, remakes_flatten, label_logits
def inference(inputs,
num_classes,
training=True,
routing_ites=3,
name='unet_pascal'):
with tf.variable_scope(name) as scope:
inputs_shape = inputs.get_shape()
batch_size = inputs_shape[0].value
combine_conv1 = _combine_conv(inputs, '1', training, out_channels=16)
combine_conv2 = _combine_conv(combine_conv1,
'2',
training,
out_channels=32)
combine_conv3 = _combine_conv(combine_conv2,
'3',
training,
out_channels=64)
combine_conv4 = _combine_conv(combine_conv3,
'4',
training,
out_channels=128)
print("\nprimary layer:")
primary_out_capsules = 32
primary_caps_activations, primary_conv = primary_caps1d(
combine_conv4,
kernel_size=5,
out_capsules=primary_out_capsules,
stride=2,
padding='VALID',
activation_length=8,
name='primary_caps')
print('primary_conv shape: %s' % primary_conv.get_shape())
print("\nclass capsule layer:")
class_caps_activations, class_coupling_coeffs = class_caps1d(
primary_caps_activations,
num_classes=num_classes,
activation_length=16,
routing_ites=routing_ites,
batch_size=batch_size,
name='class_capsules')
print('class_coupling_coeffs shape: %s' %
class_coupling_coeffs.get_shape())
print('class_caps_activations shape: %s' %
class_caps_activations.get_shape())
capsule_probs = tf.norm(primary_caps_activations, axis=-1)
caps_probs_tiled = tf.tile(tf.expand_dims(capsule_probs, -1),
[1, 1, 1, 1, num_classes])
primary_activations_shape = primary_caps_activations.get_shape()
height, width = primary_activations_shape[
2].value, primary_activations_shape[3].value
coupling_coeff_reshaped = tf.reshape(
class_coupling_coeffs,
[batch_size, primary_out_capsules, height, width, num_classes])
primary_labels = tf.reduce_sum(
coupling_coeff_reshaped * caps_probs_tiled, 1)
print('\nprimary_labels shape: %s\n' % primary_labels.get_shape())
concat1 = tf.concat(
[primary_conv,
tf.transpose(primary_labels, perm=[0, 3, 1, 2])],
axis=1,
name='concat1')
primary_label_conv = conv2d(concat1,
kernel=3,
out_channels=128,
stride=1,
padding='SAME',
activation_fn=tf.nn.relu,
data_format='NCHW',
name='primary_label_conv')
combine_deconv5 = _combine_deconv(primary_label_conv,
'5',
training,
combine_conv4,
deconv_out_channels=256)
combine_deconv4 = _combine_deconv(combine_deconv5,
'4',
training,
combine_conv3,
kernel_deconv=[7, 7],
deconv_out_channels=128)
combine_deconv3 = _combine_deconv(combine_deconv4,
'3',
training,
combine_conv2,
kernel_deconv=[6, 6],
deconv_out_channels=64)
combine_deconv2 = _combine_deconv(combine_deconv3,
'2',
training,
combine_conv1,
kernel_deconv=[6, 7],
deconv_out_channels=64)
combine_deconv1 = _combine_deconv(combine_deconv2,
'1',
training,
None,
kernel_deconv=[6, 7],
deconv_out_channels=32)
conv = conv2d(combine_deconv1,
kernel=3,
out_channels=num_classes,
stride=1,
padding='SAME',
name='label_conv')
label_logits = tf.transpose(conv, perm=[0, 2, 3, 1])
# label_logits = tf.check_numerics(label_logits, message="nan or inf from: label_logits")
print('label_logits shape: %s' % label_logits.get_shape())
return class_caps_activations, None, label_logits