def _build(self, inputs, is_training=True, test_local_stats=True):
"""Assembles the `ConvNet2D` and connects it to the graph.
Args:
inputs: A 4D Tensor of shape `[batch_size, input_height, input_width,
input_channels]`.
is_training: Boolean to indicate to `snt.BatchNorm` if we are
currently training. By default `True`.
test_local_stats: Boolean to indicate to `snt.BatchNorm` if batch
normalization should use local batch statistics at test time.
By default `True`.
Returns:
A 4D Tensor of shape `[batch_size, output_height, output_width,
output_channels[-1]]`.
"""
self._input_shape = tuple(inputs.get_shape().as_list())
net = inputs
final_index = len(self._layers) - 1
for i, layer in enumerate(self._layers):
net = layer(net)
if i != final_index or self._activate_final:
if self._use_batch_norm:
bn = batch_norm.BatchNorm(name="batch_norm_{}".format(i),
**self._batch_norm_config)
net = bn(net,
is_training=is_training,
test_local_stats=test_local_stats)
net = self._activation(net)
return net
def _build(self, inputs, is_training=None, test_local_stats=True):
"""Assembles the `ConvNet2D` and connects it to the graph.
Args:
inputs: A 4D Tensor of shape `[batch_size, input_height, input_width,
input_channels]`.
is_training: Boolean to indicate to `snt.BatchNorm` if we are
currently training. Must be specified explicitly if `use_batchnorm` is
`True`.
test_local_stats: Boolean to indicate to `snt.BatchNorm` if batch
normalization should use local batch statistics at test time.
By default `True`.
Returns:
A 4D Tensor of shape `[batch_size, output_height, output_width,
output_channels[-1]]`.
Raises:
ValueError: If `is_training` is not explicitly specified when using
batch normalization.
"""
if self._use_batch_norm and is_training is None:
raise ValueError("Boolean is_training flag must be explicitly specified " "when using batch normalization.")
self._input_shape = tuple(inputs.get_shape().as_list())
net = inputs
final_index = len(self._layers) - 1
for i, layer in enumerate(self._layers):
net = layer(net)
if i != final_index or self._activate_final:
if self._use_batch_norm:
bn = batch_norm.BatchNorm(
name="batch_norm_{}".format(i),
**self._batch_norm_config,
)
net = bn(
net,
is_training=is_training,
test_local_stats=test_local_stats,
)
net = self._activation(net)
return net
def create_batch_norm():
return batch_norm.BatchNorm(offset=False, scale=False)(
inputs, is_training, test_local_stats)
def _build(self,
inputs,
keep_prob=None,
is_training=True,
test_local_stats=True):
"""Connects the AlexNet module into the graph.
Args:
inputs: A Tensor of size [batch_size, input_height, input_width,
input_channels], representing a batch of input images.
keep_prob: A scalar Tensor representing the dropout keep probability.
is_training: Boolean to indicate to `snt.BatchNorm` if we are
currently training. By default `True`.
test_local_stats: Boolean to indicate to `snt.BatchNorm` if batch
normalization should use local batch statistics at test time.
By default `True`.
Returns:
A Tensor of size [batch_size, output_size], where `output_size` depends
on the mode the network was constructed in.
Raises:
base.IncompatibleShapeError: If any of the input image dimensions
(input_height, input_width) are too small for the given network mode.
"""
input_shape = inputs.get_shape().as_list()
if input_shape[1] < self._min_size or input_shape[2] < self._min_size:
raise base.IncompatibleShapeError(
"Image shape too small: ({:d}, {:d}) < {:d}".format(
input_shape[1], input_shape[2], self._min_size))
net = inputs
for i, params in enumerate(self._conv_layers):
output_channels, conv_params, max_pooling = params
kernel_size, stride = conv_params
conv_mod = conv.Conv2D(name="conv_{}".format(i),
output_channels=output_channels,
kernel_shape=kernel_size,
stride=stride,
padding=conv.VALID,
initializers=self._initializers,
partitioners=self._partitioners,
regularizers=self._regularizers)
if not self.is_connected:
self._conv_modules.append(conv_mod)
net = conv_mod(net)
if self._use_batch_norm:
bn = batch_norm.BatchNorm(**self._batch_norm_config)
net = bn(net, is_training, test_local_stats)
net = tf.nn.relu(net)
if max_pooling is not None:
pooling_kernel_size, pooling_stride = max_pooling
net = tf.nn.max_pool(
net,
ksize=[1, pooling_kernel_size, pooling_kernel_size, 1],
strides=[1, pooling_stride, pooling_stride, 1],
padding=conv.VALID)
net = basic.BatchFlatten(name="flatten")(net)
for i, output_size in enumerate(self._fc_layers):
linear_mod = basic.Linear(name="fc_{}".format(i),
output_size=output_size,
partitioners=self._partitioners)
if not self.is_connected:
self._linear_modules.append(linear_mod)
net = linear_mod(net)
if self._use_batch_norm:
bn = batch_norm.BatchNorm(**self._batch_norm_config)
net = bn(net, is_training, test_local_stats)
net = tf.nn.relu(net)
if keep_prob is not None:
net = tf.nn.dropout(net, keep_prob=keep_prob)
return net
def _build(self,
inputs,
keep_prob=None,
is_training=None,
test_local_stats=True):
"""Connects the AlexNet module into the graph.
The is_training flag only controls the batch norm settings, if `False` it
does not force no dropout by overriding any input `keep_prob`. To avoid any
confusion this may cause, if `is_training=False` and `keep_prob` would cause
dropout to be applied, an error is thrown.
Args:
inputs: A Tensor of size [batch_size, input_height, input_width,
input_channels], representing a batch of input images.
keep_prob: A scalar Tensor representing the dropout keep probability.
When `is_training=False` this must be None or 1 to give no dropout.
is_training: Boolean to indicate if we are currently training. Must be
specified if batch normalization or dropout is used.
test_local_stats: Boolean to indicate to `snt.BatchNorm` if batch
normalization should use local batch statistics at test time.
By default `True`.
Returns:
A Tensor of size [batch_size, output_size], where `output_size` depends
on the mode the network was constructed in.
Raises:
base.IncompatibleShapeError: If any of the input image dimensions
(input_height, input_width) are too small for the given network mode.
ValueError: If `keep_prob` is not None or 1 when `is_training=False`.
ValueError: If `is_training` is not explicitly specified when using
batch normalization.
"""
# Check input shape
if (self._use_batch_norm
or keep_prob is not None) and is_training is None:
raise ValueError(
"Boolean is_training flag must be explicitly specified "
"when using batch normalization or dropout.")
input_shape = inputs.get_shape().as_list()
if input_shape[1] < self._min_size or input_shape[2] < self._min_size:
raise base.IncompatibleShapeError(
"Image shape too small: ({:d}, {:d}) < {:d}".format(
input_shape[1], input_shape[2], self._min_size))
net = inputs
# Check keep prob
if keep_prob is not None:
valid_inputs = tf.logical_or(is_training, tf.equal(keep_prob, 1.))
keep_prob_check = tf.assert_equal(
valid_inputs,
True,
message=
"Input `keep_prob` must be None or 1 if `is_training=False`.")
with tf.control_dependencies([keep_prob_check]):
net = tf.identity(net)
for i, params in enumerate(self._conv_layers):
output_channels, conv_params, max_pooling = params
kernel_size, stride = conv_params
conv_mod = conv.Conv2D(name="conv_{}".format(i),
output_channels=output_channels,
kernel_shape=kernel_size,
stride=stride,
padding=conv.VALID,
initializers=self._initializers,
partitioners=self._partitioners,
regularizers=self._regularizers)
if not self.is_connected:
self._conv_modules.append(conv_mod)
net = conv_mod(net)
if self._use_batch_norm:
bn = batch_norm.BatchNorm(**self._batch_norm_config)
net = bn(net, is_training, test_local_stats)
net = tf.nn.relu(net)
if max_pooling is not None:
pooling_kernel_size, pooling_stride = max_pooling
net = tf.nn.max_pool(
net,
ksize=[1, pooling_kernel_size, pooling_kernel_size, 1],
strides=[1, pooling_stride, pooling_stride, 1],
padding=conv.VALID)
net = basic.BatchFlatten(name="flatten")(net)
for i, output_size in enumerate(self._fc_layers):
linear_mod = basic.Linear(name="fc_{}".format(i),
output_size=output_size,
initializers=self._initializers,
partitioners=self._partitioners)
if not self.is_connected:
self._linear_modules.append(linear_mod)
net = linear_mod(net)
if self._use_batch_norm and self._bn_on_fc_layers:
bn = batch_norm.BatchNorm(**self._batch_norm_config)
net = bn(net, is_training, test_local_stats)
net = tf.nn.relu(net)
if keep_prob is not None:
net = tf.nn.dropout(net, keep_prob=keep_prob)
return net