Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Commit to enable true fully convolutional application of network #684

Merged
merged 1 commit into from
Apr 10, 2017
Merged

Commit to enable true fully convolutional application of network #684

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
commit to enable true fully convolutional application of network
  • Loading branch information
@warmspringwinds
warmspringwinds committed Nov 24, 2016
commit 9c767ea06c53d40a620ec8736aba7ec962cf74cf
30 changes: 24 additions & 6 deletions slim/nets/vgg.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -68,7 +68,8 @@ def vgg_a(inputs,
is_training=True,
dropout_keep_prob=0.5,
spatial_squeeze=True,
scope='vgg_a'):
scope='vgg_a',
fc_conv_padding='VALID'):
"""Oxford Net VGG 11-Layers version A Example.

Note: All the fully_connected layers have been transformed to conv2d layers.
Expand All @@ -83,6 +84,11 @@ def vgg_a(inputs,
spatial_squeeze: whether or not should squeeze the spatial dimensions of the
outputs. Useful to remove unnecessary dimensions for classification.
scope: Optional scope for the variables.
fc_conv_padding: the type of padding to use for the fully connected layer
that is implemented as a convolutional layer. Use 'SAME' padding if you
are applying the network in a fully convolutional manner and want to
get a prediction map downsampled by a factor of 32 as an output. Otherwise,
the output prediction map will be (input / 32) - 6 in case of 'VALID' padding.

Returns:
the last op containing the log predictions and end_points dict.
Expand All @@ -103,7 +109,7 @@ def vgg_a(inputs,
net = slim.repeat(net, 2, slim.conv2d, 512, [3, 3], scope='conv5')
net = slim.max_pool2d(net, [2, 2], scope='pool5')
# Use conv2d instead of fully_connected layers.
net = slim.conv2d(net, 4096, [7, 7], padding='VALID', scope='fc6')
net = slim.conv2d(net, 4096, [7, 7], padding=fc_conv_padding, scope='fc6')
net = slim.dropout(net, dropout_keep_prob, is_training=is_training,
scope='dropout6')
net = slim.conv2d(net, 4096, [1, 1], scope='fc7')
Expand All @@ -127,7 +133,8 @@ def vgg_16(inputs,
is_training=True,
dropout_keep_prob=0.5,
spatial_squeeze=True,
scope='vgg_16'):
scope='vgg_16',
fc_conv_padding='VALID'):
"""Oxford Net VGG 16-Layers version D Example.

Note: All the fully_connected layers have been transformed to conv2d layers.
Expand All @@ -142,6 +149,11 @@ def vgg_16(inputs,
spatial_squeeze: whether or not should squeeze the spatial dimensions of the
outputs. Useful to remove unnecessary dimensions for classification.
scope: Optional scope for the variables.
fc_conv_padding: the type of padding to use for the fully connected layer
that is implemented as a convolutional layer. Use 'SAME' padding if you
are applying the network in a fully convolutional manner and want to
get a prediction map downsampled by a factor of 32 as an output. Otherwise,
the output prediction map will be (input / 32) - 6 in case of 'VALID' padding.

Returns:
the last op containing the log predictions and end_points dict.
Expand All @@ -162,7 +174,7 @@ def vgg_16(inputs,
net = slim.repeat(net, 3, slim.conv2d, 512, [3, 3], scope='conv5')
net = slim.max_pool2d(net, [2, 2], scope='pool5')
# Use conv2d instead of fully_connected layers.
net = slim.conv2d(net, 4096, [7, 7], padding='VALID', scope='fc6')
net = slim.conv2d(net, 4096, [7, 7], padding=fc_conv_padding, scope='fc6')
net = slim.dropout(net, dropout_keep_prob, is_training=is_training,
scope='dropout6')
net = slim.conv2d(net, 4096, [1, 1], scope='fc7')
Expand All @@ -186,7 +198,8 @@ def vgg_19(inputs,
is_training=True,
dropout_keep_prob=0.5,
spatial_squeeze=True,
scope='vgg_19'):
scope='vgg_19',
fc_conv_padding='VALID'):
"""Oxford Net VGG 19-Layers version E Example.

Note: All the fully_connected layers have been transformed to conv2d layers.
Expand All @@ -201,6 +214,11 @@ def vgg_19(inputs,
spatial_squeeze: whether or not should squeeze the spatial dimensions of the
outputs. Useful to remove unnecessary dimensions for classification.
scope: Optional scope for the variables.
fc_conv_padding: the type of padding to use for the fully connected layer
that is implemented as a convolutional layer. Use 'SAME' padding if you
are applying the network in a fully convolutional manner and want to
get a prediction map downsampled by a factor of 32 as an output. Otherwise,
the output prediction map will be (input / 32) - 6 in case of 'VALID' padding.

Returns:
the last op containing the log predictions and end_points dict.
Expand All @@ -221,7 +239,7 @@ def vgg_19(inputs,
net = slim.repeat(net, 4, slim.conv2d, 512, [3, 3], scope='conv5')
net = slim.max_pool2d(net, [2, 2], scope='pool5')
# Use conv2d instead of fully_connected layers.
net = slim.conv2d(net, 4096, [7, 7], padding='VALID', scope='fc6')
net = slim.conv2d(net, 4096, [7, 7], padding=fc_conv_padding, scope='fc6')
net = slim.dropout(net, dropout_keep_prob, is_training=is_training,
scope='dropout6')
net = slim.conv2d(net, 4096, [1, 1], scope='fc7')
Expand Down