Skip to content
Snippets Groups Projects
Commit ce4e4458 authored by Tiago de Freitas Pereira's avatar Tiago de Freitas Pereira
Browse files

[sphinx] Fixed warnings

parent 0c515d72
Branches
Tags
1 merge request!11Tfrecord support
Pipeline #
......@@ -16,54 +16,32 @@ from tensorflow.python.layers import base
def maxout(inputs, num_units, axis=-1, name=None):
"""Adds a maxout op from https://arxiv.org/abs/1302.4389
"Maxout Networks"
return MaxOut(num_units=num_units, axis=axis, name=name)(inputs)
Ian J. Goodfellow, David Warde-Farley, Mehdi Mirza, Aaron Courville, Yoshua
Bengio
Usually the operation is performed in the filter/channel dimension. This can also be
used after fully-connected layers to reduce number of features.
class MaxOut(base.Layer):
Args:
inputs: Tensor input
num_units: Specifies how many features will remain after maxout in the `axis` dimension (usually channel).
This must be multiple of number of `axis`.
axis: The dimension where max pooling will be performed. Default is the
last dimension.
name: Optional scope for name_scope.
Returns:
A `Tensor` representing the results of the pooling operation.
Raises:
ValueError: if num_units is not multiple of number of features.
"""
Adds a maxout op from
return MaxOut(num_units=num_units, axis=axis, name=name)(inputs)
"Maxout Networks"
Ian J. Goodfellow, David Warde-Farley, Mehdi Mirza, Aaron Courville, Yoshua
Bengio
class MaxOut(base.Layer):
"""Adds a maxout op from https://arxiv.org/abs/1302.4389
Usually the operation is performed in the filter/channel dimension. This can also be
used after fully-connected layers to reduce number of features.
"Maxout Networks"
**Parameters**
inputs: Tensor input
Ian J. Goodfellow, David Warde-Farley, Mehdi Mirza, Aaron Courville, Yoshua
Bengio
num_units: Specifies how many features will remain after maxout in the `axis` dimension (usually channel).
This must be multiple of number of `axis`.
Usually the operation is performed in the filter/channel dimension. This can also be
used after fully-connected layers to reduce number of features.
axis: The dimension where max pooling will be performed. Default is the
last dimension.
Args:
inputs: Tensor input
num_units: Specifies how many features will remain after maxout in the `axis` dimension (usually channel).
This must be multiple of number of `axis`.
axis: The dimension where max pooling will be performed. Default is the
last dimension.
name: Optional scope for name_scope.
Returns:
A `Tensor` representing the results of the pooling operation.
Raises:
ValueError: if num_units is not multiple of number of features.
name: Optional scope for name_scope.
"""
def __init__(self,
......@@ -100,5 +78,5 @@ class MaxOut(base.Layer):
shape[self.axis] = self.num_units
outputs.set_shape(shape)
return outputs
from .Layer import Layer
from .Conv1D import Conv1D
from .Maxout import maxout
from .Maxout import maxout, maxout
# gets sphinx autodoc done right - don't remove it
......@@ -20,6 +20,7 @@ def __appropriate__(*args):
__appropriate__(
Layer,
Conv1D,
maxout,
Maxout
)
__all__ = [_ for _ in dir() if not _.startswith('_')]
......
py:class list
\ No newline at end of file
py:class list
......@@ -6,4 +6,4 @@
===========
.. [facenet_2015] Schroff, Florian, Dmitry Kalenichenko, and James Philbin. "Facenet: A unified embedding for face recognition and clustering." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2015.
.. [facenet2015] Schroff, Florian, Dmitry Kalenichenko, and James Philbin. "Facenet: A unified embedding for face recognition and clustering." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2015.
......@@ -187,7 +187,7 @@ or :py:class:`bob.learn.tensorflow.datashuffler.TripletWithSelectionDisk`.
How the data is sampled ?
`````````````````````````
The paper [facenet_2015]_ introduced a new strategy to select triplets to train triplet networks (this is better described
The paper [facenet2015]_ introduced a new strategy to select triplets to train triplet networks (this is better described
here :py:class:`bob.learn.tensorflow.datashuffler.TripletWithSelectionDisk` and :py:class:`bob.learn.tensorflow.datashuffler.TripletWithFastSelectionDisk`).
This triplet selection relies in the current state of the network and are extensions of `bob.learn.tensorflow.datashuffler.OnlineSampling`.
......
0% Loading or .
You are about to add 0 people to the discussion. Proceed with caution.
Please register or to comment