Primitives
neps.search_spaces.architecture.primitives
#
AvgPool
#
Bases: AbstractPrimitive
Implementation of Avergae Pooling.
Source code in neps/search_spaces/architecture/primitives.py
AvgPool1x1
#
Bases: AbstractPrimitive
Implementation of Avergae Pooling with an optional 1x1 convolution afterwards. The convolution is required to increase the number of channels if stride > 1.
Source code in neps/search_spaces/architecture/primitives.py
Concat1x1
#
Bases: AbstractPrimitive
Implementation of the channel-wise concatination followed by a 1x1 convolution to retain the channel dimension.
Source code in neps/search_spaces/architecture/primitives.py
forward
#
Expecting a list of input tensors. Stacking them channel-wise and applying 1x1 conv
ConvBn
#
Bases: AbstractPrimitive
Implementation of 2d convolution, followed by 2d batch normalization and ReLU activation.
Source code in neps/search_spaces/architecture/primitives.py
ConvBnReLU
#
Bases: AbstractPrimitive
Implementation of 2d convolution, followed by 2d batch normalization and ReLU activation.
Source code in neps/search_spaces/architecture/primitives.py
DilConv
#
Bases: AbstractPrimitive
Implementation of a dilated separable convolution as used in the DARTS paper.
Source code in neps/search_spaces/architecture/primitives.py
Identity
#
MaxPool1x1
#
Bases: AbstractPrimitive
Implementation of MaxPool with an optional 1x1 convolution in case stride > 1. The 1x1 convolution is required to increase the number of channels.
Source code in neps/search_spaces/architecture/primitives.py
SepConv
#
Bases: AbstractPrimitive
Implementation of Separable convolution operation as in the DARTS paper, i.e. 2 sepconv directly after another.
Source code in neps/search_spaces/architecture/primitives.py
Sequential
#
Stem
#
Bases: AbstractPrimitive
This is used as an initial layer directly after the image input.
Source code in neps/search_spaces/architecture/primitives.py
Zero
#
Bases: AbstractPrimitive
Implementation of the zero operation. It removes the connection by multiplying its input with zero.
Source code in neps/search_spaces/architecture/primitives.py
Zero1x1
#
Bases: AbstractPrimitive
Implementation of the zero operation. It removes the connection by multiplying its input with zero.