thelper.nn.sr package¶
Neural network and model package for super resolution.
This package contains classes that define blocks and modules used in various neural network for super resolution architectures. Most of these classes have been adapted from external sources; see their individual headers for more information.
Submodules¶
thelper.nn.sr.srcnn module¶
-
class
thelper.nn.sr.srcnn.
SRCNN
(task, num_channels=1, base_filter=64, groups=1)[source]¶ Bases:
thelper.nn.utils.Module
Implements the SRCNN architecture.
See also
Dong et al., Image Super-Resolution Using Deep Convolutional Networks [arXiv], 2014.
thelper.nn.sr.vdsr module¶
-
class
thelper.nn.sr.vdsr.
VDSR
(task, num_channels=1, base_filter=64, kernel_size0=3, num_residuals=18, groups=1, activation='relu', norm='batch')[source]¶ Bases:
thelper.nn.utils.Module
Implements the VDSR architecture.
See also
Kim et al., Accurate Image Super-Resolution Using Very Deep Convolutional Networks [arXiv], 2015.