Helper Module for Deep Learning.

The Deep Labeling Network for Semantic Image Segmentation.

class pynet.models.deeplabnet.BasicBlock(inplanes, planes, stride=1, downsample=None, drop_rate=0)[source]¶

__init__(inplanes, planes, stride=1, downsample=None, drop_rate=0)[source]¶: Initialize self. See help(type(self)) for accurate signature.

expansion = 1¶

forward(x)[source]¶

class pynet.models.deeplabnet.Bottleneck(inplanes, planes, stride=1, downsample=None, drop_rate=0)[source]¶

__init__(inplanes, planes, stride=1, downsample=None, drop_rate=0)[source]¶: Initialize self. See help(type(self)) for accurate signature.

expansion = 4¶

forward(x)[source]¶

class pynet.models.deeplabnet.DeepLabNet(n_classes=2, drop_rate=0)[source]¶

Deep Labeling for Semantic Image Segmentation.

Implementation of the DeepLabV3+ variant.

DeepLabv3 employs atrous convolution to extract the features computed by deep convolutional neural networks at anarbitrary resolution. Here, we denote output stride as the ratio of input image spatial resolution to the final output resolution (before global pooling or fully-connected layer).

Reference: https://arxiv.org/pdf/1802.02611.pdf Code: https://github.com/cv-lee/BraTs

__init__(n_classes=2, drop_rate=0)[source]¶

Init class.

Parameters: n_classes: int, default 2

the number of features in the output segmentation map.

debug(name, tensor)[source]¶

Print debug message.

Parameters

name: str

the tensor name in the displayed message.

tensor: Tensor

a pytorch tensor.

forward(x)[source]¶

class pynet.models.deeplabnet.Encoder(drop_rate=0)[source]¶

DeepLabv3 as encoder.

__init__(drop_rate=0)[source]¶: Initialize self. See help(type(self)) for accurate signature.