dasf.ml.dl.models

Submodules

dasf.ml.dl.models.devconvnet

Classes

`TorchPatchDeConvNet`	Base class for all neural network modules.
`TorchPatchDeConvNetSkip`	Base class for all neural network modules.
`TorchSectionDeConvNet`	Base class for all neural network modules.
`TorchSectionDeConvNetSkip`	Base class for all neural network modules.

Package Contents

class dasf.ml.dl.models.TorchPatchDeConvNet(n_classes=4, learned_billinear=False, clip=0.1, class_weights=None)[source]

Bases: NNModule

Base class for all neural network modules.

Your models should also subclass this class.

Modules can also contain other Modules, allowing to nest them in a tree structure. You can assign the submodules as regular attributes:

import torch.nn as nn
import torch.nn.functional as F

class Model(nn.Module):
    def __init__(self):
        super().__init__()
        self.conv1 = nn.Conv2d(1, 20, 5)
        self.conv2 = nn.Conv2d(20, 20, 5)

    def forward(self, x):
        x = F.relu(self.conv1(x))
        return F.relu(self.conv2(x))

Submodules assigned in this way will be registered, and will have their parameters converted too when you call to(), etc.

Note

As per the example above, an __init__() call to the parent class must be made before assignment on the child.

Variables:: training (bool) – Boolean represents whether this module is in training or evaluation mode.

Initializes internal Module state, shared by both nn.Module and ScriptModule.

unpool

conv_block1

conv_block2

conv_block3

conv_block4

conv_block5

conv_block6

conv_block7

deconv_block8

unpool_block9

deconv_block10

unpool_block11

deconv_block12

unpool_block13

deconv_block14

unpool_block15

deconv_block16

unpool_block17

deconv_block18

seg_score19

forward(x)[source]

Same as torch.nn.Module.forward().

Args:: *args: Whatever you decide to pass into the forward method. **kwargs: Keyword arguments are also possible.
Return:: Your model’s output

init_vgg16_params(vgg16, copy_fc8=True)[source]

load()[source]: This is just a no-op load method.

class dasf.ml.dl.models.TorchPatchDeConvNetSkip(n_classes=4, learned_billinear=False, clip=0.1, class_weights=None)[source]

Bases: NNModule

Base class for all neural network modules.

Your models should also subclass this class.

Modules can also contain other Modules, allowing to nest them in a tree structure. You can assign the submodules as regular attributes:

import torch.nn as nn
import torch.nn.functional as F

class Model(nn.Module):
    def __init__(self):
        super().__init__()
        self.conv1 = nn.Conv2d(1, 20, 5)
        self.conv2 = nn.Conv2d(20, 20, 5)

    def forward(self, x):
        x = F.relu(self.conv1(x))
        return F.relu(self.conv2(x))

Submodules assigned in this way will be registered, and will have their parameters converted too when you call to(), etc.

Note

As per the example above, an __init__() call to the parent class must be made before assignment on the child.

Variables:: training (bool) – Boolean represents whether this module is in training or evaluation mode.

Initializes internal Module state, shared by both nn.Module and ScriptModule.

unpool

conv_block1

conv_block2

conv_block3

conv_block4

conv_block5

conv_block6

conv_block7

deconv_block8

unpool_block9

deconv_block10

unpool_block11

deconv_block12

unpool_block13

deconv_block14

unpool_block15

deconv_block16

unpool_block17

deconv_block18

seg_score19

forward(x)[source]

Same as torch.nn.Module.forward().

Args:: *args: Whatever you decide to pass into the forward method. **kwargs: Keyword arguments are also possible.
Return:: Your model’s output

init_vgg16_params(vgg16, copy_fc8=True)[source]

load()[source]: This is just a no-op load method.

class dasf.ml.dl.models.TorchSectionDeConvNet(n_classes=4, learned_billinear=False, clip=0.1, class_weights=False)[source]

Bases: NNModule

Base class for all neural network modules.

Your models should also subclass this class.

Modules can also contain other Modules, allowing to nest them in a tree structure. You can assign the submodules as regular attributes:

import torch.nn as nn
import torch.nn.functional as F

class Model(nn.Module):
    def __init__(self):
        super().__init__()
        self.conv1 = nn.Conv2d(1, 20, 5)
        self.conv2 = nn.Conv2d(20, 20, 5)

    def forward(self, x):
        x = F.relu(self.conv1(x))
        return F.relu(self.conv2(x))

Submodules assigned in this way will be registered, and will have their parameters converted too when you call to(), etc.

Note

As per the example above, an __init__() call to the parent class must be made before assignment on the child.

Variables:: training (bool) – Boolean represents whether this module is in training or evaluation mode.

Initializes internal Module state, shared by both nn.Module and ScriptModule.

unpool

conv_block1

conv_block2

conv_block3

conv_block4

conv_block5

conv_block6

conv_block7

deconv_block8

unpool_block9

deconv_block10

unpool_block11

deconv_block12

unpool_block13

deconv_block14

unpool_block15

deconv_block16

unpool_block17

deconv_block18

seg_score19

forward(x)[source]

Same as torch.nn.Module.forward().

Args:: *args: Whatever you decide to pass into the forward method. **kwargs: Keyword arguments are also possible.
Return:: Your model’s output

init_vgg16_params(vgg16, copy_fc8=True)[source]

load()[source]: This is just a no-op load method.

class dasf.ml.dl.models.TorchSectionDeConvNetSkip(n_classes=4, learned_billinear=False, clip=0.1, class_weights=None)[source]

Bases: NNModule

Base class for all neural network modules.

Your models should also subclass this class.

Modules can also contain other Modules, allowing to nest them in a tree structure. You can assign the submodules as regular attributes:

import torch.nn as nn
import torch.nn.functional as F

class Model(nn.Module):
    def __init__(self):
        super().__init__()
        self.conv1 = nn.Conv2d(1, 20, 5)
        self.conv2 = nn.Conv2d(20, 20, 5)

    def forward(self, x):
        x = F.relu(self.conv1(x))
        return F.relu(self.conv2(x))

Submodules assigned in this way will be registered, and will have their parameters converted too when you call to(), etc.

Note

As per the example above, an __init__() call to the parent class must be made before assignment on the child.

Variables:: training (bool) – Boolean represents whether this module is in training or evaluation mode.

Initializes internal Module state, shared by both nn.Module and ScriptModule.

unpool

conv_block1

conv_block2

conv_block3

conv_block4

conv_block5

conv_block6

conv_block7

deconv_block8

unpool_block9

deconv_block10

unpool_block11

deconv_block12

unpool_block13

deconv_block14

unpool_block15

deconv_block16

unpool_block17

deconv_block18

seg_score19

forward(x)[source]

Same as torch.nn.Module.forward().

Args:: *args: Whatever you decide to pass into the forward method. **kwargs: Keyword arguments are also possible.
Return:: Your model’s output

init_vgg16_params(vgg16, copy_fc8=True)[source]

load()[source]: This is just a no-op load method.