Module minder_utils.models.feature_extractors.simclr.basic

Classes

class Encoder

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(Model, self).__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 :meth:to, etc.

:ivar training: Boolean represents whether this module is in training or evaluation mode. :vartype training: bool

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

Expand source code

class Encoder(nn.Module):
    def __init__(self):
        super(Encoder, self).__init__()
        self.conv1 = nn.Conv2d(3, 16, kernel_size=3, stride=1, padding=1)
        self.conv2 = nn.Conv2d(16, 32, kernel_size=3, stride=1, padding=1)
        self.conv3 = nn.Conv2d(32, 64, kernel_size=3, stride=1, padding=1)
        self.conv4 = nn.Conv2d(64, 64, kernel_size=3, stride=1, padding=1)
        self.pool = nn.MaxPool2d(2, 2)
        self.fc = nn.Linear(1792, 1024)

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

        x = self.conv2(x)
        x = F.relu(x)
        x = self.pool(x)

        x = self.conv3(x)
        x = F.relu(x)
        x = self.pool(x)

        x = self.conv4(x)
        x = F.relu(x)
        x = self.pool(x)

        x = nn.Flatten()(x)
        x = self.fc(x)
        return x

Ancestors

• torch.nn.modules.module.Module

Class variables

var dump_patches : bool

var training : bool

Methods

def forward(self, x) ‑> Callable[..., Any]

Defines the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the :class:Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

Expand source code

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

    x = self.conv2(x)
    x = F.relu(x)
    x = self.pool(x)

    x = self.conv3(x)
    x = F.relu(x)
    x = self.pool(x)

    x = self.conv4(x)
    x = F.relu(x)
    x = self.pool(x)

    x = nn.Flatten()(x)
    x = self.fc(x)
    return x

class ResNetSimCLR (base_model, out_dim, **kwargs)

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(Model, self).__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 :meth:to, etc.

:ivar training: Boolean represents whether this module is in training or evaluation mode. :vartype training: bool

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

Expand source code

class ResNetSimCLR(nn.Module):

    def __init__(self, base_model, out_dim, **kwargs):
        super(ResNetSimCLR, self).__init__()
        self.resnet_dict = {"resnet18": models.resnet18(pretrained=False),
                            "resnet50": models.resnet50(pretrained=False),
                            "basic": Encoder()}

        resnet = self._get_basemodel(base_model)
        num_ftrs = resnet.fc.in_features

        self.features = nn.Sequential(*list(resnet.children())[:-1])

        # projection MLP
        self.l1 = nn.Linear(num_ftrs, num_ftrs)
        self.l2 = nn.Linear(num_ftrs, out_dim)

        self.base_model = base_model

    def _get_basemodel(self, model_name):
        try:
            model = self.resnet_dict[model_name]
            print("Feature extractor:", model_name)
            return model
        except:
            raise ("Invalid model name. Check the config file and pass one of: resnet18 or resnet50")

    def forward(self, x):
        h = self.features(x)
        h = nn.Flatten()(h) if self.base_model == 'basic' else h.squeeze()

        x = self.l1(h)
        x = F.relu(x)
        x = self.l2(x)
        return h, x

Ancestors

• torch.nn.modules.module.Module

Class variables

var dump_patches : bool

var training : bool

Methods

def forward(self, x) ‑> Callable[..., Any]

Defines the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the :class:Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

Expand source code

def forward(self, x):
    h = self.features(x)
    h = nn.Flatten()(h) if self.base_model == 'basic' else h.squeeze()

    x = self.l1(h)
    x = F.relu(x)
    x = self.l2(x)
    return h, x