CollaborativeCoding.models

Submodules

Classes

`ChristianModel`	Simple CNN model for image classification.
`JanModel`	A simple MLP network model for image classification tasks. Two hidden layers with 100 neurons.
`JohanModel`	Small MLP model for image classification.
`MagnusModel`	Base class for all neural network modules.
`SolveigModel`	A Convolutional Neural Network (CNN) model for classification.

Package Contents

class CollaborativeCoding.models.ChristianModel(image_shape, num_classes)

Bases: torch.nn.Module

Simple CNN model for image classification.

Args

image_shapetuple(int, int, int): Shape of the input image (C, H, W).
num_classesint: Number of classes in the dataset.

Processing Images

Input: (N, C, H, W): N: Batch size C: Number of input channels H: Height of the input image W: Width of the input image

Example: For grayscale images, C = 1.

Input Image Shape: (5, 1, 16, 16) CNN1 Output Shape: (5, 50, 8, 8) CNN2 Output Shape: (5, 100, 4, 4) FC Output Shape: (5, num_classes)

cnn1

cnn2

fc1

forward(x)

class CollaborativeCoding.models.JanModel(image_shape, num_classes)

Bases: torch.nn.Module

A simple MLP network model for image classification tasks. Two hidden layers with 100 neurons.

Args

image_shapetuple(int, int, int): Shape of the input image (C, H, W).
num_classesint: Number of classes in the dataset.

Processing Images

Input: (N, C, H, W): N: Batch size C: Number of input channels H: Height of the input image W: Width of the input image

Example: For grayscale images, C = 1.

Input Image Shape: (5, 1, 28, 28) flatten Output Shape: (5, 784) fc1 Output Shape: (5, 100) fc2 Output Shape: (5, 100) out Output Shape: (5, num_classes)

in_channels

height

width

num_classes

fc1

fc2

out

leaky_relu

flatten

forward(x)

class CollaborativeCoding.models.JohanModel(image_shape, num_classes)

Bases: torch.nn.Module

Small MLP model for image classification.

Parameters

image_shapetuple(int, int, int): Shape of the input image (C, H, W).
num_classesint: Number of classes in the dataset.

Processing Images

Input: (N, C, H, W): N: Batch size C: Number of input channels H: Height of the input image W: Width of the input image

Example: Grayscale images (like MNIST) have C = 1. Input shape: (N, 1, 28, 28) fc1 Output shape: (N, 77) fc2 Output shape: (N, 77) fc3 Output shape: (N, 77) fc4 Output shape: (N, num_classes)

in_channels

height

width

num_classes

in_features

fc1

fc2

fc3

fc4

relu

flatten

forward(x)

class CollaborativeCoding.models.MagnusModel(image_shape, num_classes: int)

Bases: torch.nn.Module

Base class for all neural network modules.

Your models should also subclass this class.

Modules can also contain other Modules, allowing them to be nested 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) -> None:
        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 also have their parameters converted 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.

layer1

layer2

layer3

forward(x)

Defines the forward pass of the MagnusModel. Args:

x (torch.Tensor): A four-dimensional tensor with shape
(Batch Size, Channels, Image Height, Image Width).

Returns:: torch.Tensor: The output tensor containing class logits for each input sample.

class CollaborativeCoding.models.SolveigModel(image_shape, num_classes)

Bases: torch.nn.Module

A Convolutional Neural Network (CNN) model for classification.

This model is designed for image classification tasks. It contains three convolutional blocks followed by a fully connected layer to make class predictions.

Args

image_shapetuple(int, int, int): Shape of the input image (C, H, W), where C is the number of channels, H is the height, and W is the width of the image. This parameter defines the input shape of the image that will be passed through the network.
num_classesint: The number of output classes for classification. This defines the size of the output layer (i.e., the number of units in the final fully connected layer).

Attributes

conv_block1nn.Sequential: The first convolutional block consisting of a convolutional layer, ReLU activation, and max-pooling.
conv_block2nn.Sequential: The second convolutional block consisting of a convolutional layer and ReLU activation.
conv_block3nn.Sequential: The third convolutional block consisting of a convolutional layer and ReLU activation.
fc1nn.Linear: The fully connected layer that takes the output from the convolutional blocks and outputs the final classification logits (raw scores for each class).

Methods

forward(x): Defines the forward pass of the network, which passes the input through the convolutional layers followed by the fully connected layer to produce class logits.

conv_block1

conv_block2

conv_block3

fc1

forward(x)

Defines the forward pass of the network.

Args

xtorch.Tensor: A 4D tensor with shape (Batch Size, Channels, Height, Width) representing the input images.

Returns

torch.Tensor: A 2D tensor of shape (Batch Size, num_classes) containing the logits (raw class scores) for each input image in the batch. These logits can be passed through a softmax function for probability values.