Question 1

1import torch
2import torch.nn as nn
3from torchvision.models import alexnet
4
5class CustomAlexNet(nn.Module):
6    def __init__(self, num_classes=10):
7        super(CustomAlexNet, self).__init__()
8        self.alexnet = alexnet(pretrained=True)
9        # Blank portion
10    def forward(self, x):
11        x = self.alexnet.features(x)
12        x = self.alexnet.avgpool(x)
13        x = torch.flatten(x, 1)
14        x = self.alexnet.classifier(x)
15        return x
16
17model = CustomAlexNet()

Consider the following code snippet for modifying an AlexNet architecture to adapt it for a custom classification task with 10 output classes. Fill in the blank portion with the most appropriate code snippet. import torch import torch.nn as nn from torchvision.models import alexnet class CustomAlexNet(nn.Module): def __init__(self, num_classes=10): super(CustomAlexNet, self).__init__() self.alexnet = alexnet(pretrained=True) # Blank portion def forward(self, x): x = self.alexnet.features(x) x = self.alexnet.avgpool(x) x = torch.flatten(x, 1) x = self.alexnet.classifier(x) return x model = CustomAlexNet() Which of the following code snippets correctly fills the blank portion to modify the AlexNet classifier while preserving the pretrained feature extraction layers? An RGB image of size 227 × 227 × 3 is first converted to grayscale and then passed through a 2D Convolutional Neural Network (CNN) layer with the following parameters:\ – Kernel size: 3 × 3\ – Stride: 1\ – Padding: 1\ – Number of filters: 16\ What will be the shape of the output feature map? Figure from the original question paper