Quiz Space

Deep Learning Practice · End Term · 31 Aug 2025 · May 2025 term · Set QDB1

Question 5: You are building an image classifier for the Nature12K da…

Question 5

+5 marksOne correct option

You are building an image classifier for the Nature12K dataset, which contains 12 categories of natural scenes (i.e., 12 output classes). You decide to use VGG-16 pretrained on ImageNet as a feature extractor and modify only the final layer for fine-tuning.

Below is a partially completed PyTorch code snippet:

python
import torch
import torch.nn as nn
from torchvision.models import vgg16


class Nature12KClassifier(nn.Module):
    def __init__(self):
        super(Nature12KClassifier, self).__init__()
        self.base = vgg16(pretrained=True)
        # [Missing Line]


    def forward(self, x):
        x = self.base.features(x)
        x = self.base.avgpool(x)
        x = torch.flatten(x, 1)
        x = self.base.classifier(x)
        return x


model = Nature12KClassifier()

Which of the following lines correctly fills in the missing line to adapt the VGG-16 model for Nature12K?

  1. A
  2. B
  3. C
  4. D
Show answer

Correct answer

  • A
See the whole paperTake it as a mock test

Question 5 of 22 in the IIT Madras BS Deep Learning Practice (Deep Learning Practice) End Term paper sat on 31 Aug 2025, in the May 2025 term (IIT M DEGREE AN EXAM QDB3 31 Aug 2025). It carries 5 marks.

More questions from this paper

  1. Q1Consider the task of applying a convolutional layer with a stride of 1 to an image of size 227 × 227 (Grayscale), while…
  2. Q2Figure question
  3. Q3You are given the following CNN architectures: AlexNet VGG-19 Inception-v3 ResNet-50 Which of the following correctly o…
  4. Q4Consider the following PyTorch CNN model used for a classification task on a small dataset of 64 \times 64 RGB images: …
  5. Q6The diagram below represents the block-wise flow of an unsupervised depth estimation pipeline using left-right stereo i…
  6. Q7Consider the original U-Net architecture.\ Which of the following statements about the convolutional and pooling operat…
  7. Q8Which of the following are valid advantages of using Convolutional Neural Networks (CNNs) instead of fully connected Mu…
  8. Q9In the Faster R-CNN architecture, the Region Proposal Network (RPN) plays a critical role in object detection.\ Which o…
  9. Q10Which of the following are valid advantages of YOLO compared to Fast R-CNN or Faster R-CNN?
  10. Q11Which of the following are advantages of ResNet over VGG-19?
  11. Q12Which of the following code snippets can be used for data augmentation during training in PyTorch?
  12. Q13Which of the following statements are correct regarding Generative Adversarial Networks (GANs)?
  13. Q14SRGAN and ESRGAN are both deep learning architectures designed for single image super- resolution. Which of the followi…
  14. Q15The Multi-stage Progressive Image Restoration Network (MPRNet) is a state-of-the-art architecture for tasks like image …
  15. Q16You are given a feature map of size 32 \times 32 \times 128 (height \times width \times channels). Three convolution op…
  16. Q17Figure question
  17. Q18You are evaluating an object detection model using the Mean Intersection over Union (mIoU) metric. The model predicts t…
  18. Q19Figure question
  19. Q20Two models, Model 1 and Model 2, are used to reconstruct grayscale images with pixel intensity values in the range [0, …
  20. Q21Two models, Model 1 and Model 2, are used to reconstruct grayscale images with pixel intensity values in the range [0, …
  21. Q22Two models, Model 1 and Model 2, are used to reconstruct grayscale images with pixel intensity values in the range [0, …