Quiz Space

Introduction to Deep Learning and Generative AI · Quiz 1 · 15 Mar 2026 · January 2026 term · Set 2

Question 10: A CNN produces an output feature map of size 7x7x512, wh…

Question 10

+2 marksOne correct option

A CNN produces an output feature map of size 7x7x512, which is followed by Global Average Pooling (GAP) and then a fully connected layer with 10 output classes. Which of the following statements is correct?

  1. A

    GAP converts the feature map into a 49 × 512 vector before classification

  2. B

    GAP produces a 512-dimensional vector, resulting in 5120 trainable parameters in the final layer

  3. C

    GAP produces a 7 × 7 × 1 feature map, followed by a 10-unit fully connected layer

  4. D

    GAP increases the number of parameters compared to flattening

Show answer

Correct answer

  • B

    GAP produces a 512-dimensional vector, resulting in 5120 trainable parameters in the final layer

See the whole paperTake it as a mock test

Question 10 of 24 in the IIT Madras BS Introduction to Deep Learning and Generative AI (Deep Learning and GenAI) Quiz 1 paper sat on 15 Mar 2026, in the January 2026 term (Introduction To Deep Learning And Generative Ai 15 Mar 26). It carries 2 marks.

This question was also asked in

More questions from this paper

  1. Q1What will be the output of the following PyTorch code?
  2. Q2Consider the following code snippet: What will be printed?
  3. Q3You want to train a linear model using stochastic gradient descent (SGD). Assume that the loss function and training lo…
  4. Q4Consider the following training loop: Which statement best describes the problem in this training loop?
  5. Q5You are given a dataset of 10 × 10 grayscale images. Your goal is to build a 5-class classifier. You have to adopt one …
  6. Q6An image contains 16 channels. Which of the following code snippets correctly creates a convolution layer for this imag…
  7. Q7Consider the following pytorch code to preprocess the FashionMNIST dataset. Which of the following hold true?
  8. Q8An input volume has shape 6x6x2 (height=6, width=6, depth=2 channels). Perform the following two steps on it. ● Step 1:…
  9. Q9In an Inception module, four parallel paths produce outputs of shapes: 28x28x64, 28x28x128, 28x28x32, and 28x28x32. Aft…
  10. Q11Consider the following code snippet: What will be printed?
  11. Q12A CNN uses three consecutive 3x3 convolution layers with stride 1 and no pooling. What is the receptive field of a neur…
  12. Q13An input feature map of size 32x32 is convolved using SAME padding in the following two independent cases: Case I: ● Fi…
  13. Q14Consider an input image of size 12x12x4. In the convolution layer a single filter of size 12 x 12 is passed to the imag…
  14. Q15A hidden layer in the feed_forward network of a CNN contains 5 neurons labelled A,B,C,D,E. We apply dropout to this hid…
  15. Q16Consider the following CNN : Calculate the total number of parameters in the CNN.
  16. Q17Given the input , what is the output of the network?
  17. Q18Assume the target value is . Using Mean Squared Error (MSE) as the loss function, compute the numerical value of the lo…
  18. Q19For which of the following conditions on will the first neuron of the hidden layer not be activated ( )?
  19. Q20Consider the following fixed neural network implemented in PyTorch. Loss function used: Based on the above data, answer…
  20. Q21Consider the following fixed neural network implemented in PyTorch. Loss function used: Based on the above data, answer…
  21. Q22Consider the following fixed neural network implemented in PyTorch. Loss function used: Based on the above data, answer…
  22. Q23Consider the below neural network with fixed weights and answer the given subquestions:
  23. Q24Consider the following fixed neural network implemented in PyTorch. Loss function used: Based on the above data, answer…