Quiz Space

Deep Learning Practice · Quiz 2 · 1 Dec 2024 · September 2024 term

Question 3: For a 1D convolution, given the following values: Input s…

Question 3

+4 marksOne correct option

For a 1D convolution, given the following values:

  • Input size (xx): 50
  • In channels: 16
  • Kernel size: 3
  • Padding: 1
  • Dilation: 1
  • Stride: 2
  • Out channels: 32

What is the shape of the output of the convolutional layer?

  1. A

    32 × 25

  2. B

    32 × 26

  3. C

    16 × 32 × 50

  4. D

    50 × 3

Show answer

Correct answer

  • A

    32 × 25

See the whole paperTake it as a mock test

Question 3 of 15 in the IIT Madras BS Deep Learning Practice (Deep Learning Practice) Quiz 2 paper sat on 1 Dec 2024, in the September 2024 term (IIT M DEGREE AN EXAM QDB2 01 Dec 2024). It carries 4 marks.

More questions from this paper

  1. Q1Figure question
  2. Q2Figure question
  3. Q4If an audio is of duration 10 seconds and sample rate is 48KHz, what happens to the length of audio in samples if the a…
  4. Q5If the current learning rate is 0.002 and the maximum learning rate to be achieved in 1000 steps is 0.004, what should …
  5. Q6What is the correct order of training commands?
  6. Q7To quantize the Whisper model to 8-bit integer during loading in Hugging Face, which of the following arguments should …
  7. Q8Which of the following models can be used to obtain segments for speaker diarization?
  8. Q9Which of the following arguments should be passed during dataset loading to avoid loading the full dataset at once?
  9. Q10Which of the following loss functions can be used for speaker classification?
  10. Q11If a dataset has 25600 samples, batch size is 100, each epoch processes the whole dataset only once, and gradient accum…
  11. Q12Which of the following functions can be used to replace certain values in a PyTorch tensor?
  12. Q13Which of the following trainers is commonly used for ASR sequence-to-sequence training?
  13. Q14What type of model is HiFi-GAN?
  14. Q15Which of the following should be done when a CUDA Out of Memory error is encountered during training?