Deep Learning Practice End Term 13 Sept 2026 — Question 9
Show answer
Correct answer: 18432
Question 9 of 31 in the IIT Madras BS Deep Learning Practice (Deep Learning Practice) End Term paper sat on 13 Sept 2026, in the May 2026 term (Deep Learning Practice 13 Sep 26 (Session 2)). It carries 1 mark.
More questions from this paper
- Based on the above data, answer the given subquestions.
- Based on the above data, answer the given subquestions.
- Using the actual flattened feature size from previous question number 2, how many learnable parameters (weights + bias)…
- Which of the following statements about the (corrected) model are true?
- Figure question
- Figure question
- Which layer is responsible for the decoder failing to reach the target 120×120 output, and why?
- Figure question
- Figure question
- What is the parameter compression ratio (standard ÷ depthwise-separable), rounded to 2 decimal places?
- Figure question
- Which of the following statements correctly identify a real bug in the given code ?
- Based on the above data, answer the given subquestions.
- Based on the above data, answer the given subquestions.
- A convolutional layer receives a feature map with 16 input channels and applies 32 filters, each of spatial size 5 × 5.…
- A convolutional layer is applied to a 32 × 32 input using a 5 × 5 filter with zero-padding of 2 and stride 2. Using the…
- The final classification head applies a softmax over the pre-activation scores (logits). For a 3-class problem, the log…
- Following the VGG design philosophy of replacing a single large-kernel convolution with a cascade of small 3 × 3, strid…
- Figure question
- The decoder of a depth-estimation network upsamples feature maps using a transposed convolution ("up-convolution") with…
- In the original U-Net used for dense prediction (and adaptable to depth estimation), each encoder stage applies two suc…
- The SRGAN discriminator is a stack of 8 convolutional layers, all using 3 × 3 kernels with padding 1, and strides alter…
- Efficient restoration networks (e.g., LaKDNet) replace standard convolutions with depth-wise separable convolutions (a …
- Compared with the sigmoid activation, which of the following are correct reasons for preferring the ReLU activation in …
- VGGNet replaces large convolution kernels with stacks of small 3 × 3 convolutions. Which of the following statements co…
- Which of the following statements correctly describe the Region Proposal Network (RPN) in Faster R-CNN?
- Consider the multi-task loss used to train the original YOLOv1 model. Which of the following statements about it are co…
- Regarding the channel-attention module in CBAM, which of the following are correct?
- SRGAN performs photo-realistic super-resolution using a GAN. Which of the following statements are correct?
- In the multi-scale deep network for single-image depth estimation (Eigen et al.), the architecture is split into a coar…