Learn how to calculate the output volume of a convolutional layer in CNNs using input dimensions, filter size, stride, and padding. Master this essential skill for CNN certification exams.
Question
You have an input volume that is 121 × 121 × 16 121×121×16, and convolve it with 32 filters of 4 × 4 4×4, using a stride of 3 and no padding. What is the output volume?
A. 40 x 40 x 32
B. 118 × 118 × 32
C. 40 x 40 x 16
D. 118 x 118 × 16
Answer
A. 40 x 40 x 32
Explanation
Why Option A is Correct
Option A correctly calculates both spatial dimensions (40×40) and uses the correct depth (32, matching the number of filters).
Options B and D incorrectly calculate spatial dimensions.
Options C and D incorrectly set the depth to 16, which matches the input depth but not the number of filters.
Key Takeaways for CNN Exams
- Always use the convolution formula to compute spatial dimensions.
- The output depth equals the number of filters applied.
- Stride and padding significantly affect spatial dimensions; ensure you account for them correctly.
Convolutional Neural Network CNN certification exam assessment practice question and answer (Q&A) dump including multiple choice questions (MCQ) and objective type questions, with detail explanation and reference available free, helpful to pass the Convolutional Neural Network CNN exam and earn Convolutional Neural Network CNN certification.