Answered step by step
Verified Expert Solution
Question
1 Approved Answer
In this question, we will try and understand 1 1 convolutional kernels and their functions: Given that the training mini - batch size is 3
In this question, we will try and understand convolutional kernels and their functions:
Given that the training minibatch size is images, each of dimension pixels and
channels Red Blue, Green Assume that we apply a single convolutional filter with stride
What will be the ratio between the size of the tensor before applying the filter and its size
after the application of the filter?
What is the interpretation of such a filter? Let us say we are designing a CNN to detect a
bluecolour Pepsi can. What would you expect the weights of the trained
convolutional filter to be like, when each of the weights are mapped to the to
range? Assume the convention of Red Blue Green for writing the weights Marks:
Let us say the prior layer of your network has size ie Height Width
Depth, where depth denotes the number of convolutional filters used Compare the
following two scenarios in terms of the parameters that need to be trained.
Scenario A: Kernel of size with stride of and such filters ie activation
maps
Scenario B:
Previous Layer Size
Conv kernel stride such filters
Conv kernel stride such filters
Conv x kernel stride such filters
What will be the total number of parameters and the final size of the tensor after the
application of convolutional filters in the two scenarios?
How are these two scenarios comparable?
Marks:
Step by Step Solution
There are 3 Steps involved in it
Step: 1
Get Instant Access to Expert-Tailored Solutions
See step-by-step solutions with expert insights and AI powered tools for academic success
Step: 2
Step: 3
Ace Your Homework with AI
Get the answers you need in no time with our AI-driven, step-by-step assistance
Get Started