Consider a convolutional neural network which takes as input a 42-by-54 color image (i.e. with three channels R, G, B). The first convolutional layer has 16 filters that are 6-by-6, with stride 2 and no zero-padding. Compute the number of: * weights per filter in this layer (including bias): * neurons in this layer: * connections into the neurons in this layer: * independent parameters in this layer:
Consider a convolutional neural network which takes as input a 42-by-54 color image (i.e. with three channels R, G, B). The first convolutional layer has 16 filters that are 6-by-6, with stride 2 and no zero-padding. Compute the number of: * weights per filter in this layer (including bias): * neurons in this layer: * connections into the neurons in this layer: * independent parameters in this layer:
Related questions
Question
Transcribed Image Text:Consider a convolutional neural network which takes as input a 42-by-54 color image (i.e. with three channels R, G, B). The first convolutional layer has 16 filters that are 6-by-6, with stride 2 and no zero-padding.
Compute the number of:
* weights per filter in this layer (including bias):
* neurons in this layer:
* connections into the neurons in this layer:
* independent parameters in this layer:
Expert Solution
This question has been solved!
Explore an expertly crafted, step-by-step solution for a thorough understanding of key concepts.
Step by step
Solved in 3 steps
