Suppose you have a 10x10x3 colour image input and you want to stack two convolutional layers with kernel size 3x3 with 10 and 20 filters respectively. How many parameters do you have to train for these two layers? Don't forget bias terms!
Answers
Answered by
0
Answer:
ask the question from Google
Answered by
0
Answer:
While starting with the two-dimensional channel stack, the convolutional layers located successively use the two-dimensional kernel's multiple stacks. These are stacked usually at a similar depth as the main input channels and sum up to give out a single output channel. Therefore, the formula to obtain is Nk width × Nk height × N input channels × N output channels.
Similar questions