The basics of ConvNets
3. Suppose your input is a 300 by 300 color (RGB) image, and you use a convolutional layer with 100 filters that are each 5x5. How many parameters does this hidden layer have (including the bias parameters)?
2501
2600
7500
7600
answer(D) reason:单片过滤器的大小为5*5, 由于是RGB图像,即Nc=3,故完整的一个过滤器组成是5*5*3,而每一个过滤器有一个偏置参数b,因此一个完整的过滤器有参数5*5*3 + 1 = 76,故100个过滤器有7600个参数
4.You have an input volume that is 63x63x16, and convolve it with 32 filters that are each 7x7, using a stride of 2 and no padding. What is the output volume?
29x29x32
29x29x16
16x16x32
16x16x16
answer(A)reson:⌊(nh+2p−f)/s+1⌋×⌊(nw+2p−f)/s+1⌋,带入n = 63, f = 7, s = 2, p = 0,知输出为29*29,由于是32过滤器,因此有32个堆叠输出,故29*29*32
7.You have an input volume that is 32x32x16, and apply max pooling with a stride of 2 and a filter size of 2. What is the output volume?
32x32x8
15x15x16
16x16x16
16x16x8
answer(C) reason:pooling层不会改变通道数同样带入上述公式即可得知⌊(32-2)/2 +1⌋ * ⌊(32-2)/2 +1⌋ * 16=16*16*16