Summary of the calculation formula of feature map size in convolutional neural network

W : the width of the input feature map, H : the height of the input feature map

K : kernel size convolution kernel width and height, P : padding (the number of 0s that need to be filled in the feature map ), S : stride step size

width_out : the width of the output feature map after convolution, height_out : the height of the output feature map after convolution

Ordinary convolution

Calculation formula:

width_out = (W - K + 2 * P) / S + 1 (rounded down)

height_out = (H - K + 2 * P) / S + 1 (rounded down)

pooling

Calculation formula:

width_out = (W - K) / S + 1 (round down)

height_out = (H - K) / S + 1 (rounded down)

Upsampling UpSampling2D

Upsampling is equivalent to how many times to enlarge , size=multiple

Calculation formula:

width_out = W * size

height_out = H * size

transposed convolution

Transposed convolution, commonly known as deconvolution, is one of the upsampling methods. Transposed convolution is used to increase the resolution of the feature map.

Calculation formula:

width_out = （W - 1）* S - 2 * P + K

height_out = （H - 1）* S - 2 * P + K