Dimensions calculator for CNN

Compute the dimensions of the output of your neural network from the parameters of its layers.

This is a simple spreadsheet that can be used to manually check the output dimensions of any neural network, layer after layer.
For now, the operations allowed are convolutions and poolings. The dimensions are computed from the parameters of each layer, namely the kernel size $k$ , the padding $p$ , the stride $s$ and the dilation rate $d$ using the formula:

$n_{out}=\left\lfloor\frac{n_{in}+2p-k-(k-1)(d-1)}{s}\right\rfloor+1$

Simply fill the spatial dimension of your input tensor here:

Input	Output
320

and the parameters of each layer of the network here:

Note: a "!" in the "Output" column means the dimension is < 0.