To restore the spatial dimensions of feature maps to the original input image size in a Fully Convolutional Network (FCN), a transposed convolutional layer is employed. If the spatial dimensions need to be increased by a factor of $s$, the transposed convolution is configured with a stride of $s$. To achieve the exact original dimensions, the padding is set to $s/2$ (assuming $s/2$ is an integer), and the height and width of the convolution kernel are set to $2s$. For instance, to upscale a feature map by $32$ times, the stride is $32$, the padding is $16$, and the kernel size is $64$.

# PyTorch
net.add_module('transpose_conv', nn.ConvTranspose2d(num_classes, num_classes,
                                    kernel_size=64, padding=16, stride=32))

# MXNet
net.add(nn.Conv2DTranspose(num_classes, kernel_size=64, padding=16, strides=32))