Skip to main content
. 2021 Jan 26;7:e349. doi: 10.7717/peerj-cs.349

Table 3. Comparison results of the number of parameters of the UNET model with dense network incorporating either improved dilation convolution module (IDC) or dilation convolution module.

Here DID-UNET refers to the inclusion of dense networks and IDC module and DD-UNET denotes dense networks and traditional dilation convolution added to the UNET structure.

Method Total parameters Trainable parameters Non-trainable parameters Train time epoch/(s) Test time (s)
DD-UNET 56,223,034 56,190,272 32,762 145 8
DID-UNET 52,162,362 52,132,416 29,946 135 3