Skip to main content

Table 1 Details of each encoder block and corresponding max-pool

From: SpikeSegNet-a deep learning approach utilizing encoder-decoder network with hourglass for spike segmentation and counting in wheat plant from visual imaging

Encoder block #

Input to encoder block

Convolution filter size

Number of convolution filter

Output of encoder block

Input to max-pool

Output to max-pool

Block 1

256 * 256 (patch image)

3 * 3

16

256 * 256 * 16

256 * 256 * 16

128 * 128 * 16

Block 2

128 * 128 * 16

3 * 3

64

128 * 128 * 64

128 * 128 * 64

64 * 64 * 64

Block 3

64 * 64 * 64

3 * 3

128

64 * 64 * 128

64 * 64 * 128

32 * 32 * 128

Back to article page

Plant Methods

ISSN: 1746-4811