Skip to main content

Table 2 Default parameters setting used in our experiments

From: TasselNet: counting maize tassels in the wild via local counts regression network

Parameter Remark Value
  Network architecture AlexNet-like
  Loss function \(\ell _1\)
r Sub-image size 32
\(s_r\) Sampling stride during training r/4
\(s_e\) Sampling stride during prediction r/4
\(\sigma\) Gaussian kernel parameter 8