《Table 3 Recognition accuracy w ith different feature dimensions》

  提示：宽带有限、当前游客访问压缩模式

本系列图表出处文件名：随高清版一同展现

《Individual Dairy Cattle Recognition Based on Deep Convolutional Neural Network》

1. 获取 高清版本忘记账户？点击这里登录

1. 下载图表忘记账户？点击这里登录

To verify the effect of feature dimension tow ards recognition results，different feature dimensions in full connection layer are chosen for experiments.The feature w ill not be described w ell if the dimension is small just as the results of choosing 1 024，2 048，and 3 072 show n in Table 3.When the feature dimension is 4 096，the recognition accuracy is good.Continuing to increase the dimension，the training sample recognition rate is better but the training sample result is not ideal because too big feature dimension makes over-fitting phenomenon[38].