Table 3 The hardware, software, and hyperparameters configurations for the deep learning model
From: Image analysis-based recognition and quantification of grain number per panicle in rice
Project | Content |
|---|---|
CPU | Intel Xeon E5-2682v4 |
RAM | 16 G |
GPU | Nvidia Tesla P4 |
Operating system | Ubuntu 16.04 LTS |
Cuda | Cuda8.0 with Cudnn v6 |
Data processing | Python2.7, OpenCV, LabelImg, etc. |
Deep learning framework | TensorFlow |
Deep learning algorithm | Faster RCNN ResNet101 |
Num classes | 2 (Japonica rice grain and Indica rice grain) |
Batch size | 1 |
Initial learning rate | 0.0003 |
Learning rate | 0.0003 |
Iteration steps | 30,000 |
Minimum confidence | 0.9 |