Table 2 Configuration table showing the network configuration of FCN used in this study. The table shows the various configuration settings used for FCN-8.
From: Optimizing FCN for devices with limited resources using quantization and sparsity enhancement
Network configuration | |
|---|---|
Epochs | 50 |
Learning rate | 0.0001 |
Mini batch size | 20 |
Optimizer | SGD |
Momentum | 0.9 |
Weight decay | 0.0002 |
\(L_2\) Regularization | None |
Samples in training set | 8498 |
Samples in validation set | 786 |
