Table 8.
Number of kernels | Trained accuracy | Tested accuracy | |
---|---|---|---|
Filter 1 | Filter 2 | ||
16 | 16 | 0.8780 | 0.6732 |
32 | 0.8669 | 0.6753 | |
64 | 0.8594 | 0.6832 | |
32 | 32 | 0.8650 | 0.6740 |
64 | 0.8520 | 0.6798 | |
128 | 0.8501 | 0.6470 |
The bold values are the best values obtained in the experiment.