Figure 1.
Network structure
TABLE I.
OPTIMIZER PARAMETER SETTING
| Optimizer | parameter |
|---|---|
| SGD | lr=0.001, |
| Adam | lr=0.001, |
| Adamax | lr=0.002, |
| RMSprop | lr=0.001, |
Figure 2.
Optimizer effect
TABLE II.
OPTIMIZERS TRAINING RESULTS
| optimizer | Top Accuracy/% |
|---|---|
| SGD | 87.350184 |
| Adam | 89.090000 |
| Adamax | 88.955900 |
| RMSprop | 88.676000 |
TABLE III.
RESULT OF DIFFERENT WEIGHT DECAY
| weight_decay | Train Acc%(e) | Test Acc%(e) |
|---|---|---|
| 0.01 | 89.01538(85) | 87.14659(85) |
| 0.005 | 91.59397(57) | 88.95590(57) |
| 0.0025 | 94.51470(88) | 90.01229(88) |
| 0.001 | 97.21119(90) | 89.70498(24) |
Figure 3.
Training Accuracy of different regularization
Figure 4.
Training Loss of different regularization
Figure 5.
Test Accuracy of different regularization
Figure 6.
Tetst Loss of different regularization
Figure 7.
SVHN-Complete house number
Figure 8.
SVHN-Part number
TABLE IV.
AUGMENTATION RESULT
| Subset category | Number of samples |
|---|---|
| Training set | 73257 |
| Extra set | 531131 |
| Test set | 26032 |
Figure 9.
Example of train set
Figure 10.
Example of extra set
Figure 11.
Example of test set
Figure 12.
Category distribution of SVHN
TABLE V.
RESULT AFTER DATA AUGMENTATION
| Train sample number | test sample number | Best test accuracy | time |
|---|---|---|---|
| 73257 | 26032 | 90.01229 | 1h24min |
| 604388 | 26032 | 92.32483 | 6h17min |
Figure 13.
Training of the model after adding data augmentation
Figure 14.
Figure 1 Test result