Closed ChrisZeThird closed 1 year ago
Average is 0.424
: The network learns by heart and it learns the average value.
Method to find angle occurrence:
# Find angle occurrence
unique_angles, counts = np.unique(np.around(angle_list, 3), return_counts=True)
stat = [(angle, count) for angle, count in zip(unique_angles, counts) if count > threshold]
Can be useful.
Resampling is successful, still need to test to train the network on it.
MSE is now bigger than before
Resampling not enough to avoid network to learn by heart
MSE still at 0.01
:
Changed the parameter for resampling:
Network still learns by heart:
I can't resample too much otherwise I won't have enough data to train the network on. Need to explore other issues.
As shown in issue #7 the angles are not well distributed with a strong imbalance for angles between
0.41
and0.48
. This issue explores resampling for better training.