Closed seppestaes closed 5 years ago
Your learning rate seems quite low. Did you face the same issue for higher learning rates?
Normalize your input image may help you solve this problem
It is more likely about your settings for the training. If you have trouble with the preprocessing step please have a look to testing code (test.py).
Library versions Tensorflow 1.5.1 Keras 2.2.2 keras_vggface 0.5
Bug reports: Finetuning vggface (VGG16) using UTK dataset subset Softmax Multiclass Logistic Regression
val_loss never improves val_acc remains constant
Code Sample: