FaceNet

FaceNet copied to clipboard

val_loss frozen at 0.2000

1

When I started training process, the val_loss fixed. Epoch 00001: val_loss improved from inf to 0.20000, saving model to models/model.01-0.2000.hdf5 Epoch 2/15 211/1539 [===>..........................] - ETA: 48:51 - loss: 0.1927...

nzinfo

Hi, Great codes. Thank you. I'm trying to understand your code structure. If I want to train on my own dataset, the process should be: Calculate embeddings > Save as...

hazxone