Medix-AI/coqui-tts
Medix-AI
/
coqui-tts
mirror of https://github.com/coqui-ai/TTS.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

pick best model by loss function is run_eval is true

This commit is contained in:
Eren Golge 2019-02-05 11:55:41 +01:00
parent e12bbc2a5c
commit 0308c92c16
1 changed files with 4 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
train.py
View File

@ -429,7 +429,10 @@ def main(args):
" | > Train Loss: {:.5f} Validation Loss: {:.5f}".format( " | > Train Loss: {:.5f} Validation Loss: {:.5f}".format(
train_loss, val_loss), train_loss, val_loss),
flush=True) flush=True)
best_loss = save_best_model(model, optimizer, train_loss, best_loss, target_loss = train_loss
if c.run_eval:
target_loss = val_loss
best_loss = save_best_model(model, optimizer, target_loss, best_loss,
OUT_PATH, current_step, epoch) OUT_PATH, current_step, epoch)