Resume Training using a checkpoint?

keithito / tacotron

A TensorFlow implementation of Google's Tacotron speech synthesis with pre-trained model (unofficial)

MIT License

2.94k stars 965 forks source link

Open berkaycinci opened 3 years ago

berkaycinci commented 3 years ago

Do you have suggestions to resume training from a checkpoint? How can i modify code to do that? @keithito

Riha1992 commented 3 years ago

You can simply run the following command: python train.py --restore_step = xxxx

berkaycinci commented 3 years ago

Thanks @Riha1992