Can I train on cpu and control layer freezing ?

[Faisal-Hajari]

[yumeng5]

Hi,

While it's possible to freeze most layers to save computation and make it possible to train on CPUs, it's not recommended to do so -- the hyperparameters (e.g., learning rate, batch size) will need to be re-tuned and there's no guarantee on how well the trained model will be. It's probably better to seek for GPU resources like Google Colab.

Best, Yu