search

okankop / Efficient-3DCNNs

PyTorch Implementation of "Resource Efficient 3D Convolutional Neural Networks", codes and pretrained models.
MIT License
777 stars 151 forks source link

How to set the parameter of lr_step #31

Closed kinfeparty closed 3 years ago

kinfeparty commented 3 years ago

Hello! I want to train the model in Jester dataset. I found that the lr_step in your code is [45, 60, 50, 200, 250].

But the code in https://github.com/ahmetgunduz/Real-time-GesRec/blob/master/opts.py is [15, 25, 35, 45, 60, 50, 200, 250].

Do you train the model with different lr_step? If I want to train my model such as large model (resnext101、resnet50) ,Which lr_step should I use?

okankop commented 3 years ago

For Jester dataset, you can use the lr steps of [15, 25, 35] and stop training after 40 epochs. You will observe that at these lr_steps, the validation loss already converges.