Some question about the training process

[EnQing626]

Hi xiankai, thanks for the sharing codes. I have some questions about the training process.

1. I noticed that your shared code 'train_iteration_conf.py' firstly loads the pre-trained model named 'deeplab_davis_12_0.pth'. Have you pre-trained this model from saliency datasets(MSRA10K and DUT), which means that the saliency datasets are used both in pre-training and fine-tuning (on DAVIS16)?

2. For the fucntion 'get_1x_lr_params' and 'get_10x_lr_params', why the setting is different by using single GPU and multiple GPUs?

Thank you

[carrierlxk]

Hi, thanks for your interest in our work.
Q1, we use saliency datasets for both pre-training and finetuning.
Q2, The reason is that if you use multiple GPUs, the keys of the saved model have a pre-fix: 'module'. If you train the model on a single GPU, the saved model has no 'module'.