Closed calebrob6 closed 3 years ago
FYI -- the pretrained model weights don't work if you aren't using a GPU as the model is only wrapped in DataParallel when you have a GPU here -- https://github.com/aatifjiwani/rgb-footprint-extract/blob/main/models/deeplab/evaluate.py#L58
@calebrob6 Fixed in #7. If --no-cuda is passed in as a flag, then it will parse the weights to remove the module. prefix from the DataParallel wrapper (if needed)
--no-cuda
module.
DataParallel
FYI -- the pretrained model weights don't work if you aren't using a GPU as the model is only wrapped in DataParallel when you have a GPU here -- https://github.com/aatifjiwani/rgb-footprint-extract/blob/main/models/deeplab/evaluate.py#L58