2019-04-15から1日間の記事一覧
All pre-trained models expect input images normalized in the same way, i.e. mini-batches of 3-channel RGB images of shape (3 x H x W), where H and W are expected to be at least 224. https://pytorch.org/docs/stable/torchvision/models.html
@classmethod def create_from_ll(cls, lls:LabelLists, bs:int=64, val_bs:int=None, ds_tfms:Optional[TfmList]=None, num_workers:int=defaults.cpus, dl_tfms:Optional[Collection[Callable]]=None, device:torch.device=None, test:Optional[PathOrStr]…