Skip to content
This repository has been archived by the owner on Oct 9, 2023. It is now read-only.

Commit

Permalink
Remove redundant num_features arg from Classification model (#88)
Browse files Browse the repository at this point in the history
* remove num_features arg from Classification model

* add annotations to args

Co-authored-by: Jirka Borovec <[email protected]>
  • Loading branch information
kaushikb11 and Borda authored Feb 8, 2021
1 parent 13acf78 commit 841986a
Showing 1 changed file with 3 additions and 4 deletions.
7 changes: 3 additions & 4 deletions flash/vision/classification/model.py
Original file line number Diff line number Diff line change
Expand Up @@ -38,10 +38,9 @@ class ImageClassifier(ClassificationTask):

def __init__(
self,
num_classes,
backbone="resnet18",
num_features: int = None,
pretrained=True,
num_classes: int,
backbone: str = "resnet18",
pretrained: bool = True,
loss_fn: Callable = F.cross_entropy,
optimizer: Type[torch.optim.Optimizer] = torch.optim.SGD,
metrics: Union[Callable, Mapping, Sequence, None] = (Accuracy()),
Expand Down

0 comments on commit 841986a

Please sign in to comment.