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This repository has been archived by the owner on Oct 9, 2023.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

Commit

Permalink
v0.2.3
Browse files Browse the repository at this point in the history
  • Loading branch information
Borda committed Apr 17, 2021
1 parent c3f01d2 commit 03ccce3
Show file tree
Hide file tree
Showing 3 changed files with 13 additions and 2 deletions.
11 changes: 11 additions & 0 deletions CHANGELOG.md
Original file line number Diff line number Diff line change
Expand Up @@ -5,6 +5,17 @@ All notable changes to this project will be documented in this file.
The format is based on [Keep a Changelog](http://keepachangelog.com/en/1.0.0/).


## [0.2.3] - 2021-04-17

### Added

- Added TIMM integration as backbones ([#196](https://github.com/PyTorchLightning/lightning-flash/pull/196))

### Fixed

- Fixed `nltk.download` ([#210](https://github.com/PyTorchLightning/lightning-flash/pull/210))


## [0.2.2] - 2021-04-05

### Changed
Expand Down
2 changes: 1 addition & 1 deletion flash/__init__.py
Original file line number Diff line number Diff line change
Expand Up @@ -14,7 +14,7 @@
"""Root package info."""
import os

__version__ = "0.2.2"
__version__ = "0.2.3"
__author__ = "PyTorchLightning et al."
__author_email__ = "[email protected]"
__license__ = 'Apache-2.0'
Expand Down
2 changes: 1 addition & 1 deletion tests/core/test_model.py
Original file line number Diff line number Diff line change
Expand Up @@ -44,7 +44,7 @@ def __len__(self) -> int:

@pytest.mark.parametrize("metrics", [None, pl.metrics.Accuracy(), {"accuracy": pl.metrics.Accuracy()}])
def test_classificationtask_train(tmpdir: str, metrics: Any):
model = nn.Sequential(nn.Flatten(), nn.Linear(28 * 28, 10), nn.LogSoftmax())
model = nn.Sequential(nn.Flatten(), nn.Linear(28 * 28, 10), nn.Softmax())
train_dl = torch.utils.data.DataLoader(DummyDataset())
val_dl = torch.utils.data.DataLoader(DummyDataset())
task = ClassificationTask(model, F.nll_loss, metrics=metrics)
Expand Down

0 comments on commit 03ccce3

Please sign in to comment.