v0.3.4 & changelog

Author: Borda

.pre-commit-config.yaml

@@ -26,9 +26,8 @@ repos:
     rev: 'v0.31.0'
     hooks:
       - id: yapf
-        args: [ --in-place, --parallel ]
 
-#  - repo: https://github.com/pre-commit/mirrors-mypy
-#    rev: 'v0.902'
-#    hooks:
-#      - id: mypy
+  - repo: https://github.com/PyCQA/flake8
+    rev: 3.9.2
+    hooks:
+      - id: flake8

CHANGELOG.md

@@ -5,28 +5,20 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
 
-## [unReleased] - 2021-MM-DD
-
-### Added
-
+## [0.3.4] - 2021-06-17
 
 ### Changed
 
 - Replaced `load_boston` with `load_diabetes` in the docs and tests ([#629](https://github.com/PyTorchLightning/lightning-bolts/pull/629))
-
-
 - Added base encoder and MLP dimension arguments to BYOL constructor ([#637](https://github.com/PyTorchLightning/lightning-bolts/pull/637))
 
-
-### Deprecated
-
-
-### Removed
-
-
 ### Fixed
 
 - Fixed the MNIST download giving HTTP 503 ([#633](https://github.com/PyTorchLightning/lightning-bolts/pull/633))
+- Fixed type annotation of `ExperienceSource.__iter__` ([#645](https://github.com/PyTorchLightning/lightning-bolts/pull/645))
+- Fixed `pretrained_urls` on Windows ([#652](https://github.com/PyTorchLightning/lightning-bolts/pull/652))
+- Fixed logistic regression ([#655](https://github.com/PyTorchLightning/lightning-bolts/pull/655), [#664](https://github.com/PyTorchLightning/lightning-bolts/pull/664))
+- Fixed double softmax in `SSLEvaluator` ([#663](https://github.com/PyTorchLightning/lightning-bolts/pull/663))
 
 
 ## [0.3.3] - 2021-04-17

pl_bolts/__about__.py

@@ -1,4 +1,4 @@
-__version__ = '0.4.0dev'
+__version__ = '0.3.4'
 __author__ = 'PyTorchLightning et al.'
 __author_email__ = 'name@pytorchlightning.ai'
 __license__ = 'Apache-2.0'

pl_bolts/models/regression/logistic_regression.py

@@ -90,6 +90,7 @@ def validation_epoch_end(self, outputs: List[Dict[str, Tensor]]) -> Dict[str, Te
         return {'val_loss': val_loss, 'log': tensorboard_logs, 'progress_bar': progress_bar_metrics}
 
     def test_step(self, batch: Tuple[Tensor, Tensor], batch_idx: int) -> Dict[str, Tensor]:
+        x, y = batch
         x = x.view(x.size(0), -1)
         y_hat = self.linear(x)
         acc = accuracy(F.softmax(y_hat, -1), y)