You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: CHANGELOG.md
+9-6Lines changed: 9 additions & 6 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -4,14 +4,10 @@ All notable changes to this project will be documented in this file.
4
4
The format is based on [Keep a Changelog](http://keepachangelog.com/en/1.0.0/)
5
5
and this project adheres to [Semantic Versioning](http://semver.org/spec/v2.0.0.html).
6
6
7
-
## 0.0.2 - 2017-11-12
7
+
## [0.1.0] - 2017-11-12
8
8
### Added
9
9
- Implemented reconstruction loss.
10
10
- Saving reconstructed image as file.
11
-
- Bug fixes:
12
-
- Missing square in equation 4 for margin (class) loss.
13
-
- More intuitive variable naming.
14
-
- Resolve Pylint warnings and reformat code.
15
11
- Improve training speed by using PyTorch DataParallel to wrap our model.
16
12
- PyTorch will parallelized the model and data over multiple GPUs.
17
13
- Supports training:
@@ -21,9 +17,16 @@ and this project adheres to [Semantic Versioning](http://semver.org/spec/v2.0.0.
21
17
- with or without CUDA (tested with CUDA version 8.0.61)
22
18
- cuDNN 5 (tested with cuDNN 5.1.3)
23
19
20
+
### Changed
21
+
- More intuitive variable naming.
22
+
23
+
### Fixed
24
+
- Resolve Pylint warnings and reformat code.
25
+
- Missing square in equation 4 for margin (class) loss.
26
+
24
27
## 0.0.1 - 2017-11-04
25
28
### Added
26
29
- Initial release. The first beta version. API is stable. The code runs. So, I think it's safe to use for development but not ready for general production usage.
0 commit comments