Skip to content
This repository has been archived by the owner on Jul 2, 2021. It is now read-only.

Commit

Permalink
Merge pull request #257 from yuyu2172/update-0.4.10
Browse files Browse the repository at this point in the history
Update 0.4.10
  • Loading branch information
Hakuyume authored Jun 9, 2017
2 parents 72297d2 + a41cb1a commit 6476cbf
Show file tree
Hide file tree
Showing 2 changed files with 11 additions and 1 deletion.
10 changes: 10 additions & 0 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -38,6 +38,16 @@ Environments under Python 2.7.12 and 3.6.0 are tested.

# Features

## Data conventions

ChainerCV follows the following conventions.

+ Channels of a color image are ordered as RGB. The shape of an image-array is CHW (channel, height, width).
+ Axis-dependent values follow row-column order.
+ Shape of an image is always represented as `(height, width)`.
+ Coordinates of bounding boxes are ordered as `(y_min, x_min, y_max, x_max)`. `(y_min, x_min)` and `(y_max, x_max)` are coordinates of the top left and the bottom right vertices of a bounding box respectively.
+ Coordinates of keypoints are ordered as `(y, x)`.

## Models
Currently, ChainerCV supports networks for object detection and semantic segmentation.
We are planning to support networks with different tasks in the future.
Expand Down
2 changes: 1 addition & 1 deletion setup.py
Original file line number Diff line number Diff line change
Expand Up @@ -26,7 +26,7 @@

setup(
name='chainercv',
version='0.4.9',
version='0.4.10',
packages=find_packages(),
author='Yusuke Niitani',
author_email='[email protected]',
Expand Down

0 comments on commit 6476cbf

Please sign in to comment.