Skip to content

Commit

Permalink
update to 0.9.0
Browse files Browse the repository at this point in the history
  • Loading branch information
haiasd committed Jan 17, 2023
1 parent 3953bd2 commit c300956
Show file tree
Hide file tree
Showing 4 changed files with 36 additions and 3 deletions.
6 changes: 6 additions & 0 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -46,6 +46,12 @@ EasyCV is an all-in-one computer vision toolbox based on PyTorch, mainly focuses


## What's New
[🔥 2023.01.17]

* 17/01/2023 EasyCV v0.9.0 was released.
- Support Single-lens MOT
- Support video recognition (X3D, SWIN-video)

[🔥 2022.12.02]

* 02/12/2022 EasyCV v0.8.0 was released.
Expand Down
8 changes: 7 additions & 1 deletion README_zh-CN.md
Original file line number Diff line number Diff line change
Expand Up @@ -45,9 +45,15 @@ EasyCV是一个涵盖多个领域的基于Pytorch的计算机视觉工具箱,


## 最新进展
[🔥 2023.01.17]

* 17/01/2023 EasyCV v0.9.0 was released.
- 支持单镜头多目标跟踪。
- 增加视频识别算法 (X3D, SWIN-video)

[🔥 2022.12.02]

* 02/12/2022 EasyCV v0.8.0 was released.
* 02/12/2022 EasyCV v0.8.0 版本发布.
- bevformer-base NDS在nuscenes val上提升0.8,训练速度提升10%,推理速度提升40%。
- 支持Objects365预训练,加入DINO++模型在200M模型规模下可达到63.4mAP的精度(同等规模下精度最佳)。

Expand Down
21 changes: 21 additions & 0 deletions docs/source/change_log.md
Original file line number Diff line number Diff line change
@@ -1,3 +1,24 @@
# v 0.9.0 (17/01/2023)

## Highlights
- Support Single-lens MOT ([#258](https://github.com/alibaba/EasyCV/pull/258))
- Support video recognition (X3D, SWIN-video) ([#256](https://github.com/alibaba/EasyCV/pull/256))

## New Features
- Add inception config and voc config for FCN and UperNet ([#261](https://github.com/alibaba/EasyCV/pull/261))
- Add inference time under V100 for the benchmark of deitiii and hydra attention ([#251](https://github.com/alibaba/EasyCV/pull/251))
- Add bev-blancehybrid benchmark ([#249](https://github.com/alibaba/EasyCV/pull/249))

## Improvements
- Optimize data source apis ([#254](https://github.com/alibaba/EasyCV/pull/254))
- Update predict.py to support input model directory ([#252](https://github.com/alibaba/EasyCV/pull/252))


## Bug Fixes
- Fix MAE arg error after timm upgrade ([#255](https://github.com/alibaba/EasyCV/pull/255))
- Fix export SSL models bug, avoid loading default pretrained backbone model ([#257](https://github.com/alibaba/EasyCV/pull/257))
- Fix bug can't find config files while easycv is installed ([#253](https://github.com/alibaba/EasyCV/pull/253))

# v 0.8.0 (5/12/2022)

## Highlights
Expand Down
4 changes: 2 additions & 2 deletions easycv/version.py
Original file line number Diff line number Diff line change
Expand Up @@ -2,5 +2,5 @@
# GENERATED VERSION FILE
# TIME: Thu Nov 5 14:17:50 2020

__version__ = '0.8.0'
short_version = '0.8.0'
__version__ = '0.9.0'
short_version = '0.9.0'

0 comments on commit c300956

Please sign in to comment.