ziyuan.tw 9552a8533e add ConvNeXt model ...

增加ConvNeXt模型和修复代码bug：模型需要输入BGR格式图像，但读取图片代码默认输出为RGB格式，造成归一化预处理错误，模型精度下降。
        Link: https://code.alibaba-inc.com/Ali-MaaS/MaaS-lib/codereview/11192762

2023-01-09 06:56:05 +08:00

..

audios

[to #42322933] feat:add speech separation pipeline

2023-01-03 13:18:44 +08:00

images

add ConvNeXt model

2023-01-09 06:56:05 +08:00

pointclouds

add cv_pointnet2_sceneflow-estimation_general

2022-12-29 08:09:57 +08:00

regression

Fix bugs in testlevel1 & 2

2022-12-01 21:16:55 +08:00

videos

Add HiTeA model for VideoQA and Caption (12.30)

2022-12-29 08:06:34 +08:00