fix figure
This commit is contained in:
ArrowLuo
Родитель
c2a5a4ed18
Коммит
0a7c07f566
|
|
@ -3,6 +3,8 @@ The implementation of paper [**UniVL: A Unified Video and Language Pre-Training
|
||||||
|
|
||||||
UniVL is a **video-language pretrain model**. It is designed with four modules and five objectives for both video language understanding and generation tasks. It is also a flexible model for most of the multimodal downstream tasks considering both efficiency and effectiveness.
|
UniVL is a **video-language pretrain model**. It is designed with four modules and five objectives for both video language understanding and generation tasks. It is also a flexible model for most of the multimodal downstream tasks considering both efficiency and effectiveness.
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
# Preliminary
|
# Preliminary
|
||||||
Execute below scripts in the main folder firstly. It will avoid *download conflict* when doing distributed pretrain.
|
Execute below scripts in the main folder firstly. It will avoid *download conflict* when doing distributed pretrain.
|
||||||
```
|
```
|
||||||
|
|
|
||||||
Двоичный файл не отображается.
|
После Ширина: | Высота: | Размер: 83 KiB |
Двоичные данные
assets/imgs/UniVL_framework.png
Двоичные данные
assets/imgs/UniVL_framework.png
Двоичный файл не отображается.
|
До Ширина: | Высота: | Размер: 78 KiB |
Загрузка…
Ссылка в новой задаче