You can not select more than 25 topicsTopics must start with a chinese character,a letter or number, can include dashes ('-') and can be up to 35 characters long.
It is recommented that each pipleine should implement `_batch` to make a list of preprocessed data into a batched data dict.
Then by paasing batch_size=n we can use batch inference in pipline, for example
```python
img_captioning = pipeline(
Tasks.image_captioning,
model='damo/ofa_image-caption_coco_large_en')
results = img_captioning(
[{
'image': 'data/test/images/image_captioning.png'
} for _ in range(6)],
batch_size=2)
```
Link: https://code.alibaba-inc.com/Ali-MaaS/MaaS-lib/codereview/10051193