File size: 295 Bytes
5fa1a76
 
 
 
 
 
 
1
2
3
4
5
6
7
[ViltProcessor] wraps a BERT tokenizer and ViLT image processor into a convenient single processor:
 

from transformers import ViltProcessor
processor = ViltProcessor.from_pretrained(model_checkpoint)

To preprocess the data we need to encode the images and questions using the [ViltProcessor].