| words = ["hello", "world"] | |
| boxes = [[1, 2, 3, 4], [5, 6, 7, 8]] # make sure to normalize your bounding boxes | |
| encoding = processor(image, question, words, boxes=boxes, return_tensors="pt") | |
| print(encoding.keys()) | |
| dict_keys(['input_ids', 'token_type_ids', 'attention_mask', 'bbox', 'image']) | |
| LayoutLMv2Config | |
| [[autodoc]] LayoutLMv2Config | |
| LayoutLMv2FeatureExtractor | |
| [[autodoc]] LayoutLMv2FeatureExtractor | |
| - call | |
| LayoutLMv2ImageProcessor | |
| [[autodoc]] LayoutLMv2ImageProcessor | |
| - preprocess | |
| LayoutLMv2Tokenizer | |
| [[autodoc]] LayoutLMv2Tokenizer | |
| - call | |
| - save_vocabulary | |
| LayoutLMv2TokenizerFast | |
| [[autodoc]] LayoutLMv2TokenizerFast | |
| - call | |
| LayoutLMv2Processor | |
| [[autodoc]] LayoutLMv2Processor | |
| - call | |
| LayoutLMv2Model | |
| [[autodoc]] LayoutLMv2Model | |
| - forward | |
| LayoutLMv2ForSequenceClassification | |
| [[autodoc]] LayoutLMv2ForSequenceClassification | |
| LayoutLMv2ForTokenClassification | |
| [[autodoc]] LayoutLMv2ForTokenClassification | |
| LayoutLMv2ForQuestionAnswering | |
| [[autodoc]] LayoutLMv2ForQuestionAnswering |