deplot / README.md

Update README.md

7f04d6c 11 months ago

No virus

4.32 kB

	---
	language:
	- en
	- fr
	- ro
	- de
	- multilingual
	inference: false
	pipeline_tag: visual-question-answering
	license: apache-2.0
	---
	# Model card for DePlot

	<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/model_doc/deplot_architecture.png"
	alt="drawing" width="600"/>


	# Table of Contents

	0. [TL;DR](#TL;DR)
	1. [Using the model](#using-the-model)
	2. [Contribution](#contribution)
	3. [Citation](#citation)

	# TL;DR

	The abstract of the paper states that:

	> Visual language such as charts and plots is ubiquitous in the human world. Comprehending plots and charts requires strong reasoning skills. Prior state-of-the-art (SOTA) models require at least tens of thousands of training examples and their reasoning capabilities are still much limited, especially on complex human-written queries. This paper presents the first one-shot solution to visual language reasoning. We decompose the challenge of visual language reasoning into two steps: (1) plot-to-text translation, and (2) reasoning over the translated text. The key in this method is a modality conversion module, named as DePlot, which translates the image of a plot or chart to a linearized table. The output of DePlot can then be directly used to prompt a pretrained large language model (LLM), exploiting the few-shot reasoning capabilities of LLMs. To obtain DePlot, we standardize the plot-to-table task by establishing unified task formats and metrics, and train DePlot end-to-end on this task. DePlot can then be used off-the-shelf together with LLMs in a plug-and-play fashion. Compared with a SOTA model finetuned on more than >28k data points, DePlot+LLM with just one-shot prompting achieves a 24.0% improvement over finetuned SOTA on human-written queries from the task of chart QA.


	# Using the model

	You can run a prediction by querying an input image together with a question as follows:

	```python
	from transformers import Pix2StructProcessor, Pix2StructForConditionalGeneration
	import requests
	from PIL import Image

	processor = Pix2StructProcessor.from_pretrained('google/deplot')
	model = Pix2StructForConditionalGeneration.from_pretrained('google/deplot')

	url = "https://raw.githubusercontent.com/vis-nlp/ChartQA/main/ChartQA%20Dataset/val/png/5090.png"
	image = Image.open(requests.get(url, stream=True).raw)

	inputs = processor(images=image, text="Generate underlying data table of the figure below:", return_tensors="pt")
	predictions = model.generate(**inputs, max_new_tokens=512)
	print(processor.decode(predictions[0], skip_special_tokens=True))
	```

	# Converting from T5x to huggingface

	You can use the [`convert_pix2struct_checkpoint_to_pytorch.py`](https://github.com/huggingface/transformers/blob/main/src/transformers/models/pix2struct/convert_pix2struct_original_pytorch_to_hf.py) script as follows:
	```bash
	python convert_pix2struct_checkpoint_to_pytorch.py --t5x_checkpoint_path PATH_TO_T5X_CHECKPOINTS --pytorch_dump_path PATH_TO_SAVE --is_vqa
	```
	if you are converting a large model, run:
	```bash
	python convert_pix2struct_checkpoint_to_pytorch.py --t5x_checkpoint_path PATH_TO_T5X_CHECKPOINTS --pytorch_dump_path PATH_TO_SAVE --use-large --is_vqa
	```
	Once saved, you can push your converted model with the following snippet:
	```python
	from transformers import Pix2StructForConditionalGeneration, Pix2StructProcessor

	model = Pix2StructForConditionalGeneration.from_pretrained(PATH_TO_SAVE)
	processor = Pix2StructProcessor.from_pretrained(PATH_TO_SAVE)

	model.push_to_hub("USERNAME/MODEL_NAME")
	processor.push_to_hub("USERNAME/MODEL_NAME")
	```

	# Contribution

	This model was originally contributed by Fangyu Liu, Julian Martin Eisenschlos et al. and added to the Hugging Face ecosystem by [Younes Belkada](https://huggingface.co/ybelkada).

	# Citation

	If you want to cite this work, please consider citing the original paper:
	```
	@misc{liu2022deplot,
	title={DePlot: One-shot visual language reasoning by plot-to-table translation},
	author={Liu, Fangyu and Eisenschlos, Julian Martin and Piccinno, Francesco and Krichene, Syrine and Pang, Chenxi and Lee, Kenton and Joshi, Mandar and Chen, Wenhu and Collier, Nigel and Altun, Yasemin},
	year={2022},
	eprint={2212.10505},
	archivePrefix={arXiv},
	primaryClass={cs.CL}
	}
	```