---
title: deplot
canonical_url: "https://www.modelscope.cn/models/cubeai/deplot"
md_url: "https://www.modelscope.cn/models/cubeai/deplot.md"
repository: cubeai/deplot
chinese_name: "看图问答(deplot)"
last_updated: 2024-03-06
license: "Apache License 2.0"
pipeline_tag: visual-question-answering
tasks:
  - visual-question-answering
model_type:
  - pix2struct
architectures:
  - Pix2StructForConditionalGeneration
parameters: 282.3M
tensor_type:
  - F32
library_name:
  - safetensors
  - pytorch
frameworks:
  - Pytorch
downloads: 75
stars: 0
---

# deplot

> deplot - cubeai 在 ModelScope 开源的模型。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…

cubeai/deplot 是 ModelScope 魔搭社区上的 282.3M 参数visual-question-answering模型，采用 Apache License 2.0 许可。

- **Repository**: cubeai/deplot
- **License**: Apache License 2.0
- **Tasks**: visual-question-answering
- **Parameters**: 282.3M
- **Downloads**: 75
- **Stars**: 0
- **Last updated**: 2024-03-06

Source: https://www.modelscope.cn/models/cubeai/deplot

---

# 看图问答(deplot)

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.

## 使用

https://openi.pcl.ac.cn/cubeai-model-zoo/hf_google_deplot

## 模型来源

https://hf-mirror.com/google/deplot