TheRenderedSST2Dataset

文档摘要

The Rendered SST2 Dataset In the paper, we used an image classification dataset called Rendered SST2, to evaluate the model's capability on optical character recognition. To do so, we rendered the sentences in the Standford Sentiment Treebank v2 dataset and used those as the input to the CLIP image encoder.

The Rendered SST2 Dataset

In the paper, we used an image classification dataset called Rendered SST2, to evaluate the model's capability on optical character recognition. To do so, we rendered the sentences in the Standford Sentiment Treebank v2 dataset and used those as the input to the CLIP image encoder.

The following command will download a 131MB archive countaining the images and extract into a subdirectory rendered-sst2:


wget https://openaipublic.azureedge.net/clip/data/rendered-sst2.tgz
tar zxvf rendered-sst2.tgz

作者与出处

原作者： Datawhale

来源：Datawhale

原文： https://github.com/datawhalechina/tiny-universe

许可证：CC BY-NC-SA 4.0

整理：灏天文库整理

由灏天文库结构化整理，提供目录导航、全文检索与在线阅读，便于系统化学习