huggingface--transformers/docs/source/en/model_doc/textnet.md

This model was published in HF papers on 2021-11-03 and contributed to Hugging Face Transformers on 2025-01-08.

TextNet

Overview

The TextNet model was proposed in FAST: Faster Arbitrarily-Shaped Text Detector with Minimalist Kernel Representation by Zhe Chen, Jiahao Wang, Wenhai Wang, Guo Chen, Enze Xie, Ping Luo, Tong Lu. TextNet is a vision backbone useful for text detection tasks. It is the result of neural architecture search (NAS) on backbones with reward function as text detection task (to provide powerful features for text detection).

TextNet backbone as part of FAST. Taken from the original paper.

This model was contributed by Raghavan, jadechoghari and nielsr.

Usage tips

TextNet is mainly used as a backbone network for the architecture search of text detection. Each stage of the backbone network is comprised of a stride-2 convolution and searchable blocks. Specifically, we present a layer-level candidate set, defined as {conv3×3, conv1×3, conv3×1, identity}. As the 1×3 and 3×1 convolutions have asymmetric kernels and oriented structure priors, they may help to capture the features of extreme aspect-ratio and rotated text lines.

TextNet is the backbone for Fast, but can also be used as an efficient text/image classification, we add a TextNetForImageClassification as is it would allow people to train an image classifier on top of the pre-trained textnet weights

TextNetConfig

autodoc TextNetConfig

TextNetImageProcessor

autodoc TextNetImageProcessor - preprocess

TextNetImageProcessorPil

autodoc TextNetImageProcessorPil - preprocess

TextNetModel

autodoc TextNetModel - forward

TextNetForImageClassification

autodoc TextNetForImageClassification - forward