capdec/README.md

Image Captioning with CapDec

author: David Wang

Description

This operator generates the caption with CapDec which describes the content of the given image. ExpansionNet v2 introduces the Block Static Expansion which distributes and processes the input over a heterogeneous and arbitrarily big collection of sequences characterized by a different length compared to the input one. This is an adaptation from DavidHuji/CapDec.

Code Example

Load an image from path './image.jpg' to generate the caption.

Write the pipeline in simplified style:

import towhee

towhee.glob('./image.jpg') \
      .image_decode() \
      .image_captioning.capdec(model_name='capdec_noise_0') \
      .show()

Write a same pipeline with explicit inputs/outputs name specifications:

import towhee

towhee.glob['path']('./image.jpg') \
      .image_decode['path', 'img']() \
      .image_captioning.capdec['img', 'text'](model_name='capdec_noise_0') \
      .select['img', 'text']() \
      .show()

Factory Constructor

Create the operator via the following factory method

capdec(model_name)

Parameters:

​ model_name: str

​ The model name of CapDec. Supported model names:

• capdec_noise_0
• capdec_noise_01
• capdec_noise_001
• capdec_noise_0001

Interface

An image captioning operator takes a towhee image as input and generate the correspoing caption.

Parameters:

​ data: towhee.types.Image (a sub-class of numpy.ndarray)

​ The image to generate caption.

Returns: str

​ The caption generated by model.