Image Captioning with MAGIC

author: David Wang

Description

This operator generates the caption with MAGIC which describes the content of the given image. MAGIC is a simple yet efficient plug-and-play framework, which directly combines an off-the-shelf LM (i.e., GPT-2) and an image-text matching model (i.e., CLIP) for image-grounded text generation. During decoding, MAGIC influences the generation of the LM by introducing a CLIP-induced score, called magic score, which regularizes the generated result to be semantically related to a given image while being coherent to the previously generated context. This is an adaptation from yxuansu / MAGIC.

Code Example

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

Write a pipeline with explicit inputs/outputs name specifications:

from towhee import pipe, ops, DataCollection

p = (
    pipe.input('url')
    .map('url', 'img', ops.image_decode.cv2_rgb())
    .map('img', 'text', ops.image_captioning.magic(model_name='magic_mscoco')) 
    .output('img', 'text')
)

DataCollection(p('./image.jpg')).show()

Factory Constructor

Create the operator via the following factory method

magic(model_name)

Parameters:

​ model_name: str

​ The model name of MAGIC. Supported model names:

• magic_mscoco

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.