Image-Text Retrieval Embdding with SLIP

author: David Wang

Description

This operator extracts features for image or text with SLIP, a multi-task learning framework for combining self-supervised learning and CLIP pre-training. This is an adaptation from facebookresearch/SLIP.

Code Example

Load an image from path './moon.jpg' to generate an image embedding.

Read the text 'moon in the night.' to generate a text embedding.

Write a pipeline with explicit inputs/outputs name specifications:

from towhee import pipe, ops, DataCollection

img_pipe = (
    pipe.input('url')
    .map('url', 'img', ops.image_decode.cv2_rgb())
    .map('img', 'vec', ops.image_text_embedding.slip(model_name='slip_vit_small', modality='image'))
    .output('img', 'vec')
)

text_pipe = (
    pipe.input('text')
    .map('text', 'vec', ops.image_text_embedding.slip(model_name='slip_vit_small', modality='text'))
    .output('text', 'vec')
)

DataCollection(img_pipe('./moon.jpg')).show()
DataCollection(text_pipe('moon in the night.')).show()

Factory Constructor

Create the operator via the following factory method

slip(model_name, modality)

Parameters:

​ model_name: str

​ The model name of SLIP. Supported model names:

• slip_vit_small
• slip_vit_base
• slip_vit_large

​ modality: str

​ Which modality(image or text) is used to generate the embedding.

Interface

An image-text embedding operator takes a towhee image or string as input and generate an embedding in ndarray.

Parameters:

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

​ The data (image or text based on specified modality) to generate embedding.

Returns: numpy.ndarray

​ The data embedding extracted by model.