Image-Text Retrieval Embdding with CLIP

author: David Wang

Description

This operator extracts features for image or text with CLIP which can generate embeddings for text and image by jointly training an image encoder and text encoder to maximize the cosine similarity.

Code Example

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

Read the text 'A teddybear on a skateboard in Times Square.' to generate an text embedding.

Write the pipeline in simplified style:

import towhee

towhee.glob('./teddy.jpg') \
      .image_decode() \
      .towhee.clip(model_name='ViT-B/32', modality='image') \
      .show()

towhee.dc(["A teddybear on a skateboard in Times Square."]) \
      .towhee.clip(model_name='ViT-B/32', modality='text') \
      .show()

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

import towhee

towhee.glob['path']('./teddy.jpg') \
      .image_decode['path', 'img']() \
      .towhee.clip['img', 'vec'](model_name='ViT-B/32', modality='image') \
      .select['img', 'vec']() \
      .show()

towhee.dc['text'](["A teddybear on a skateboard in Times Square."]) \
      .towhee.clip['text','vec'](model_name='ViT-B/32', modality='text') \
      .select['text', 'vec']() \
      .show()

Factory Constructor

Create the operator via the following factory method

clip(model_name, modality)

Parameters:

​ model_name: str

​ The model name of CLIP. Supported model names:

• clip_resnet_r50
• clip_resnet_r101
• clip_vit_b32
• clip_vit_b16

​ 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.