From aebd7c020745dad18c4b0b60cb807a5c733c721c Mon Sep 17 00:00:00 2001 From: wxywb Date: Thu, 3 Nov 2022 14:42:11 +0800 Subject: [PATCH] add the doc Signed-off-by: wxywb --- README.md | 108 +++++++++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 107 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index a7ed215..3c702f5 100644 --- a/README.md +++ b/README.md @@ -1,2 +1,108 @@ -# albef +# Image-Text Retrieval Embdding with ALBEF + +*author: David Wang* + + +
+ + + +## Description + +This operator extracts features for image or text with [ALBEF](https://arxiv.org/abs/2103.00020) which can generate embeddings for text and image by jointly training an image encoder and text encoder to maximize the cosine similarity. This research introduced a contrastive loss to ALign the image and text representations BEfore Fusing (ALBEF) them through cross-modal attention, which enables more grounded vision and language representation learning. This repo is an adaptation from [salesforce / ALBEF](https://github.com/salesforce/ALBEF) + + +
+ + +## 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*: + +```python +import towhee + +towhee.glob('./teddy.jpg') \ + .image_decode() \ + .image_text_embedding.albef(model_name='albef_4m', modality='image') \ + .show() + +towhee.dc(["A teddybear on a skateboard in Times Square."]) \ + .image_text_embedding.albef(model_name='albef_4m', modality='text') \ + .show() +``` +result1 +result2 + +*Write a same pipeline with explicit inputs/outputs name specifications:* + +```python +import towhee + +towhee.glob['path']('./teddy.jpg') \ + .image_decode['path', 'img']() \ + .image_text_embedding.albef['img', 'vec'](model_name='albef_4m', modality='image') \ + .select['img', 'vec']() \ + .show() + +towhee.dc['text'](["A teddybear on a skateboard in Times Square."]) \ + .image_text_embedding.albef['text','vec'](model_name='albef_4m', modality='text') \ + .select['text', 'vec']() \ + .show() +``` +result1 +result2 + + +
+ + + +## Factory Constructor + +Create the operator via the following factory method + +***albef(model_name, modality)*** + +**Parameters:** + +​ ***model_name:*** *str* + +​ The model name of ALBEF. Supported model names: +- albef_4m +- albef_14m + + +​ ***modality:*** *str* + +​ Which modality(*image* or *text*) is used to generate the embedding. + +
+ + + +## Interface + +An image-text embedding operator takes a [towhee image](link/to/towhee/image/api/doc) 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. + + + +