You can deploy this model and start earning money today!

unum-cloud/
uform-vl-english-small-gpu-fp16

Name: uform-vl-english-small-gpu-fp16
Availability: InStock

Views

No views yet

UForm

Multi-Modal Inference Library
For Semantic Search Applications

UForm is a Multi-Modal Modal Inference package, designed to encode Multi-Lingual Texts, Images, and, soon, Audio, Video, and Documents, into a shared vector space!

This is model card of the English only model with:

4 layers BERT (2 layers for unimodal encoding and rest layers for multimodal encoding)
ViT-S/16 (image resolution is 224x224)

If you need Multilingual model, check this.

Evaluation

The following metrics were obtained with multimodal re-ranking (text-to-image retrieval):

Dataset	Recall@1	Recall@5	Recall@10
Zero-Shot Flickr	0.565	0.790	0.860
Zero-Shot MS-COCO	0.281	0.525	0.645

ImageNet-Top1: 0.361
ImageNet-Top5: 0.608

Installation

pip install uform[onnx-gpu]

Usage

To load the model:

python

import uform

model, processor = uform.get_model_onnx('unum-cloud/uform-vl-english-small', device='gpu', dtype='fp16')

To encode data:

python

from PIL import Image

text = 'a small red panda in a zoo'
image = Image.open('red_panda.jpg')

image_data = processor.preprocess_image(image)
text_data = processor.preprocess_text(text)

image_features, image_embedding = model.encode_image(image_data, return_features=True)
text_features, text_embedding = model.encode_text(text_data, return_features=True)
score, joint_embedding = model.encode_multimodal(
    image_features=image_features,
    text_features=text_features,
    attention_mask=text_data['attention_mask'],
    return_scores=True
)

There are two options to calculate semantic compatibility between an image and a text: cosine similarity and Matching Score.

Cosine Similarity

The similarity will belong to the [-1, 1] range, 1 meaning the absolute match.

Pros:

Computationally cheap.
Only unimodal embeddings are required, unimodal encoding is faster than joint encoding.
Suitable for retrieval in large collections.

Cons:

Takes into account only coarse-grained features.

Matching Score

Unlike cosine similarity, unimodal embedding are not enough. Joint embedding will be needed and the resulting score will belong to the [0, 1] range, 1 meaning the absolute match.