blip_image_embeddings

radames/blip_image_embeddings

blip_image_embeddings is a feature extraction model from radames. Use it when you need embeddings to search or compare text. It is set up for transformers. The card lists the license as bsd-3-clause.

This repository implements a custom task for feature-extraction for 🤗 Inference Endpoints. The code for the customized pipeline is in the pipeline.py. To use deploy this model a an Inference Endpoint you have to sele…

Downloads · 30 days

Access

Public

Updated Jun 9, 2024

Repo size

3.7 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.pth3.7 GB · 100%

At a glance

Task: Feature Extraction
Library: transformers
License: bsd-3-clause
Access: Public
Created: Apr 11, 2023
Updated: Jun 9, 2024
SHA: dace0eb4

Try a prompt

Spaces

amengdewo/radames-blip_image_embeddings

Model card

From the Hugging Face model README

Fork of salesforce/BLIP for a `feature-extraction` task on 🤗Inference endpoint.

This repository implements a custom task for feature-extraction for 🤗 Inference Endpoints. The code for the customized pipeline is in the pipeline.py. To use deploy this model a an Inference Endpoint you have to select Custom as task to use the pipeline.py file. -> double check if it is selected

expected Request payload

{
  "inputs": "/9j/4AAQSkZJRgABAQEBLAEsAAD/2wBDAAMCAgICAgMC....", // base64 image as bytes
}

below is an example on how to run a request using Python and requests.

Run Request

prepare an image.

!wget https://huggingface.co/datasets/mishig/sample_images/resolve/main/palace.jpg

2.run request

import json
from typing import List
import requests as r
import base64
ENDPOINT_URL = "https://api-inference.huggingface.co/models/radames/blip_image_embeddings"
HF_TOKEN = ""
def predict(path_to_image: str = None):
    with open(path_to_image, "rb") as i:
        b64 = base64.b64encode(i.read())
    payload = {"inputs": b64.decode("utf-8")}
    response = r.post(
        ENDPOINT_URL, headers={"X-Wait-For-Model": "true", "Authorization": f"Bearer {HF_TOKEN}"}, json=payload
    )
    return response.json()
prediction = predict(
    path_to_image="palace.jpg"
)

expected output

[0.016450975090265274,
  -0.5551009774208069,
  0.39800673723220825,
  -0.6809228658676147,
  2.053842782974243,
  -0.4712907075881958,...]

Task: Feature Extraction
Library: transformers
License: bsd-3-clause
Created: Apr 11, 2023
Updated: Jun 9, 2024