andreasjansson / clip-features

Return CLIP features for the clip-vit-large-patch14 model

  • Public
  • 66M runs
  • GitHub

Run time and cost

This model costs approximately $0.00022 to run on Replicate, or 4545 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia T4 GPU hardware. Predictions typically complete within 1 seconds.

Readme

Cog model that outputs clip-vit-large-patch14 features for text and images.

Run with the API:

import replicate
import numpy as np
from numpy.linalg import norm

def cos_sim(a, b):
    return np.dot(a, b) / (norm(a) * norm(b))

inputs = """
a photo of a dog
a cat
two cats with remote controls
https://replicate.com/api/models/cjwbw/clip-vit-large-patch14/files/36b04aec-efe2-4dea-9c9d-a5faca68b2b2/000000039769.jpg
"""

# run prediction
model = replicate.models.get("andreasjansson/clip-features")
outputs = model.predict(inputs=inputs)

# output similarity of the three text lines with the image on line 4
for i in range(3):
    print(outputs[i]["input"])
    print(cos_sim(outputs[i]["embedding"], outputs[3]["embedding"]))
    print()
"""

# run prediction
model = replicate.models.get("andreasjansson/clip-features")
outputs = model.predict(inputs=inputs)

# output similarity of the three text lines with the image on line 4
for i in range(3):
    print(outputs[i].input)
    print(cos_sim(outputs[i].embedding, outputs[3].embedding))
    print()