View file src/colab/clip.py - Download

# -*- coding: utf-8 -*-
"""CLIP.ipynb

Automatically generated by Colab.

Original file is located at
    https://colab.research.google.com/drive/1X_DBCHLOElS05AdqU15S45MiAm9MgLww

https://huggingface.co/docs/transformers/model_doc/clip#notes

CLIP is a is a multimodal vision and language model motivated by overcoming the fixed number of object categories when training a computer vision model. CLIP learns about images directly from raw text by jointly training on 400M (image, text) pairs. Pretraining on this scale enables zero-shot transfer to downstream tasks. CLIP uses an image encoder and text encoder to get visual features and text features. Both features are projected to a latent space with the same number of dimensions and their dot product gives a similarity score.

You can find all the original CLIP checkpoints under the OpenAI organization.

Click on the CLIP models in the right sidebar for more examples of how to apply CLIP to different image and language tasks.

The example below demonstrates how to calculate similarity scores between multiple text descriptions and an image with Pipeline or the AutoModel class.
"""

import torch
from transformers import pipeline
import requests

url = "http://images.cocodataset.org/val2017/000000039769.jpg"

from PIL import Image
im = Image.open(requests.get(url, stream=True).raw)
im

clip = pipeline(
   task="zero-shot-image-classification",
   model="openai/clip-vit-base-patch32",
   torch_dtype=torch.bfloat16,
   device=0
)
labels = ["a photo of a cat", "a photo of a dog", "a photo of a car"]
clip(url, candidate_labels=labels)

import requests
import torch
from PIL import Image
from transformers import AutoProcessor, AutoModel

model = AutoModel.from_pretrained("openai/clip-vit-base-patch32", torch_dtype=torch.bfloat16, attn_implementation="sdpa")
processor = AutoProcessor.from_pretrained("openai/clip-vit-base-patch32")

url = "http://images.cocodataset.org/val2017/000000039769.jpg"
image = Image.open(requests.get(url, stream=True).raw)
labels = ["a photo of a cat", "a photo of a dog", "a photo of a car"]

inputs = processor(text=labels, images=image, return_tensors="pt", padding=True)

outputs = model(**inputs)
logits_per_image = outputs.logits_per_image
probs = logits_per_image.softmax(dim=1)
most_likely_idx = probs.argmax(dim=1).item()
most_likely_label = labels[most_likely_idx]
print(f"Most likely label: {most_likely_label} with probability: {probs[0][most_likely_idx].item():.3f}")