CLIP Image-Text Matching

pip install git+https://github.com/openai/CLIP.git
pip install torch torchvision ftfy regex tqdm

import torch
import clip
from PIL import Image

# Load model
device = "cuda" if torch.cuda.is_available() else "cpu"
model, preprocess = clip.load("ViT-B/32", device=device)

# Load image
image = preprocess(Image.open("photo.jpg")).unsqueeze(0).to(device)

# Define possible labels
text = clip.tokenize(["a dog", "a cat", "a bird", "a car"]).to(device)

# Compute similarity
with torch.no_grad():
    image_features = model.encode_image(image)
    text_features = model.encode_text(text)

    # Cosine similarity
    logits_per_image, logits_per_text = model(image, text)
    probs = logits_per_image.softmax(dim=-1).cpu().numpy()

# Print results
labels = ["a dog", "a cat", "a bird", "a car"]
for label, prob in zip(labels, probs[0]):
    print(f"{label}: {prob:.2%}")

# Models (sorted by size)
models = [
    "RN50",           # ResNet-50
    "RN101",          # ResNet-101
    "ViT-B/32",       # Vision Transformer (recommended)
    "ViT-B/16",       # Better quality, slower
    "ViT-L/14",       # Best quality, slowest
]

model, preprocess = clip.load("ViT-B/32")

# Compute embeddings
image_features = model.encode_image(image)
text_features = model.encode_text(text)

# Normalize
image_features /= image_features.norm(dim=-1, keepdim=True)
text_features /= text_features.norm(dim=-1, keepdim=True)

# Cosine similarity
similarity = (image_features @ text_features.T).item()
print(f"Similarity: {similarity:.4f}")

# Index images
image_paths = ["img1.jpg", "img2.jpg", "img3.jpg"]
image_embeddings = []

for img_path in image_paths:
    image = preprocess(Image.open(img_path)).unsqueeze(0).to(device)
    with torch.no_grad():
        embedding = model.encode_image(image)
        embedding /= embedding.norm(dim=-1, keepdim=True)
    image_embeddings.append(embedding)

image_embeddings = torch.cat(image_embeddings)

# Search with text query
query = "a sunset over the ocean"
text_input = clip.tokenize([query]).to(device)
with torch.no_grad():
    text_embedding = model.encode_text(text_input)
    text_embedding /= text_embedding.norm(dim=-1, keepdim=True)

# Find most similar images
similarities = (text_embedding @ image_embeddings.T).squeeze(0)
top_k = similarities.topk(3)

for idx, score in zip(top_k.indices, top_k.values):
    print(f"{image_paths[idx]}: {score:.3f}")

# Define categories
categories = [
    "safe for work",
    "not safe for work",
    "violent content",
    "graphic content"
]

text = clip.tokenize(categories).to(device)

# Check image
with torch.no_grad():
    logits_per_image, _ = model(image, text)
    probs = logits_per_image.softmax(dim=-1)

# Get classification
max_idx = probs.argmax().item()
max_prob = probs[0, max_idx].item()

print(f"Category: {categories[max_idx]} ({max_prob:.2%})")

# Process multiple images
images = [preprocess(Image.open(f"img{i}.jpg")) for i in range(10)]
images = torch.stack(images).to(device)

with torch.no_grad():
    image_features = model.encode_image(images)
    image_features /= image_features.norm(dim=-1, keepdim=True)

# Batch text
texts = ["a dog", "a cat", "a bird"]
text_tokens = clip.tokenize(texts).to(device)

with torch.no_grad():
    text_features = model.encode_text(text_tokens)
    text_features /= text_features.norm(dim=-1, keepdim=True)

# Similarity matrix (10 images × 3 texts)
similarities = image_features @ text_features.T
print(similarities.shape)  # (10, 3)

# Store CLIP embeddings in Chroma/FAISS
import chromadb

client = chromadb.Client()
collection = client.create_collection("image_embeddings")

# Add image embeddings
for img_path, embedding in zip(image_paths, image_embeddings):
    collection.add(
        embeddings=[embedding.cpu().numpy().tolist()],
        metadatas=[{"path": img_path}],
        ids=[img_path]
    )

# Query with text
query = "a sunset"
text_embedding = model.encode_text(clip.tokenize([query]))
results = collection.query(
    query_embeddings=[text_embedding.cpu().numpy().tolist()],
    n_results=5
)