OpenCLIP: Open source CLIP implementation

import torch
import open_clip
from PIL import Image
import numpy as np

class CLIPClassifier:
    def __init__(self, model_configs):
        self.models = []
        for config in model_configs:
            model, _, preprocess = open_clip.create_model_and_transforms(
                config['arch'], pretrained=config['pretrained']
            )
            model.eval()
            tokenizer = open_clip.get_tokenizer(config['arch'])
            self.models.append({
                'model': model, 'preprocess': preprocess, 
                'tokenizer': tokenizer, 'name': config['name']
            })
    
    def classify_image(self, image_path, labels):
        results = {}
        image = Image.open(image_path)
        
        for model_info in self.models:
            processed_image = model_info['preprocess'](image).unsqueeze(0)
            text_tokens = model_info['tokenizer'](labels)
            
            with torch.no_grad():
                image_features = model_info['model'].encode_image(processed_image)
                text_features = model_info['model'].encode_text(text_tokens)
                
                image_features /= image_features.norm(dim=-1, keepdim=True)
                text_features /= text_features.norm(dim=-1, keepdim=True)
                
                probs = (100.0 * image_features @ text_features.T).softmax(dim=-1)
                results[model_info['name']] = dict(zip(labels, probs[0].tolist()))
        
        return results