【Paddle-CLIP】使用 CLIP 模型进行图像识别

!pip install paddleclip

import paddlefrom PIL import Imagefrom clip import tokenize, load_model

model, transforms = load_model('ViT_B_32', pretrained=True)

# 设置图片路径和标签img_path = "apple.jpeg"labels = ['apple', 'fruit', 'pear', 'peach']# 准备输入数据img = Image.open(img_path)
display(img)
image = transforms(Image.open(img_path)).unsqueeze(0)
text = tokenize(labels)# 计算特征with paddle.no_grad():
    logits_per_image, logits_per_text = model(image, text)
    probs = paddle.nn.functional.softmax(logits_per_image, axis=-1)# 打印结果for label, prob in zip(labels, probs.squeeze()):    print('该图片为 %s 的概率是：%.02f%%' % (label, prob*100.))

# 设置图片路径和标签img_path = "fruit.jpg"labels = ['apple', 'fruit', 'pear', 'peach']# 准备输入数据img = Image.open(img_path)
display(img)
image = transforms(Image.open(img_path)).unsqueeze(0)
text = tokenize(labels)# 计算特征with paddle.no_grad():
    logits_per_image, logits_per_text = model(image, text)
    probs = paddle.nn.functional.softmax(logits_per_image, axis=-1)# 打印结果for label, prob in zip(labels, probs.squeeze()):    print('该图片为 %s 的概率是：%.02f%%' % (label, prob*100.))

import paddlefrom clip import tokenize, load_modelfrom paddle.vision.datasets import Cifar100# 加载模型model, transforms = load_model('ViT_B_32', pretrained=True)# 加载 Cifar100 数据集cifar100 = Cifar100(mode='test', backend='pil')
classes = [    'apple', 'aquarium_fish', 'baby', 'bear', 'beaver', 'bed', 'bee', 'beetle', 'bicycle', 'bottle', 
    'bowl', 'boy', 'bridge', 'bus', 'butterfly', 'camel', 'can', 'castle', 'caterpillar', 'cattle', 
    'chair', 'chimpanzee', 'clock', 'cloud', 'cockroach', 'couch', 'crab', 'crocodile', 'cup', 'dinosaur', 
    'dolphin', 'elephant', 'flatfish', 'forest', 'fox', 'girl', 'hamster', 'house', 'kangaroo', 'keyboard', 
    'lamp', 'lawn_mower', 'leopard', 'lion', 'lizard', 'lobster', 'man', 'maple_tree', 'motorcycle', 'mountain', 
    'mouse', 'mushroom', 'oak_tree', 'orange', 'orchid', 'otter', 'palm_tree', 'pear', 'pickup_truck', 'pine_tree', 
    'plain', 'plate', 'poppy', 'porcupine', 'possum', 'rabbit', 'raccoon', 'ray', 'road', 'rocket', 
    'rose', 'sea', 'seal', 'shark', 'shrew', 'skunk', 'skyscraper', 'snail', 'snake', 'spider', 
    'squirrel', 'streetcar', 'sunflower', 'sweet_pepper', 'table', 'tank', 'telephone', 'television', 'tiger', 'tractor', 
    'train', 'trout', 'tulip', 'turtle', 'wardrobe', 'whale', 'willow_tree', 'wolf', 'woman', 'worm']# 准备输入数据image, class_id = cifar100[3637]
display(image)
image_input = transforms(image).unsqueeze(0)
text_inputs = tokenize(["a photo of a %s" % c for c in classes])# 计算特征with paddle.no_grad():
    image_features = model.encode_image(image_input)
    text_features = model.encode_text(text_inputs)# 筛选 Top_5image_features /= image_features.norm(axis=-1, keepdim=True)
text_features /= text_features.norm(axis=-1, keepdim=True)
similarity = (100.0 * image_features @ text_features.t())
similarity = paddle.nn.functional.softmax(similarity, axis=-1)
values, indices = similarity[0].topk(5)# 打印结果for value, index in zip(values, indices):    print('该图片为 %s 的概率是：%.02f%%' % (classes[index], value*100.))

import osimport paddleimport numpy as npfrom tqdm import tqdmfrom paddle.io import DataLoaderfrom clip import tokenize, load_modelfrom paddle.vision.datasets import Cifar100from sklearn.linear_model import LogisticRegression# 加载模型model, transforms = load_model('ViT_B_32', pretrained=True)# 加载数据集train = Cifar100(mode='train', transform=transforms, backend='pil')
test = Cifar100(mode='test', transform=transforms, backend='pil')# 获取特征def get_features(dataset):
    all_features = []
    all_labels = []    
    with paddle.no_grad():        for images, labels in tqdm(DataLoader(dataset, batch_size=100)):
            features = model.encode_image(images)
            all_features.append(features)
            all_labels.append(labels)    return paddle.concat(all_features).numpy(), paddle.concat(all_labels).numpy()# 计算并获取特征train_features, train_labels = get_features(train)
test_features, test_labels = get_features(test)# 逻辑回归classifier = LogisticRegression(random_state=0, C=0.316, max_iter=1000, verbose=1, n_jobs=-1)
classifier.fit(train_features, train_labels)# 模型评估predictions = classifier.predict(test_features)
accuracy = np.mean((test_labels == predictions).astype(np.float)) * 100.# 打印结果print(f"Accuracy = {accuracy:.3f}")