多模态对比语言图像预训练CLIP：打破语言与视觉的界限

ftfy
regex
tqdm
torch
torchvision

$ conda install --yes -c pytorch pytorch=1.7.1 torchvision cudatoolkit=11.0
$ pip install ftfy regex tqdm
$ pip install git+https://github.com/openai/CLIP.git

import torch
import clip
from PIL import Image

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

image = preprocess(Image.open("CLIP.png")).unsqueeze(0).to(device)
text = clip.tokenize(["a diagram", "a dog", "a cat"]).to(device)

with torch.no_grad():
    image_features = model.encode_image(image)
    text_features = model.encode_text(text)
    
    logits_per_image, logits_per_text = model(image, text)
    probs = logits_per_image.softmax(dim=-1).cpu().numpy()

print("Label probs:", probs)  # prints: [[0.9927937  0.00421068 0.00299572]]

import os
import clip
import torch
from torchvision.datasets import CIFAR100

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

#Download the dataset
cifar100 = CIFAR100(root=os.path.expanduser("~/.cache"), download=True, train=False)

#Prepare the inputs
image, class_id = cifar100[3637]
image_input = preprocess(image).unsqueeze(0).to(device)
text_inputs = torch.cat([clip.tokenize(f"a photo of a {c}") for c in cifar100.classes]).to(device)

#Calculate features
with torch.no_grad():
    image_features = model.encode_image(image_input)
    text_features = model.encode_text(text_inputs)

#Pick the top 5 most similar labels for the image
image_features /= image_features.norm(dim=-1, keepdim=True)
text_features /= text_features.norm(dim=-1, keepdim=True)
similarity = (100.0 * image_features @ text_features.T).softmax(dim=-1)
values, indices = similarity[0].topk(5)

#Print the result
print("\nTop predictions:\n")
for value, index in zip(values, indices):
    print(f"{cifar100.classes[index]:>16s}: {100 * value.item():.2f}%")

Top predictions:

           snake: 65.31%
          turtle: 12.29%
    sweet_pepper: 3.83%
          lizard: 1.88%
       crocodile: 1.75%

import os
import clip
import torch

import numpy as np
from sklearn.linear_model import LogisticRegression
from torch.utils.data import DataLoader
from torchvision.datasets import CIFAR100
from tqdm import tqdm

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

#Load the dataset
root = os.path.expanduser("~/.cache")
train = CIFAR100(root, download=True, train=True, transform=preprocess)
test = CIFAR100(root, download=True, train=False, transform=preprocess)


def get_features(dataset):
    all_features = []
    all_labels = []
    
    with torch.no_grad():
        for images, labels in tqdm(DataLoader(dataset, batch_size=100)):
            features = model.encode_image(images.to(device))

            all_features.append(features)
            all_labels.append(labels)

    return torch.cat(all_features).cpu().numpy(), torch.cat(all_labels).cpu().numpy()

#Calculate the image features
train_features, train_labels = get_features(train)
test_features, test_labels = get_features(test)

#Perform logistic regression
classifier = LogisticRegression(random_state=0, C=0.316, max_iter=1000, verbose=1)
classifier.fit(train_features, train_labels)

#Evaluate using the logistic regression classifier
predictions = classifier.predict(test_features)
accuracy = np.mean((test_labels == predictions).astype(float)) * 100.
print(f"Accuracy = {accuracy:.3f}")