import ruclip

device = 'cuda'
clip, processor = ruclip.load('ruclip-vit-base-patch32-384', device=device)

import torch
import base64
import requests
import matplotlib.pyplot as plt
from PIL import Image
from io import BytesIO

# prepare images
bs4_urls = requests.get('https://raw.githubusercontent.com/sberbank-ai/ru-dolph/master/pics/pipelines/cats_vs_dogs_bs4.json').json()
images = [Image.open(BytesIO(base64.b64decode(bs4_url))) for bs4_url in bs4_urls]

# prepare classes
classes = ['кошка', 'собака']
templates = ['{}', 'это {}', 'на картинке {}', 'это {}, домашнее животное']

# predict
predictor = ruclip.Predictor(clip, processor, device, bs=8, templates=templates)
with torch.no_grad():
    text_latents = predictor.get_text_latents(classes)
    pred_labels = predictor.run(images, text_latents)

# show results
f, ax = plt.subplots(2,4, figsize=(12,6))
for i, (pil_img, pred_label) in enumerate(zip(images, pred_labels)):
    ax[i//4, i%4].imshow(pil_img)
    ax[i//4, i%4].set_title(classes[pred_label])

train = CIFAR100(root, download=True, train=True)
test = CIFAR100(root, download=True, train=False)

with torch.no_grad():
    X_train = predictor.get_image_latents((pil_img for pil_img, _ in train)).cpu().numpy()
    X_test = predictor.get_image_latents((pil_img for pil_img, _ in test)).cpu().numpy()
    y_train, y_test = np.array(train.targets), np.array(test.targets)

clf = LogisticRegression(solver='lbfgs', penalty='l2', max_iter=1000, verbose=1)
clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)
accuracy = np.mean((y_test == y_pred).astype(np.float)) * 100.
print(f"Accuracy = {accuracy:.3f}")