vqg_pred.py

from PIL import Image
import requests
import torch
from torchvision import transforms
from torchvision.transforms.functional import InterpolationMode
from lzma import FILTER_LZMA1

try:
    from _lzma import *
    from _lzma import _encode_filter_properties, _decode_filter_properties
except ImportError:
    from backports.lzma import *
    from backports.lzma import _encode_filter_properties, _decode_filter_properties

device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')


def load_demo_image(image_size, device):
    img_url = 'https://storage.googleapis.com/sfr-vision-language-research/BLIP/demo.jpg'
    raw_image = Image.open(requests.get(img_url, stream=True).raw).convert('RGB')

    w, h = raw_image.size
    print(raw_image.resize((w // 5, h // 5)))

    transform = transforms.Compose([
        transforms.Resize((image_size, image_size), interpolation=InterpolationMode.BICUBIC),
        transforms.ToTensor(),
        transforms.Normalize((0.48145466, 0.4578275, 0.40821073), (0.26862954, 0.26130258, 0.27577711))
    ])
    image = transform(raw_image).unsqueeze(0).to(device)
    return image