中文和英文同时匹配图片时中文得分非常低

[HiddenMarkovModel]

当对一张图片与中文和英文的文本分别相似度计算时, 中文文本的得分远小于英文的得分.

import torch
from PIL import Image
import requests
import cn_clip.clip as clip
from cn_clip.clip import load_from_name, available_models


print("Available models:", available_models())
# Available models: ['ViT-B-16', 'ViT-L-14', 'ViT-L-14-336', 'ViT-H-14', 'RN50']

device = "cuda" if torch.cuda.is_available() else "cpu"
model, preprocess = load_from_name("ViT-L-14-336", device=device, download_root='checkpoint')

model.eval()

img_path = "examples/dog.jpg"
text_list = ["猫", "狗", "dog"]

image = preprocess(Image.open(str(img_path))).unsqueeze(0).to(device)
text = clip.tokenize(text_list).to(device)

with torch.no_grad():
  image_features = model.encode_image(image)
  text_features = model.encode_text(text)

  image_features /= image_features.norm(dim=-1, keepdim=True)
  text_features /= text_features.norm(dim=-1, keepdim=True)

  logits_per_image, logits_per_text = model.get_similarity(image, text)
  probs = logits_per_image.softmax(dim=-1).cpu().numpy()


for i, prompt in enumerate(text_list):
  print(f"{prompt}: {probs[0][i]}")

结果为: 猫: 4.565715789794922e-05 狗: 0.010009765625 dog: 0.98974609375

这种问题怎么解决?