add usage

README.md

@@ -1,3 +1,59 @@
 ---
 license: mit
 ---
+
+# recruit-jp/japanese-clip-vit-b-32-roberta-base
+
+## 使い方
+
+```python
+import io
+import requests
+from PIL import Image
+
+import torch
+import torchvision
+from transformers import AutoTokenizer, AutoModel
+
+model_name = "recruit-jp/japanese-clip-vit-b-32-roberta-base"
+device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModel.from_pretrained(model_name, trust_remote_code=True).to(device)
+
+def _convert_to_rgb(image):
+    return image.convert('RGB')
+
+
+preprocess = torchvision.transforms.Compose([
+    torchvision.transforms.Resize(size=224, interpolation=torchvision.transforms.InterpolationMode.BICUBIC, max_size=None),
+    torchvision.transforms.CenterCrop(size=(224, 224)),
+    _convert_to_rgb,
+    torchvision.transforms.ToTensor(),
+    torchvision.transforms.Normalize(mean=[0.48145466, 0.4578275, 0.40821073], std=[0.26862954, 0.26130258, 0.27577711])
+])
+
+
+def tokenize(tokenizer, texts):
+    texts = ["[CLS]" + text for text in texts]
+    encodings = [
+        tokenizer(text, max_length=77, padding="max_length", truncation=True, add_special_tokens=False)["input_ids"]
+        for text in texts
+    ]
+    return torch.LongTensor(encodings)
+
+# Run!
+image = Image.open(io.BytesIO(requests.get('https://images.pexels.com/photos/2253275/pexels-photo-2253275.jpeg?auto=compress&cs=tinysrgb&dpr=3&h=750&w=1260').content))
+image = preprocess(image).unsqueeze(0).to(device)
+text = tokenize(tokenizer, texts=["犬", "猫", "象"]).to(device)
+
+with torch.inference_mode():
+    image_features = model.get_image_features(image)
+    image_features /= image_features.norm(dim=-1, keepdim=True)
+
+    text_features = model.get_text_features(input_ids=text)
+    text_features /= text_features.norm(dim=-1, keepdim=True)
+
+    probs = image_features @ text_features.T
+
+print("Label probs:", probs.cpu().numpy()[0])
+```