Upload 2 files

app.py

@@ -0,0 +1,42 @@
+import gradio as gr
+import torch
+import clip
+from PIL import Image
+
+device = "cuda" if torch.cuda.is_available() else "cpu"
+
+def calculate_similarity(image, text, model_name):
+
+    model, preprocess = load_model(model_name)
+    # 画像の前処理
+    image = preprocess(image).unsqueeze(0).to(device)
+    
+    # テキストの前処理
+    text = clip.tokenize([text]).to(device)
+    
+    # 類似度の計算
+    with torch.no_grad():
+        image_features = model.encode_image(image)
+        text_features = model.encode_text(text)
+        
+        similarity = torch.cosine_similarity(image_features, text_features).cpu().numpy()[0]
+        
+    return similarity
+
+def load_model(model_name):
+    model, preprocess = clip.load(model_name, device=device)
+    return model, preprocess
+
+iface = gr.Interface(
+    fn=calculate_similarity,
+    inputs=[
+        gr.Image(type="pil"), 
+        gr.Textbox(lines=2, placeholder="A photo of a ..."),
+        gr.Radio(["ViT-B/32", "ViT-B/16", "ViT-L/14", "ViT-L/14@336px"], label="モデル選択")
+    ],
+    outputs="number",
+    title="CLIPによる画像とテキストの類似度計算",
+    description="類似度を計算したい画像とテキストを入力し，使用するCLIPモデルを選択してください．"
+)
+
+iface.launch()

requirements.txt

@@ -0,0 +1,68 @@
+aiofiles==23.2.1
+annotated-types==0.7.0
+anyio==4.8.0
+certifi==2025.1.31
+charset-normalizer==3.4.1
+click==8.1.8
+clip @ git+https://github.com/openai/CLIP.git@dcba3cb2e2827b402d2701e7e1c7d9fed8a20ef1
+contourpy==1.3.0
+cycler==0.12.1
+exceptiongroup==1.2.2
+fastapi==0.115.8
+ffmpy==0.5.0
+filelock==3.17.0
+fonttools==4.56.0
+fsspec==2025.2.0
+ftfy==6.3.1
+gradio==4.44.1
+gradio_client==1.3.0
+h11==0.14.0
+httpcore==1.0.7
+httpx==0.28.1
+huggingface-hub==0.28.1
+idna==3.10
+importlib_resources==6.5.2
+Jinja2==3.1.5
+kiwisolver==1.4.7
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
+matplotlib==3.9.4
+mdurl==0.1.2
+mpmath==1.3.0
+networkx==3.2.1
+numpy==2.0.2
+orjson==3.10.15
+packaging==24.2
+pandas==2.2.3
+pillow==10.4.0
+pydantic==2.10.6
+pydantic_core==2.27.2
+pydub==0.25.1
+Pygments==2.19.1
+pyparsing==3.2.1
+python-dateutil==2.9.0.post0
+python-multipart==0.0.20
+pytz==2025.1
+PyYAML==6.0.2
+regex==2024.11.6
+requests==2.32.3
+rich==13.9.4
+ruff==0.9.5
+semantic-version==2.10.0
+shellingham==1.5.4
+six==1.17.0
+sniffio==1.3.1
+starlette==0.45.3
+sympy==1.13.1
+tomlkit==0.12.0
+torch==2.6.0
+torchvision==0.21.0
+tqdm==4.67.1
+typer==0.15.1
+typing_extensions==4.12.2
+tzdata==2025.1
+urllib3~=2.0
+uvicorn==0.34.0
+wcwidth==0.2.13
+websockets==12.0
+zipp==3.21.0