init comit

app.py

@@ -0,0 +1,86 @@
+import gradio as gr
+from transformers import pipeline, CLIPProcessor, CLIPModel
+from PIL import Image
+import torch
+import openai
+import base64
+import io
+
+# ── 1. DEIN MODELL (von Hugging Face) ──────────────────────────
+MY_MODEL_ID = "DEIN-USERNAME/DEIN-MODELL"  # ← anpassen!
+my_classifier = pipeline("image-classification", model=MY_MODEL_ID)
+
+# ── 2. CLIP (Open-Source) ──────────────────────────────────────
+clip_model = CLIPModel.from_pretrained("openai/clip-vit-base-patch32")
+clip_processor = CLIPProcessor.from_pretrained("openai/clip-vit-base-patch32")
+
+# Deine Klassen (anpassen!)
+LABELS = ["cat", "dog", "bird"]  # ← deine eigenen Klassen
+
+def predict_my_model(image):
+    results = my_classifier(image)
+    return {r["label"]: r["score"] for r in results}
+
+def predict_clip(image):
+    inputs = clip_processor(
+        text=LABELS, images=image, return_tensors="pt", padding=True
+    )
+    with torch.no_grad():
+        outputs = clip_model(**inputs)
+    probs = outputs.logits_per_image.softmax(dim=1)[0]
+    return {label: float(prob) for label, prob in zip(LABELS, probs)}
+
+def predict_openai(image):
+    client = openai.OpenAI(api_key=openai.api_key)
+    
+    # Bild zu Base64 konvertieren
+    buf = io.BytesIO()
+    image.save(buf, format="JPEG")
+    b64 = base64.b64encode(buf.getvalue()).decode()
+    
+    response = client.chat.completions.create(
+        model="gpt-4o",
+        messages=[{
+            "role": "user",
+            "content": [
+                {"type": "image_url",
+                 "image_url": {"url": f"data:image/jpeg;base64,{b64}"}},
+                {"type": "text",
+                 "text": f"Classify this image as one of: {LABELS}. "
+                         f"Return only a JSON like: {{\"label\": score, ...}} "
+                         f"where scores sum to 1."}
+            ]
+        }],
+        max_tokens=100
+    )
+    import json
+    return json.loads(response.choices[0].message.content)
+
+def classify_all(image):
+    r1 = predict_my_model(image)
+    r2 = predict_clip(image)
+    r3 = predict_openai(image)
+    return r1, r2, r3
+
+# ── Beispielbilder ─────────────────────────────────────────────
+examples = ["example1.jpg", "example2.jpg"]  # ← eigene Bilder
+
+# ── Gradio Interface ───────────────────────────────────────────
+with gr.Blocks(title="Image Classification Comparison") as demo:
+    gr.Markdown("# 🖼️ Image Classification – Model Comparison")
+    gr.Markdown("Compare your custom model, CLIP, and GPT-4o Vision.")
+    
+    with gr.Row():
+        img_input = gr.Image(type="pil", label="Upload Image")
+    
+    btn = gr.Button("Classify!", variant="primary")
+    
+    with gr.Row():
+        out1 = gr.Label(label="🏷️ My Model")
+        out2 = gr.Label(label="🔍 CLIP")
+        out3 = gr.Label(label="🤖 GPT-4o")
+    
+    btn.click(classify_all, inputs=img_input, outputs=[out1, out2, out3])
+    gr.Examples(examples=examples, inputs=img_input)
+
+demo.launch()

requrements.txt

@@ -0,0 +1,5 @@
+gradio
+transformers
+torch
+openai
+pillow