Upload 2 files

app.py

@@ -0,0 +1,49 @@
+import gradio as gr
+from transformers import pipeline, AutoImageProcessor, AutoModelForImageClassification
+
+# Image Processor explizit laden!
+processor = AutoImageProcessor.from_pretrained("google/vit-base-patch16-224")
+model = AutoModelForImageClassification.from_pretrained("Granitagushi/vit-base-fruits-360")
+
+vit_classifier = pipeline(
+    "image-classification",
+    model=model,
+    image_processor=processor,
+    device=0  # oder -1 für CPU
+)
+
+clip_detector = pipeline(
+    model="openai/clip-vit-large-patch14",
+    task="zero-shot-image-classification"
+)
+
+labels_fruits = [
+    'Orange', 'Strawberry Wedge', 'Banana', 'Cherry', 'Apple Red'
+]
+
+def classify_fruit(image):
+    vit_results = vit_classifier(image)
+    vit_output = {result['label']: result['score'] for result in vit_results}
+    clip_results = clip_detector(image, candidate_labels=labels_fruits)
+    clip_output = {result['label']: result['score'] for result in clip_results}
+    return {"ViT Classification": vit_output, "CLIP Zero-Shot Classification": clip_output}
+
+example_images = [
+    ["example_images/Apple.jpg"],
+    ["example_images/Banana.jpg"],
+    ["example_images/Cherry.jpg"],
+    ["example_images/orange.jpg"],
+    ["example_images/strawberry.jpg"]
+]
+
+iface = gr.Interface(
+    fn=classify_fruit,
+    inputs=gr.Image(type="filepath"),
+    outputs=gr.JSON(),
+    title="Fruit Classification Comparison",
+    description="Upload an image of a fruit, and compare results from a trained ViT model and a zero-shot CLIP model.",
+    examples=example_images
+)
+
+if __name__ == "__main__":
+    iface.launch()

requirements.txt

@@ -0,0 +1,7 @@
+transformers
+datasets
+torch
+gradio
+Pillow
+tqdm
+scikit-learn