Upload 2 files

app.py

@@ -0,0 +1,29 @@
+import gradio as gr
+from transformers import ViTImageProcessor, ViTForImageClassification
+from PIL import Image
+import torch
+
+# Load model and processor
+model_name = "google/vit-base-patch16-224"
+model = ViTForImageClassification.from_pretrained(model_name)
+processor = ViTImageProcessor.from_pretrained(model_name)
+
+def classify_image(image):
+    inputs = processor(images=image, return_tensors="pt")
+    with torch.no_grad():
+        outputs = model(**inputs)
+    logits = outputs.logits
+    predicted_class_idx = logits.argmax(-1).item()
+    predicted_label = model.config.id2label[predicted_class_idx]
+    return predicted_label
+
+demo = gr.Interface(
+    fn=classify_image,
+    inputs=gr.Image(type="pil"),
+    outputs="text",
+    title="ViT Image Classifier",
+    description="Upload an image to classify it using Vision Transformer (ViT)."
+)
+
+if __name__ == "__main__":
+    demo.launch()

requirements.txt

@@ -0,0 +1,5 @@
+transformers
+gradio
+torch
+Pillow
+datasets