first test of files

app.py

@@ -0,0 +1,34 @@
+import gradio as gr
+from transformers import AutoImageProcessor, ConvNextForImageClassification
+from PIL import Image
+import torch
+
+# Load model and processor from your model repo on the Hub
+model = ConvNextForImageClassification.from_pretrained("todorristov/car_classification_model")
+processor = AutoImageProcessor.from_pretrained("todorristov/car_classification_model")
+
+# Define inference function
+def classify_car(image):
+    inputs = processor(images=image, return_tensors="pt")
+    with torch.no_grad():
+        outputs = model(**inputs)
+        probs = torch.nn.functional.softmax(outputs.logits, dim=1)
+        predicted_class_idx = probs.argmax().item()
+        label = model.config.id2label[str(predicted_class_idx)]
+        confidence = probs[0][predicted_class_idx].item()
+    return f"{label} ({confidence:.2%})"
+
+# Gradio UI
+title = "Car Classification (Brand, Model & Year)"
+description = "Upload a car image to identify its brand, model, and year of production."
+
+demo = gr.Interface(
+    fn=classify_car,
+    inputs=gr.Image(type="pil", label="Upload Car Image"),
+    outputs=gr.Text(label="Prediction"),
+    title=title,
+    description=description
+)
+
+if __name__ == "__main__":
+    demo.launch()

requirements.txt

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