add app.py

app.py

@@ -0,0 +1,44 @@
+
+from transformers import ViTFeatureExtractor, ViTForImageClassification
+
+import torch
+import gradio as gr
+
+from PIL import Image
+
+feature_extractor = ViTFeatureExtractor.from_pretrained('google/vit-base-patch16-224')
+model = ViTForImageClassification.from_pretrained('google/vit-base-patch16-224')
+
+def classify_image(image):
+
+    with torch.no_grad():
+        model.eval()
+
+        inputs = feature_extractor(images=image, return_tensors="pt")
+        outputs = model(**inputs)
+    
+    logits = outputs.logits
+    prob = torch.nn.functional.softmax(logits, dim=1)
+
+    top10_prob, top10_indices = torch.topk(prob, 10)
+    top10_confidences = {}
+    for i in range(10):
+        top10_confidences[model.config.id2label[int(top10_indices[0][i])]] = float(top10_prob[0][i])
+
+    return top10_confidences #confidences
+
+
+with gr.Blocks(title="ViT ImageNet Classification - ClassCat",
+            css=".gradio-container {background:mintcream;}"
+        ) as demo:
+    gr.HTML("""<div style="font-family:'Times New Roman', 'Serif'; font-size:16pt; font-weight:bold; text-align:center; color:royalblue;">ViT - ImageNet Classification</div>""")
+
+    with gr.Row(): 
+        input_image = gr.Image(type="pil", image_mode="RGB", shape=(224, 224))
+        output_label=gr.Label(label="Probabilities", num_top_classes=3)
+
+    send_btn = gr.Button("Infer")
+    send_btn.click(fn=classify_image, inputs=input_image, outputs=output_label)
+
+#demo.queue(concurrency_count=3)
+demo.launch(debug=True)