Add application file

app.py

@@ -0,0 +1,50 @@
+import gradio as gr
+import json
+from transformers import pipeline
+
+
+def load_label_to_name_mapping(json_file_path):
+    """Load the label-to-name mapping from a JSON file."""
+    with open(json_file_path, 'r') as f:
+        mapping = json.load(f)
+    return {int(k): v for k, v in mapping.items()}
+
+def infer_flower_name(classifier, image):
+    """Perform inference on an image and return the flower name."""
+    # Perform inference
+    # Load the model checkpoint for inference
+    
+    result = classifier(image)
+    # Get the label from the inference result
+    label = result[0]['label'].split('_')[-1]  # The label is usually in the format 'LABEL_#'
+    label = int(label)
+    
+    # Map the integer label to the flower name
+    json_file_path = 'label_to_name.json'
+    label_to_name = load_label_to_name_mapping(json_file_path)
+    flower_name = label_to_name.get(label, "Unknown")
+    
+    return flower_name
+
+def predict(flower):# would call a model to make a prediction on an input and return the output.
+    classifier = pipeline("image-classification", model="checkpoint-160")
+    flower_name = infer_flower_name(classifier, flower)
+    return flower_name
+
+#def predict2(flower2): # output top 3 with prob?
+#    classifier = pipeline("image-classification", model="checkpoint-160")
+#    result = classifier(flower2)
+#    print(result)
+#    return result
+
+description = "Upload an image of a flower and discover its species!"
+title = "Bloom Classifier"
+examples = ["example.jpg", "image_00293.jpg","image_02828.jpg"]
+demo = gr.Interface(fn=predict, 
+                    inputs=gr.Image(type="pil"), 
+                    outputs=gr.Label(num_top_classes=3),
+                    description=description,
+                    title = title,
+                    examples=examples)
+
+demo.launch()