Update app.py

app.py

@@ -43,11 +43,38 @@ def get_image(url) -> PIL.Image:
     response = requests.get(url)
     image = PIL.Image.open(BytesIO(response.content))
     return image
+
+
             
 
 model = load_model()
 labels = load_labels()
 
+def predictx(url: str, score_threshold: float) -> tuple[dict[str, float], dict[str, float], str]:
+    _, height, width, _ = model.input_shape
+    response = requests.get(url)
+    image = PIL.Image.open(BytesIO(response.content))
+    
+    image = np.asarray(image)
+    image = tf.image.resize(image, size=(height, width), method=tf.image.ResizeMethod.AREA, preserve_aspect_ratio=True)
+    image = image.numpy()
+    image = dd.image.transform_and_pad_image(image, width, height)
+    image = image / 255.0
+    probs = model.predict(image[None, ...])[0]
+    probs = probs.astype(float)
+
+    indices = np.argsort(probs)[::-1]
+    result_all = dict()
+    result_threshold = dict()
+    for index in indices:
+        label = labels[index]
+        prob = probs[index]
+        result_all[label] = prob
+        if prob < score_threshold:
+            break
+        result_threshold[label] = prob
+    result_text = ", ".join(result_all.keys())
+    return result_threshold, result_all, result_text
 
 def predict(image: PIL.Image.Image, score_threshold: float) -> tuple[dict[str, float], dict[str, float], str]:
     _, height, width, _ = model.input_shape
@@ -104,7 +131,7 @@ with gr.Blocks(css="style.css") as demo:
         fn=predict,
         inputs=[url, score_threshold],
         outputs=[result, result_json, result_text],
-        api_name="predict",
+        api_name="predictx",
     )
 
 if __name__ == "__main__":