Update app.py

app.py

@@ -11,18 +11,27 @@ pipes = {
     "chinese-clip-vit-large-patch14-336px": pipeline("zero-shot-image-classification", model="OFA-Sys/chinese-clip-vit-large-patch14-336px"),
     "chinese-clip-vit-huge-patch14": pipeline("zero-shot-image-classification", model="OFA-Sys/chinese-clip-vit-huge-patch14"),
 }
+inputs = [
+    gr.inputs.Image(type='pil'),
+    "text",
+    gr.inputs.Radio(choices=[
+                                "chinese-clip-vit-base-patch16",
+                                "chinese-clip-vit-large-patch14", 
+                                "chinese-clip-vit-large-patch14-336px", 
+                                "chinese-clip-vit-huge-patch14",
+                            ], type="value", default="chinese-clip-vit-base-patch16", label="Model"), 
+]
 images="festival.jpg"
 
-def shot(image, labels_text):
-    PIL_image = Image.fromarray(np.uint8(image)).convert('RGB')
-    labels = labels_text.split(",")
-    res = pipes['chinese-clip-vit-base-patch16'](images=PIL_image, 
+def shot(image, labels_text, model_name):
+    labels = labels_text.split(",").strip(" ")
+    res = pipes[model_name](images=image, 
            candidate_labels=labels,
            hypothesis_template= "一张{}的图片。")
     return {dic["label"]: dic["score"] for dic in res}
-    
+
 iface = gr.Interface(shot, 
-                    ["image", "text"], 
+                    inputs, 
                     "label", 
                     examples=[["festival.jpg", "灯笼, 鞭炮, 对联"], 
                               ["cat-dog-music.png", "音乐表演, 体育运动"],