Update app.py

app.py

@@ -35,10 +35,12 @@ def shot(image, labels_text, model_name, hypothesis_template):
            hypothesis_template=hypothesis_template)
     return {dic["label"]: dic["score"] for dic in res}
 
+lei = "机动车道,非机动车道,人车混行道路,斑马线人行道,主干道路,乡间道路,内部小巷,人行横道,十字路口,丁字路口,岔路口,铁路沿线,铁路路口,高架桥,立交桥,过街天桥,桥梁,天桥上下口,地下隧道,地下人行通道,隧道通行区域,穿山隧道,隧道出入口,水池,河流,湖面,室外停车场,路面划线停车位,城市广场,裸露农田,林区,草坪,树木,公交站台,收费站,检查站,加油站,岗亭,车行道闸,人行闸机,安检机器,铁门,保安亭,门或电动门,人员出入口,车辆出入口,广告牌,横幅,沿街商铺,露天烧烤摊,超市,建筑施工,道路施工,人员卡口,车辆卡口,人行闸机,场所主出入口,安检门,X光安检机,电梯内部,扶梯,楼梯,台阶,室内通道,走廊,前台区域,公共大厅,室内停车场"
+
 iface = gr.Interface(shot, 
             inputs, 
             "label", 
-            examples=[["festival.jpg", "灯笼, 鞭炮, 对联", "ViT/B-16", "一张{}的图片。"], 
+            examples=[["festival.jpg", lei, "ViT/B-16", "一张{}的图片。"], 
                       ["cat-dog-music.png", "音乐表演, 体育运动", "ViT/B-16", "一张{}的图片。"],
                       ["football-match.jpg", "梅西, C罗, 马奎尔", "ViT/B-16", "一张{}的图片。"]],
             description="""<p>Chinese CLIP is a contrastive-learning-based vision-language foundation model pretrained on large-scale Chinese data. For more information, please refer to the paper and official github. Also, Chinese CLIP has already been merged into Huggingface Transformers! <br><br>