Develop: get fight recognition model from model dir (#6324)

* Update action.md

delete the step of change model name of fight recognition

* Update video_action_infer.py

get model path from model_dir without model name

* optimize action vis

deploy/pipeline/docs/tutorials/action.md

@@ -184,9 +184,8 @@ VIDEO_ACTION:  # 基于视频分类的行为识别模型配置
 
 ### 使用方法
 1. 从上表链接中下载预测部署模型并解压到`./output_inference`路径下；
-2. 修改解压后`ppTSM`文件夹中的文件名称为`model.pdiparams、model.pdiparams.info和model.pdmodel`；
-3. 修改配置文件`deploy/pipeline/config/infer_cfg_pphuman.yml`中`VIDEO_ACTION`下的`enable`为`True`；
-4. 输入视频，启动命令如下：
+2. 修改配置文件`deploy/pphuman/config/infer_cfg_pphuman.yml`中`VIDEO_ACTION`下的`enable`为`True`；
+3. 输入视频，启动命令如下：
 ```
 python deploy/pipeline/pipeline.py --config deploy/pipeline/config/infer_cfg_pphuman.yml \
                                                    --video_file=test_video.mp4 \

deploy/pipeline/pipeline.py

@@ -919,9 +919,12 @@ class PipePredictor(object):
             video_action_score = None
             if video_action_res and video_action_res["class"] == 1:
                 video_action_score = video_action_res["score"]
+            mot_boxes = None
+            if mot_res:
+                mot_boxes = mot_res['boxes']
             image = visualize_action(
                 image,
-                mot_res['boxes'],
+                mot_boxes,
                 action_visual_collector=None,
                 action_text="SkeletonAction",
                 video_action_score=video_action_score,

deploy/pipeline/pphuman/video_action_infer.py

@@ -96,8 +96,8 @@ class VideoActionRecognizer(object):
 
         self.recognize_times = Timer()
 
-        model_file_path = os.path.join(model_dir, "ppTSM.pdmodel")
-        params_file_path = os.path.join(model_dir, "ppTSM.pdiparams")
+        model_file_path = glob.glob(os.path.join(model_dir, "*.pdmodel"))[0]
+        params_file_path = glob.glob(os.path.join(model_dir, "*.pdiparams"))[0]
         self.config = Config(model_file_path, params_file_path)
 
         if device == "GPU" or device == "gpu":