How to access tensor_meta when using nvdspreprocess?

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU) GPU
• DeepStream Version 7.0
• Issue Type( questions, new requirements, bugs) questions

I am developing with Python and I’ve been trying to access tensor_meta in the preprocess example (deepstream-preprocess-test), but frame_meta.frame_user_meta_list is always None.

The same method works fine when not using nvdspreprocess. What could be the reason for this issue?

--- deepstream_preprocess_test_1.py	2024-06-12 15:23:57.794090819 +0800
+++ deepstream_preprocess_test.py	2024-06-12 15:24:54.493681793 +0800
@@ -85,19 +85,6 @@
         except StopIteration:
             break
 
-        l_user = frame_meta.frame_user_meta_list
-        print(l_user)
-        while l_user is not None:
-            try:
-                user_meta = pyds.NvDsUserMeta.cast(l_user.data)
-            except StopIteration:
-                break
-            if user_meta.base_meta.meta_type != pyds.NvDsMetaType.NVDSINFER_TENSOR_OUTPUT_META:
-                continue
-            
-            tensor_meta = pyds.NvDsInferTensorMeta.cast(user_meta.user_meta_data)
-            print(tensor_meta)
-
         frame_number = frame_meta.frame_num
         l_obj = frame_meta.obj_meta_list
         num_rects = frame_meta.num_obj_meta
3

You can refer to this topic 292345.

4

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.