• Hardware Platform (Jetson / GPU): dPU A40.
• DeepStream Version: 6.4-triton-multiarch.
• TensorRT Version: 8.6.2.3.
• NVIDIA GPU Driver Version (valid for GPU only): 525.147.05.
• Issue Type( questions, new requirements, bugs): questions.
• How to reproduce the issue ? (This is for bugs. Including which sample app is using, the configuration files content, the command line used and other details for reproducing)
I am currently using DeepStream Python, and my pipeline is sources → streammux → pgie (person detection) → tracker → sgie (reid), but I noticed that the config of config_tracker_NvDCF_accuracy.yml uses the reid model and we can use outputReidTensor=1 to get embeddings from the model. So, I changed my pipeline to sources → streammux → pgie → tracker. However, it seems that outputReidTensor=1 is not working because in the code snippet
l_batch_user=batch_meta.batch_user_meta_list
print("l_batch_user", l_batch_user)
while l_batch_user is not None:
try:
user_meta= pyds.NvDsUserMeta.cast(l_batch_user.data)
except StopIteration:
break
if user_meta and user_meta.base_meta.meta_type == pyds.NVDS_TRACKER_BATCH_REID_META:
pReidTensor = pyds.NvDsReidTensorBatch.cast(user_meta.user_meta_data)
print("pReidTensor", pReidTensor)
try:
l_batch_user=l_batch_user.next
except StopIteration:
break
try:
l_frame = l_frame.next
except StopIteration:
break
l_batch_user=batch_meta.batch_user_meta_list is NULL. Can you guide me on how to fix this? Thank you in advance.