Tensorflow MobileNetv2 doesn't work with deepstream

Autonomous Machines Jetson & Embedded Systems Jetson Nano
1

I followed the official instructions provided for Inception_v2 but I am using ssd_mobilenet_v2 instead of inception. I converted the file to uff format but when I run it using deepstream, it is throwing this error:

[libprotobuf FATAL /home/erisuser/p4sw/sw/gpgpu/MachineLearning/DIT/externals/protobuf/aarch64/10.0/include/google/protobuf/repeated_field.h:1408] CHECK failed: (index) < (current_size_): 
terminate called after throwing an instance of 'google_private::protobuf::FatalException'
  what():  CHECK failed: (index) < (current_size_): Aborted (core dumped)

Anyone else faced this issue? Stuck at this for two days and I am unable to figure out what is wrong. Any help would be highly appreciated.

2

Hi,

Would you mind to share the complete log with us?
It looks like there are some operations of your model don’t create the MemoryData right.

A possible cause is that ssd_mobilenet_v2 requires some TensorRT plugin implementation and customized compiling.
Have you successfully loaded your model with our TensorRT sample: /usr/src/tensorrt/samples/python/uff_ssd/
If not, it’s recommended to try it. This can make sure your uff model and plugin operation is correct.

Thanks.