objectDetector_SSD fails on ssd_mobilenet_v2

Hello,
I successfully followed the README in objectDetector_SSD and got the ssd_inception_v2_coco_2017_11_17 running.

I did the same steps with ssd_mobilenet_v2_coco_2018_03_29 and when running the pipeline, it is failing during creating the engine from the ssd_mobilenet_v2.uff model file.

Trying to create engine from model files
0:00:02.520856928 12355     0x262b40a0 ERROR                nvinfer gstnvinfer.cpp:511:gst_nvinfer_logger:<primary_gie_classifier> NvDsInferContext[UID 1]:log(): Parameter check failed at: ../builder/Layers.h::setAxis::333, condition: axis >= 0
0:00:02.563495104 12355     0x262b40a0 ERROR                nvinfer gstnvinfer.cpp:511:gst_nvinfer_logger:<primary_gie_classifier> NvDsInferContext[UID 1]:log(): Concatenate/concat: all concat input tensors must have the same dimensions except on the concatenation axis
0:00:02.563597792 12355     0x262b40a0 ERROR                nvinfer gstnvinfer.cpp:511:gst_nvinfer_logger:<primary_gie_classifier> NvDsInferContext[UID 1]:log(): Could not compute dimensions for Concatenate/concat, because the network is not valid
0:00:02.564067680 12355     0x262b40a0 ERROR                nvinfer gstnvinfer.cpp:511:gst_nvinfer_logger:<primary_gie_classifier> NvDsInferContext[UID 1]:generateTRTModel(): Failed while building cuda engine for network
0:00:02.570758208 12355     0x262b40a0 ERROR                nvinfer gstnvinfer.cpp:511:gst_nvinfer_logger:<primary_gie_classifier> NvDsInferContext[UID 1]:initialize(): Failed to create engine from model files

Hi,

You will need to update the config file for ssd_mobilenet_v2_coco_2018_03_29.
Please check this GitHub for the information:
https://github.com/AastaNV/TRT_object_detection/tree/master/config

Thanks.

I updated the config, converted successsfully to *.uff-file, but it is still not able to create an engine from it.
Now, I get the following error.

deepstream-app: nvdsiplugin_ssd.cpp:53: FlattenConcat::FlattenConcat(int, bool): Assertion `mConcatAxisID == 1 || mConcatAxisID == 2 || mConcatAxisID == 3' failed.

Hi,

Are you trying to concat two input on the batch axis (axis=0)?
Please noticed that TensorRT cannot support cross batch concatenate currently.

Thanks.