AssertionError: Exporting FasterRCNN model

when i fire export command using :
tlt-export -k $KEY --export_module faster_rcnn --outputs dense_class/Softmax,dense_regress/BiasAdd,proposal -o /workspace/frcnn_kitti.etlt /workspace/output/faster_rcnn/frcnn_kitti.epoch12.tlt

i am facing following error:
9-10-21 10:33:17.488246: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1115] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 5323 MB memory) -> physical GPU (device: 0, name: Quadro K6000, pci bus id: 0000:02:00.0, compute capability: 3.5)
2019-10-21 10:33:17.489330: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1115] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:1 with 4291 MB memory) -> physical GPU (device: 1, name: Tesla K20c, pci bus id: 0000:82:00.0, compute capability: 3.5)
WARNING:tensorflow:From /usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/op_def_library.py:263: colocate_with (from tensorflow.python.framework.ops) is deprecated and will be removed in a future version.
Instructions for updating:
Colocations handled automatically by placer.
2019-10-21 10:33:24,593 [WARNING] tensorflow: From /usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/op_def_library.py:263: colocate_with (from tensorflow.python.framework.ops) is deprecated and will be removed in a future version.
Instructions for updating:
Colocations handled automatically by placer.
Traceback (most recent call last):
File “/usr/local/bin/tlt-export”, line 10, in
sys.exit(main())
File “./common/magnet_export.py”, line 206, in main
File “./common/magnet_export.py”, line 382, in magnet_export
AssertionError: Exporting FasterRCNN model

Thanks,
Deep

Hi sdeep038,
As mentioned in https://docs.nvidia.com/metropolis/TLT/tlt-release-notes/index.html, FasterRCNN currently supports only single GPU training with a batch-size of 1.

I find the root cause now.
You are missing the spec file. Please add it into command.