Hello,
I’ve been trying to run the TensorRT tutorial (https://docs.nvidia.com/deeplearning/sdk/tensorrt-api/topics/topics/workflows/tf_to_tensorrt.html) but the program halts at:
engine = trt.utils.uff_to_trt_engine(G_LOGGER, uff_model, parser, 1, 1 << 20)
The program produces the following error:
---------------------------------------------------------------------------
AssertionError Traceback (most recent call last)
<ipython-input-21-d6e6de8c521d> in <module>()
----> 1 engine = trt.utils.uff_to_trt_engine(G_LOGGER, uff_model, parser, 1, 1 << 20)
/usr/lib/python2.7/dist-packages/tensorrt/utils/_utils.py in uff_to_trt_engine(logger, stream, parser, max_batch_size, max_workspace_size, datatype, plugin_factory, calibrator)
225 filename, line, func, text = tb_info[-1]
226
--> 227 raise AssertionError('UFF parsing failed on line {} in statement {}'.format(line, text))
228
229
AssertionError: UFF parsing failed on line 219 in statement assert(engine)
I’m not yet very familiar with TensorRT. Could any one provide me with additional information to solve this?
Library information:
Tensorflow: 1.4.1
TensorRT: 4.0.0.3
Cuda: 8.0.33
cuDNN: 6.0.21