I’m new in using TensorRT Python API.
Could you help me to migrate simple angle prediction model from Keras framework to TensorRT via ONNX?
TensorRT Version: 220.127.116.11
GPU Type: GeForce GTX 1060 6 GB
Nvidia Driver Version: 440.33.01
CUDA Version: 10.2
CUDNN Version: 7.1
Operating System + Version: Ubuntu 18.04
Python Version (if applicable): 3.6
TensorFlow Version (if applicable): 2.3.1
Issue refer to this one:
My model has two dynamic input. I had set up optimization profiles, but I can not transfer it to engine bulder.
profile.set_shape('input_5', (1, 64, 64, 3), (20, 64, 64, 3), (100, 64, 64, 3)) profile.set_shape('input_6', (1, 3), (20, 3), (100, 3)) config.add_optimization_profile(profile) engine = builder.build_cuda_engine(network)
On the last step I have an error:
[TensorRT] ERROR: Network has dynamic or shape inputs, but no optimization profile has been defined.
Could you please provide some examples with dynamic shapes on Python TensorRT and help me?