I was trying to create trt engine in TRT-container of image(tensorrt:19.12-py3),
and following the guidelines of NVIDIA-AI-IOT repo https://github.com/NVIDIA-AI-IOT/tf_trt_models#ic_models . but every time after executing this code my jupyter lab kernel dies.
import tensorflow.contrib.tensorrt as trt trt_graph = trt.create_inference_graph( input_graph_def=frozen_graph, outputs=output_names, max_batch_size=1, max_workspace_size_bytes=1 << 25, precision_mode='FP16', minimum_segment_size=50 )
is there any possible solution for this or any special environment setup is required to run thin?