Can I reconstruct the network using tensorrt API when change a caffe mode to a tensorrt model?


I konw I can reconstruct the network using tensorrt API when original model is pytorch or tensorflow, but I’m not sure if the caffe model can do the same .I remeber you should change parameter format when change the tensorflow mode to tensorrt model… So can I directly set the parameter of the caffe model to the tensorRT model?

sorry for my poor english


TensorRT Version: 7.0
GPU Type: T4
Nvidia Driver Version: 10.2
CUDA Version: 7.** / 8.**
CUDNN Version:
Operating System + Version: ubuntu
Python Version (if applicable):
TensorFlow Version (if applicable):
PyTorch Version (if applicable):
Baremetal or Container (if container which image + tag):

Relevant Files

Please attach or include links to any models, data, files, or scripts necessary to reproduce your issue. (Github repo, Google Drive, Dropbox, etc.)

Steps To Reproduce

Please include:

  • Exact steps/commands to build your repro
  • Exact steps/commands to run your repro
  • Full traceback of errors encountered