Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

upload files for TensorRT and TF-TRT for yolo LP #508

Open
wants to merge 10 commits into
base: tensorrt
Choose a base branch
from

Conversation

ongzizhao
Copy link
Contributor

@ongzizhao ongzizhao commented Nov 1, 2021

Created two nodes for tensorRT inference. Requires TensorRT, protobuf=3.8.0 and pycuda installed (currently only tested on Nvidia jetson) Refer to the notion page for more details: https://www.notion.so/TensorRT-d63035adb45c43e180a2517c9fce474d

yolo_TF_TRT:
-Builds a tensortRT optimized saved_model format using the TF TensorRT API
-Requires the saved model directory of yolov4 and yolov4tiny (TF2 saved model format)
-File path of the newly built tensorRT saved_model can be editied in the config file

tensorRT:
-use a preconverted .trt yolov4 and yolov4tiny model for inference
-Following the notion page, yolov4/v4tiny models converted from darknet weigjts > onnx > .trt
-requires precompiling of C++ plugin, currently the plugin is referenced from another repo found in the notion page. If this specific method is adopted, the plugin folder has to be replicated from the other repo.
-The plugin path then has to be updated in the config file

@ongzizhao ongzizhao self-assigned this Nov 1, 2021
@ongtw ongtw self-assigned this Jan 5, 2022
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants