search

isarsoft / yolov4-triton-tensorrt

This repository deploys YOLOv4 as an optimized TensorRT engine to Triton Inference Server
http://www.isarsoft.com
Other
276 stars 63 forks source link

Config.pbtxt requirement file #24

Closed chiehpower closed 3 years ago

chiehpower commented 3 years ago

Hi isarsoft,

I really appreciate your contributions on this repository!! I can successfully generate the tensorrt engine on TensorRT 20.03.1 image from NGC. I wonder where can I get the config.pbtxt file in order to deploy on model repository of triton inference server?

Thank you so much!

BR, Chieh

olibartfast commented 3 years ago

Hi, when starting the triton server if you pass the param --strict-model-config=false you don't need the config file because Triton should generate it for you, like the one below:

platform: "tensorrt_plan"
max_batch_size: 1
input {
  name: "data"
  data_type: TYPE_FP32
  dims: 3
  dims: 608
  dims: 608
}
output {
  name: "prob"
  data_type: TYPE_FP32
  dims: 7001
  dims: 1
  dims: 1
}
default_model_filename: "model.plan"
chiehpower commented 3 years ago

Dear @francescooliva ,

Thanks for your reply and your important information! I will test again. Thank you!