TensorRT7.1 download failed

AI & Data Science Deep Learning (Training & Inference) TensorRT
#1

Description

I plan to deploy tensorrt OSS 7.1 on both of my jetson tx2 platform and jetson NX, I follow the instructions on website:
GitHub - NVIDIA/TensorRT at release/7.1,

git clone -b master GitHub - NVIDIA/TensorRT: TensorRT is a C++ library for high performance inference on NVIDIA GPUs and deep learning accelerators. TensorRT
cd TensorRT
git submodule update --init --recursive
export TRT_SOURCE=pwd

When I try “git submodule update --init --recursive” , It always give me：

Submodule path ‘parsers/onnx’: checked out ‘84b5be1d6fc03564f2c0dba85a2ee75bad242c2e’
Cloning into ‘third_party/onnx’…
remote: Enumerating objects: 13, done.
remote: Counting objects: 100% (13/13), done.
remote: Compressing objects: 100% (12/12), done.
error: RPC failed; curl 18 transfer closed with outstanding read data remaining
fatal: The remote end hung up unexpectedly
fatal: early EOF
fatal: index-pack failed
fatal: clone of ‘https://github.com/onnx/onnx.git’ into submodule path ‘third_party/onnx’ failed
Failed to recurse into submodule path ‘parsers/onnx’

I know i need to update three submodules as shown in .gitmodule, but i can’t successfully update any one of them

[submodule “third_party/protobuf”]
path = third_party/protobuf
url = https://github.com/protocolbuffers/protobuf.git
branch = 3.8.x
[submodule “third_party/cub”]
path = third_party/cub
url = https://github.com/NVlabs/cub.git
branch = 1.8.0
[submodule “parsers/onnx”]
path = parsers/onnx
url = https://github.com/onnx/onnx-tensorrt.git
branch = 7.1

I got stuck at this for several days, help me.

Environment

TensorRT Version: TensorRT7.1
GPU Type: Jetson TX2/Jetson NX
Nvidia Driver Version:
CUDA Version: cuda10.2
CUDNN Version: 8.0.0.180-1
Operating System + Version: ubuntu18.04
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
#3

Hi @zhouzhongliang,

Please follow the TesorRT installation guide.
https://docs.nvidia.com/deeplearning/tensorrt/install-guide/index.html

Thank you.

#4

Thank you for your quick reply.

the <> tell me how to install TensorRT , but my jetson tx2 have already installed tensorrt7.1.
for my understanding, I just need to download tensorrt OSS 7.1 and install it. and that is where i got stuck。

thank you!

#5

Hi @zhouzhongliang,

This looks like Jetson issue. Please post your query in Jetson forum.

Thank you.

#6

I finally download the required code to successfuly build tensorrt and its oss by download manually indicated by .gitmodule file

anyway ,thanks for your support

1 Like