search

NVIDIA / TensorRT

NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.
https://developer.nvidia.com/tensorrt
Apache License 2.0
10.32k stars 2.09k forks source link

ubuntu-cross-aarch64.Dockerfile docker/jetpack_files: file does not exist #1671

Closed cyrusbehr closed 2 years ago

cyrusbehr commented 2 years ago

Trying to build the ubuntu-cross-aarch64.Dockerfile image. Using release 8.2.1

Running the command docker build -t aarch64-tensorrt -f ubuntu-cross-aarch64.Dockerfile .. from the docker directory fails because of the following error:

Step 22/33 : COPY docker/jetpack_files /pdk_files
COPY failed: file not found in build context or excluded by .dockerignore: stat docker/jetpack_files: file does not exist

Am I missing something? I wasn't able to find the docker/jetpack_files directory either.

cyrusbehr commented 2 years ago

Running ./docker/build.sh --file docker/ubuntu-cross-aarch64.Dockerfile --tag tensorrt-jetpack-cuda10.2 --cuda 10.2 like suggested in the readme also fails with the same error message.

cyrusbehr commented 2 years ago

Looks like i missed the steps listed in the readme:

(Optional - for Jetson builds only) Download the JetPack SDK Download and launch the JetPack SDK manager. Login with your NVIDIA developer account. Select the platform and target OS (example: Jetson AGX Xavier, Linux Jetpack 4.6), and click Continue. Under Download & Install Options change the download folder and select Download now, Install later. Agree to the license terms and click Continue. Move the extracted files into the /docker/jetpack_files folder.