Here is the information of official TensorFlow release for XavierNX.
Python 3.6+JetPack4.5
sudo apt-get install libhdf5-serial-dev hdf5-tools libhdf5-dev zlib1g-dev zip libjpeg8-dev liblapack-dev libblas-dev gfortran
sudo apt-get install python3-pip
sudo pip3 install -U pip testresources setuptools==49.6.0
sudo pip3 install -U numpy==1.16.1 future==0.18.2 mock==3.0.5 h5py==2.10.0 keras_preprocessing==1.1.1 keras_applications==1.0.8 gast==0.2.2 futures protobuf pybind11
# TF-2.x
$ sudo pip3 install --pre --extra-index-url https://developer.download.nvidia.com/compute/redist/jp/v45 tensorflow
# TF-1.15
$ sudo pip3 install --pre --extra-index-url https://developer.download.nvidia.com/compute/redist/jp/v45 ‘tensorflow<2’
Python 3.6+JetPack4.4
$ sudo apt-get update
$ sudo apt-get install libhdf5-serial-dev hdf5-tools libhdf5-dev zlib1g-dev zip libjpeg8-dev liblapack-dev libblas-dev gfortran
$ sudo apt-get install python3-pip
$ sudo pip3 install -U pip testresources setuptools
$ sudo pip3 install -U numpy==1.16.1 future==0.17.1 mock==3.0.5 h5py==2.9.0 keras_preprocessing==1.0.5 keras_applications==1.0.8 gast==0.2.2 futures protobuf pybind11
# TF-2.x
$ sudo pip3 install --pre --extra-index-url https://developer.download.nvidia.com/compute/redist/jp/v44 tensorflow==2.3.1+nv20.12
# TF-1.15
$ sudo pip3 install --pre --extra-index-url https://developer.download.nvidia.com/compute/redist/jp/v44 ‘tensorflow<2’
Thanks.
3 Likes
Does JetPack 4.4 support for TF C API?
Hi,
I meet the error , showed as below.
So, which one should I select?
So, how to get the version of nv ?
Hi,
Please try this command:
$ sudo pip3 install --extra-index-url https://developer.download.nvidia.com/compute/redist/jp/v44 tensorflow==1.15.2+nv20.6
Thanks.
Hi,
Sorry that we don’t support C++ API in our latest package.
This is in our feature request list and will be prioritized by our internal team.
Thanks.
I am working with a lower version of tensorflow (1.8), is there a way to choose the version of tensorflow that is downloaded onto the Xavier NX?
Thanks. Just a note here for people with fresh installation. Python 3.6 needs to be installed with python3.6-dev as well using sudo apt-get install python3.6-dev so that numpy gets installed.
Hi,
I’ve tried running this command. The package is installed but it still shows tensorflow is not installed. Do I need to build it again or add any path for installation?
Hi, how are you?
I’ve a Jetson Xavier NX, I followed the instructions, but it throws me the following errors:
I was checking the forum and it seems this error is recurring (Unable to install tensorflow in jetpack 4.6 Unable to reach https://repo.download.nvidia.com/jetson/x86_64 calling apt-get update ).
how is it solved? or should we wait for services to stabilize?
there is another forum or platform where we can obtain a status of the services and/or inform you of that?
thank you very much for your time and help,
Sebastián
UPDATE:
Hi,
Your problem is most likely due to an issue that we are experiencing with our downloads. We are actively working to resolve this issue. Unfortunately we don’t have an ETA for when this will be fixed. I will post here when we are up and running.
Thanks for your patience,
Tom K