This release contains mirror downloads of the DNN models used by the repo.

During the build process, the jetson-inference repo will automatically attempt to download the models for you.

The primary site storing the models is on Box.com. However, users from China may be unable to access Box.com, so if your system is unable to download the models from their primary location, you can grab the models that you wish to download below.

For each model that you wish to use for inferencing at runtime, download the associated archive found below to your <jetson-inference>/data/networks directory, and then extract it with the following command:

cd <jetson-inference>/data/networks/
tar -zxvf <model-archive-name>.tar.gz

Beforehand, clone the repo like normal. This release page is not meant for storing a version of the code.