I was looking at the Jetson install guide after the new updates and it looks pretty good. I have a few comments

• We should specify exactly what JetPack, TensorRT versions that MMDeploy SDK has been tested successfully with. i.e. Jetpack 4.6 rev 3 and above and TensorRT version XX
• We should specify which versions of PyTorch and torchvision that are compatible to make sure the user picks correct versions. We could include this link.
• Install instructions for PyTorch, Torchvision should list all the steps required, i.e.:

# pytorch
wget https://nvidia.box.com/shared/static/fjtbno0vpo676a25cgvuqc1wty0fkkg6.whl -O torch-1.10.0-cp36-cp36m-linux_aarch64.whl
pip3 install torch-1.10.0-cp36-cp36m-linux_aarch64.whl
# torchvision
sudo apt-get install <necessary dependencies> -y
sudo rm -r torchvision
git clone --branch v0.11.1 https://github.com/pytorch/vision torchvision
cd torchvision
export BUILD_VERSION=0.11.1  # where 0.x.0 is the torchvision version
python3 setup.py install
cd ../