I cannot installing PyTorch for python2.7

I want to do Transfer Learning with PyTorch .
I’m using Jetson Xavier NX for device and jetpack is 4.4.

I tried transfer learning according to the procedure on the following site.
jetson-inference/pytorch-transfer-learning.md at master · dusty-nv/jetson-inference · GitHub

I could install PyTorch for python3.6. However I couldn’t install PyTorch for python2.7.
I got an error in the above url Processing images with TensorRT section.

terminal command: $imagenet-console.py --model=cat_dog/resnet18.onnx --input_blob=input_0 --output_blob=output_0 --labels=$DATASET/labels.txt $DATASET/test/dog/01.jpg dog.jpg

The following error statement:
jetson.inference.init.py
jetson.inference – initializing Python 2.7 bindings…
jetson.inference – registering module types…
jetson.inference – done registering module types
jetson.inference – done Python 2.7 binding initialization
jetson.utils.init.py
jetson.utils – initializing Python 2.7 bindings…
jetson.utils – registering module functions…
jetson.utils – done registering module functions
jetson.utils – registering module types…
jetson.utils – done registering module types
jetson.utils – done Python 2.7 binding initialization
[image] failed to find file ‘/test/dog/01.jpg’
Traceback (most recent call last):
File “/usr/local/bin/imagenet-console.py”, line 46, in
img, width, height = jetson.utils.loadImageRGBA(opt.file_in)
Exception: jetson.utils – loadImageRGBA() failed to load the image

So, I want to know how to install PyTorch for python2.7 or how to run PyTorch for python3.6.