Hi ,
I have tried out both loss.backward() and model_engine.backward(loss) for my code. There are several subtle differences that I have observed , for one retain_graph = True does not work for model_engine.backward(loss) . This is creating a problem since buffers are not being retained every time I run the code for some reason.
Please look into this if you could.
Description
If the Triton server build fails due to any reason, I have to delete the /tmp/citritonbuild/<backend> folders to prevent the next rebuild from throwing git repo already exists error.
Triton Information
r21.05
I am building the Triton server myself.
To Reproduce
uninstall one of the dependency needed by a backend.
run build.py with all the backends enabled
The latest release of openvino has changed the inference engine API, providing a new API that takes advantage of the full potential of Intel's latest version of IR (IR 11). More information can be found at this link. We should adapt nebullvm's OpenVinoInferenceLearner to their latest API.
Usef
Hi, I am so interesting in your project, and wonder if you need contributor and how could I make my own contribution?
Bounds check and call [] operator
'max_request_size' seems to refer to bytes, not mb.
Add a description, image, and links to the inference topic page so that developers can more easily learn about it.
To associate your repository with the inference topic, visit your repo's landing page and select "manage topics."
I figured out a way to get the (x,y,z) data points for each frame from one hand previously. but im not sure how to do that for the new holistic model that they released. I am trying to get the all landmark data points for both hands as well as parts of the chest and face. does anyone know how to extract the holistic landmark data/print it to a text file? or at least give me some directions as to h