-
Notifications
You must be signed in to change notification settings - Fork 2.1k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
How to convert tensorflow pb (in NCHW format with ResizeOp) into OpenVino IR? #652
Comments
@lazarevevgeny Can you help? |
If your TF model is in NCHW layout you need to specify |
@ilyachur @lazarevevgeny Thank you guys. I convert the pb( And when I run infer use openvino ( just in CPU first), I get one error:
The openvino info:
My pb model contain Node
Then what should I do? |
I make a small pb model (in OpenVino 2020.R2): You can test with it. |
@ausk Thank you for the reproducer. I checked it on the last master and the problem is that at the current moment OpenVINO supports Interpolate operation which is performed over spatial dimensions only. Unfortunately in your case Interpolate is performed on axises 1, 2. |
We will look to this problem and find solution to fix it. |
@ilyachur it is a different story. The MO does not convert the model correctly. During the conversion the Transpose before ResizeNearestNeighbor should be removed because in OpenVINO Interpolate works in NCHW layout but in TF the ResizeNearestNeighbor expects input in the NHWC layout. This is a tricky bug to be solved on the MO side. |
@ilyachur @lazarevevgeny Thank you for your help. Best regards. |
@ausk, the issue has been fixed. Please, take the MO from the master branch and convert the model again. Then use IE from OpenVINO 2020.4 to infer the model. Closing the ticket. |
@witignite , you can use Netron to visualize the graph. |
* update the dockerfile to use cuda base image and correct apt nvidia packages * Return cudnn into Dockerfile, adds drivers * Update README.md --------- Co-authored-by: Dariusz Trawinski <Dariusz.Trawinski@intel.com>
Hi, I have a tensorflow pb model in
NCHW
format,how to convert it into OpenVino IR?If I convert it directly, then I get
What openvino thinks:
nhwc(1,1,224,224) => nchw(1,224,1,224)
But actually, it is:
nchw(1,1,224,224) => nwch(1,224,1,224)
.While there is no predefined
NWCH
format in openvino.So does anyone know how to convert the pb(in
NCHW
format) into IR?The text was updated successfully, but these errors were encountered: