Skip to content
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

5.1 #427

Open
wants to merge 2 commits into
base: 5.1
Choose a base branch
from
Open

5.1 #427

wants to merge 2 commits into from

Conversation

NikolasMarkou
Copy link

#426 Fixed ResizeNearest and added ResizeBilinear that should be supported in that branch based on the API

@CLAassistant
Copy link

CLAassistant commented Apr 6, 2020

CLA assistant check
All committers have signed the CLA.

@NikolasMarkou
Copy link
Author

Hello is there a problem in merging this ?

@DJMeng
Copy link

DJMeng commented May 29, 2020

Nice work, Do you fix ResizeNearest and added ResizeBilinear that should be supported in 7.0 branch? Thanks very much. my problems is #469

@NikolasMarkou
Copy link
Author

Hi @DJMeng I haven't read through that branch. Check the code and if it fits push it otherwise you will have to wait for my client to move to that :)

@DJMeng
Copy link

DJMeng commented May 29, 2020

Hi @DJMeng I haven't read through that branch. Check the code and if it fits push it otherwise you will have to wait for my client to move to that :)

Ok,Thanks for your reply.

And when you convert onnx to trt on branch 5.1, do you meet this error?

[8] Assertion failed: trt_dtype == nvinfer1::DataType::kHALF && cast_dtype == ::ONNX_NAMESPACE::TensorProto::FLOAT

My env is : torch:1.3, opset:9,onnx=1.7

@NikolasMarkou
Copy link
Author

NikolasMarkou commented May 29, 2020 via email

@DJMeng
Copy link

DJMeng commented May 29, 2020

This is a casting issue, check your types. Not everything is supported

On Fri, 29 May 2020, 11:14 DJMeng, @.***> wrote: Hi @DJMeng https://github.com/DJMeng I haven't read through that branch. Check the code and if it fits push it otherwise you will have to wait for my client to move to that :) Ok,Thanks for your reply.And when you convert onnx to trt on branch 5.1, do you meet this error? [8] Assertion failed: trt_dtype == nvinfer1::DataType::kHALF && cast_dtype == ::ONNX_NAMESPACE::TensorProto::FLOAT use — You are receiving this because you modified the open/close state. Reply to this email directly, view it on GitHub <#427 (comment)>, or unsubscribe https://github.com/notifications/unsubscribe-auth/AAI7CDH2L3JCTOKYGEN4EQ3RT5VGHANCNFSM4MCHK5KQ .

Thank you. I will try other ways.

@NikolasMarkou
Copy link
Author

Hello @kevinch-nv , is there a problem with the commit ?

@NikolasMarkou NikolasMarkou reopened this Jun 18, 2020
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants