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

added resnet50 with mlmodelscope #15

Closed
wants to merge 3 commits into from

Conversation

cli99
Copy link
Contributor

@cli99 cli99 commented Dec 8, 2018

No description provided.

@profvjreddi
Copy link
Contributor

@cli99 Cheng, I am going to close this and not merge the code into the code base as we are all set on the models. Sound good?

@abduld
Copy link
Contributor

abduld commented Jul 4, 2019

I think this should to the optionzal harness directory per previous discussions? what do you think/

@psyhtest
Copy link
Contributor

psyhtest commented Jul 4, 2019

@abduld I think it could land to v0.5/classification_and_detection/optional_harness_mlmodelscope/resnet. But do I understand it correctly that you do not support any of the official v0.5 TF/PT/ONNX models, only some Caffe/Caffe2/MXNet ones?

@abduld
Copy link
Contributor

abduld commented Jul 5, 2019

no we support the TF/PT/ONNX/Caffe/Caffe2/MXNet/... ones

@psyhtest
Copy link
Contributor

psyhtest commented Jul 6, 2019

The official TF/PT/ONNX models are not part of this PR, hence my question. I would suggest to open a new PR for these, but I defer to @jveejay here.

@JinjunXiong
Copy link

@jveejay Hi Vijay, can you please review this again? We have other MLPerf models integrated with MLModelScope and would like to make them as an option for others to run MLPerf models. This is only the first model we'd like to try this process. Thanks.

@guschmue
Copy link
Contributor

guschmue commented Jul 8, 2019

I don't see the use of the official models either. This PR is from December, don't think we had the official models at that time. Also I see no loadgen being used.

@profvjreddi profvjreddi added the inference v1.0 to be resolved in the upcoming release label Jul 10, 2019
@abduld
Copy link
Contributor

abduld commented Jul 18, 2019

Thanks. We will punt this to the 0.6 release.

@guschmue
Copy link
Contributor

closing this one - you must use the reference models.

@guschmue guschmue closed this Apr 20, 2020
tjablin added a commit to tjablin/inference that referenced this pull request Feb 26, 2022
Add NVIDIA MLPerf-Inference 2.0 calibration docs for Triton CPU
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
inference v1.0 to be resolved in the upcoming release
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

6 participants