Dong Lin

@reedwm Toby is the person who added Docker support for PerfZero. I don't have experience with docker and I don't know which part of service in our infra uses docker....

Thank you @gaborvecsei for offering to fix this issue! If the PR is easy to review (e.g. it just changed a version), it will be great and I can just...

Thanks for the PR. LGTM. @becketqin Do you want to take a look at this PR?

Hi @hidefromkgb, the ResNet50 test runs ResNet50 inference on CPU for one step and checks that its last layer (i.e. softmax layer) generates the expected numerical output as the corresponding...

@hidefromkgb Yeah your observation is correct. The [resnet50_graph_inference.mlir](https://github.com/tensorflow/runtime/blob/master/integrationtest/resnet/resnet50_graph_inference.mlir) indeed does not include the softmax layer, whereas the ResNet50 inference in production will include the softmax layer as the last layer....

@hidefromkgb I might have missed some knowledge here. Can you explain where does that `58990869004419072.f` come from? The MLIR test takes an input tensor, applies the ResNet50 inference pipeline (excluding...

@hidefromkgb Sorry, I didn't realize you were talking about the `5.899087e+16` as shown in your first comment. I just re-run the corresponding TF model without the softmax layer and it...

Supported protobuf in PR #127.

@MartijnVisser Do you have time to review this PR?

@MartijnVisser Thanks for the comments. flink-ml docs is built by this script https://github.com/apache/infrastructure-bb2/blob/master/flink-ml.py. This script is executed every day by a build bot whose status can be found by searching...