Open psyhtest opened 3 years ago
By the way, the above mentioned postprocessing issue also needs to be fixed but here's a quick workaround (installing the LoadGen Python module to userspace):
$ python -m pip install --user $(find $(ck locate env --tags=mlperf,inference,dividiti.rnnt) -name *.whl)
Processing ./dist/mlperf_loadgen-0.5a0-cp38-cp38-linux_x86_64.whl
Installing collected packages: mlperf-loadgen
Successfully installed mlperf-loadgen-0.5a0
The RNN-T CmdGen is work-in-progress. We started it for the v0.7 submission round, but eventually did not submit due to a belatedly discovered postprocessing issue. Not surprisingly, it needs more love to get into shape.
Currently, the usage is:
Future improvements:
--model
parameter should be optional. (We only support one model after all.)--sut
parameter should allow any SUT name. At the moment, it is restricted to handful, and alternatives result in an error (CK error: [cmdgen] build_map[sut] is missing both 'aws-g4dn.4xsmall' and '###' values!
.)mlperf-closed-aws-g4dn.4xlarge-pytorch-v1.15.1-rnnt-singlestream
) must include the--mode
to allow keeping both performance and accuracy experiment entries simultaneously. At the moment, a previously recorded experiment entry for one mode must be removed (ck rm local:experiment:mlperf-closed*rnnt* -f
) to allow for the other mode.v1.15.1
). The default inference engine name (pytorch
) should be customizable according to the plugins used.