mlcommons / ck

Collective Mind (CM) is a small, modular, cross-platform and decentralized workflow automation framework with a human-friendly interface and reusable automation recipes to make it easier to build, run, benchmark and optimize AI, ML and other applications and systems across diverse and continuously changing models, data, software and hardware
https://access.cKnowledge.org/challenges
Apache License 2.0
600 stars 111 forks source link

[W:onnxruntime:, graph.cc:3593 CleanUnusedInitializersAndNodeArgs] Removing initializer 'bert.pooler.dense.bias'. It is not used by any node and should be removed from the model. #1184

Open KingICCrab opened 6 months ago

KingICCrab commented 6 months ago

When I run the command cm run script --tags=generate-run-cmds,inference,_find-performance,_all-scenarios --model=bert-99 --implementation=reference --device=cuda --backend=onnxruntime --category=edge --division=open --quiet There are some warnnings which I don't konw it matters. 2024-03-23 16:39:29.057780772 [W:onnxruntime:, graph.cc:3593 CleanUnusedInitializersAndNodeArgs] Removing initializer 'bert.pooler.dense.bias'. It is not used by any node and should be removed from the model. 2024-03-23 16:39:29.057866605 [W:onnxruntime:, graph.cc:3593 CleanUnusedInitializersAndNodeArgs] Removing initializer 'bert.pooler.dense.weight'. It is not used by any node and should be removed from the model.

I also get a bad result.

zhaohc710-reference-gpu-onnxruntime-v1.17.1-default_config +---------+--------------+----------+-------+-----------------+---------------------------------+ | Model | Scenario | Accuracy | QPS | Latency (in ms) | Power Efficiency (in samples/J) | +---------+--------------+----------+-------+-----------------+---------------------------------+ | bert-99 | SingleStream | - | - | X 0.0 | | | bert-99 | Offline | - | 2.657 | - | | +---------+--------------+----------+-------+-----------------+---------------------------------+

My GPU is RTX4070 labtop, the results may be too small?

arjunsuresh commented 1 week ago

Sorry for the late reply. Please follow the current documentation for running MLPerf inference.