search

intel / ai-reference-models

Intel® AI Reference Models: contains Intel optimizations for running deep learning workloads on Intel® Xeon® Scalable processors and Intel® Data Center GPUs
Apache License 2.0
674 stars 220 forks source link

Inconsistent "permissions" behavior between fp32 vs int8 with Resnet50 model #84

Open brian-a-scott opened 3 years ago

brian-a-scott commented 3 years ago

try to run models/quickstart/image_recognition/tensorflow/resnet50/inference; both fp32 and int8. Using wget command to download the .gz file to Documents directory and using tar to unzip the file. fp32 runs without issues. int8 gives "bash: quickstart/int8_inference.sh: Permission denied".

dmsuehir commented 3 years ago

Thanks @brian-a-scott. This will get fixed in the next release. In the meantime, you can run chmod +x int8_inference.sh so that the script can be executed.

brian-a-scott commented 3 years ago

Thanks. Brian

From: Dina Suehiro Jones @.> Sent: Friday, June 25, 2021 8:51 AM To: IntelAI/models @.> Cc: Scott, Brian A @.>; Mention @.> Subject: Re: [IntelAI/models] Inconsistent "permissions" behavior between fp32 vs int8 with Resnet50 model (#84)

Thanks @brian-a-scotthttps://github.com/brian-a-scott. This will get fixed in the next release. In the meantime, you can run chmod +x int8_inference.sh so that the script can be executed.

— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHubhttps://github.com/IntelAI/models/issues/84#issuecomment-868659958, or unsubscribehttps://github.com/notifications/unsubscribe-auth/AL5XL7PPZGWP7DYCTNUIZOLTUSQVJANCNFSM47COOZSA.

sramakintel commented 5 months ago

@brian-a-scott: did the workaround help resolve the issue? If not, can you try our latest optimzations for tensorflow rn50? https://www.intel.com/content/www/us/en/developer/articles/containers/cpu-reference-model-containers.html