Image Classification using Mobilenet models
Install CM following the installation page.
Mobilenet models are not official MLPerf models and so cannot be used for a Closed division MLPerf inference submission. But since they can be run with Imagenet dataset, we are allowed to use them for Open division submission. Only CPU runs are supported now.
TFLite Backend
Mobilenet V1
cm run script --tags=run,mobilenet-models,_tflite,_mobilenet-v1 \
--adr.compiler.tags=gcc
Mobilenet V2
cm run script --tags=run,mobilenet-models,_tflite,_mobilenet-v2 \
--adr.compiler.tags=gcc
Mobilenet V2
cm run script --tags=run,mobilenet-models,_tflite,_mobilenet-v2 \
--adr.compiler.tags=gcc
Mobilenet V1,V2,V3
cm run script --tags=run,mobilenet-models,_tflite,_mobilenet \
--adr.compiler.tags=gcc
Efficientnet
cm run script --tags=run,mobilenet-models,_tflite,_efficientnet \
--adr.compiler.tags=gcc
ARMNN Backend
Mobilenet V1
cm run script --tags=run,mobilenet-models,_tflite,_armnn,_mobilenet-v1 \
--adr.compiler.tags=gcc
Mobilenet V2
cm run script --tags=run,mobilenet-models,_tflite,_armnn,_mobilenet-v2 \
--adr.compiler.tags=gcc
Mobilenet V2
cm run script --tags=run,mobilenet-models,_tflite,_armnn,_mobilenet-v2 \
--adr.compiler.tags=gcc
Mobilenet V1,V2,V3
cm run script --tags=run,mobilenet-models,_tflite,_armnn,_mobilenet \
--adr.compiler.tags=gcc
Efficientnet
cm run script --tags=run,mobilenet-models,_tflite,_armnn,_efficientnet \
--adr.compiler.tags=gcc