get-ml-model-efficientnet-lite
Automatically generated README for this automation recipe: get-ml-model-efficientnet-lite
Category: AI/ML models
License: Apache 2.0
- CM meta description for this script: _cm.json
- Output cached? True
Reuse this script in your project
Install MLCommons CM automation meta-framework
Pull CM repository with this automation recipe (CM script)
cm pull repo mlcommons@cm4mlops
Print CM help from the command line
cmr "get ml-model efficientnet raw ml-model-efficientnet ml-model-efficientnet-lite lite tflite image-classification" --help
Run this script
Run this script via CLI
cm run script --tags=get,ml-model,efficientnet,raw,ml-model-efficientnet,ml-model-efficientnet-lite,lite,tflite,image-classification[,variations]
Run this script via CLI (alternative)
cmr "get ml-model efficientnet raw ml-model-efficientnet ml-model-efficientnet-lite lite tflite image-classification [variations]"
Run this script from Python
import cmind
r = cmind.access({'action':'run'
'automation':'script',
'tags':'get,ml-model,efficientnet,raw,ml-model-efficientnet,ml-model-efficientnet-lite,lite,tflite,image-classification'
'out':'con',
...
(other input keys for this script)
...
})
if r['return']>0:
print (r['error'])
Run this script via Docker (beta)
cm docker script "get ml-model efficientnet raw ml-model-efficientnet ml-model-efficientnet-lite lite tflite image-classification[variations]"
Variations
-
No group (any combination of variations can be selected)
Click here to expand this section.
_tflite
-
Group "kind"
Click here to expand this section.
_lite0(default)- ENV variables:
- CM_ML_MODEL_EFFICIENTNET_LITE_KIND:
lite0
- CM_ML_MODEL_EFFICIENTNET_LITE_KIND:
- ENV variables:
_lite1- ENV variables:
- CM_ML_MODEL_EFFICIENTNET_LITE_KIND:
lite1
- CM_ML_MODEL_EFFICIENTNET_LITE_KIND:
- ENV variables:
_lite2- ENV variables:
- CM_ML_MODEL_EFFICIENTNET_LITE_KIND:
lite2
- CM_ML_MODEL_EFFICIENTNET_LITE_KIND:
- ENV variables:
_lite3- ENV variables:
- CM_ML_MODEL_EFFICIENTNET_LITE_KIND:
lite3
- CM_ML_MODEL_EFFICIENTNET_LITE_KIND:
- ENV variables:
_lite4- ENV variables:
- CM_ML_MODEL_EFFICIENTNET_LITE_KIND:
lite4
- CM_ML_MODEL_EFFICIENTNET_LITE_KIND:
- ENV variables:
-
Group "precision"
Click here to expand this section.
_fp32(default)- ENV variables:
- CM_ML_MODEL_EFFICIENTNET_LITE_PRECISION:
fp32 - CM_ML_MODEL_INPUTS_DATA_TYPE:
fp32 - CM_ML_MODEL_PRECISION:
fp32 - CM_ML_MODEL_WEIGHTS_DATA_TYPE:
fp32
- CM_ML_MODEL_EFFICIENTNET_LITE_PRECISION:
- ENV variables:
_uint8- Aliases:
_int8 - ENV variables:
- CM_ML_MODEL_EFFICIENTNET_LITE_PRECISION:
int8 - CM_ML_MODEL_INPUTS_DATA_TYPE:
uint8 - CM_ML_MODEL_PRECISION:
uint8 - CM_ML_MODEL_WEIGHTS_DATA_TYPE:
uint8
- CM_ML_MODEL_EFFICIENTNET_LITE_PRECISION:
- Aliases:
-
Group "resolution"
Click here to expand this section.
_resolution-224(default)- ENV variables:
- CM_ML_MODEL_IMAGE_HEIGHT:
224 - CM_ML_MODEL_IMAGE_WIDTH:
224 - CM_ML_MODEL_MOBILENET_RESOLUTION:
224 - CM_DATASET_PREPROCESSED_IMAGENET_DEP_TAGS:
_resolution.224
- CM_ML_MODEL_IMAGE_HEIGHT:
- ENV variables:
_resolution-240- ENV variables:
- CM_ML_MODEL_IMAGE_HEIGHT:
240 - CM_ML_MODEL_IMAGE_WIDTH:
240 - CM_ML_MODEL_MOBILENET_RESOLUTION:
240 - CM_DATASET_PREPROCESSED_IMAGENET_DEP_TAGS:
_resolution.240
- CM_ML_MODEL_IMAGE_HEIGHT:
- ENV variables:
_resolution-260- ENV variables:
- CM_ML_MODEL_IMAGE_HEIGHT:
260 - CM_ML_MODEL_IMAGE_WIDTH:
260 - CM_ML_MODEL_MOBILENET_RESOLUTION:
260 - CM_DATASET_PREPROCESSED_IMAGENET_DEP_TAGS:
_resolution.260
- CM_ML_MODEL_IMAGE_HEIGHT:
- ENV variables:
_resolution-280- ENV variables:
- CM_ML_MODEL_IMAGE_HEIGHT:
280 - CM_ML_MODEL_IMAGE_WIDTH:
280 - CM_ML_MODEL_MOBILENET_RESOLUTION:
280 - CM_DATASET_PREPROCESSED_IMAGENET_DEP_TAGS:
_resolution.280
- CM_ML_MODEL_IMAGE_HEIGHT:
- ENV variables:
_resolution-300- ENV variables:
- CM_ML_MODEL_IMAGE_HEIGHT:
300 - CM_ML_MODEL_IMAGE_WIDTH:
300 - CM_ML_MODEL_MOBILENET_RESOLUTION:
300 - CM_DATASET_PREPROCESSED_IMAGENET_DEP_TAGS:
_resolution.300
- CM_ML_MODEL_IMAGE_HEIGHT:
- ENV variables:
Default variations
_fp32,_lite0,_resolution-224
Default environment
These keys can be updated via --env.KEY=VALUE or env dictionary in @input.json or using script flags.
- CM_ML_MODEL_INPUTS_DATA_TYPE:
fp32 - CM_ML_MODEL_PRECISION:
fp32 - CM_ML_MODEL_WEIGHTS_DATA_TYPE:
fp32
Script output
cmr "get ml-model efficientnet raw ml-model-efficientnet ml-model-efficientnet-lite lite tflite image-classification [variations]" -j