get-ml-model-mobilenet
Automatically generated README for this automation recipe: get-ml-model-mobilenet
Category: AI/ML models
License: Apache 2.0
-
Notes from the authors, contributors and users: README-extra
-
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 mobilenet raw ml-model-mobilenet image-classification" --help
Run this script
Run this script via CLI
cm run script --tags=get,ml-model,mobilenet,raw,ml-model-mobilenet,image-classification[,variations]
Run this script via CLI (alternative)
cmr "get ml-model mobilenet raw ml-model-mobilenet image-classification [variations]"
Run this script from Python
import cmind
r = cmind.access({'action':'run'
'automation':'script',
'tags':'get,ml-model,mobilenet,raw,ml-model-mobilenet,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 mobilenet raw ml-model-mobilenet image-classification[variations]"
Variations
-
No group (any combination of variations can be selected)
Click here to expand this section.
_tflite
-
Group "framework"
Click here to expand this section.
_onnx- ENV variables:
- CM_ML_MODEL_DATA_LAYOUT:
NCHW - CM_ML_MODEL_FRAMEWORK:
onnx
- CM_ML_MODEL_DATA_LAYOUT:
- ENV variables:
_tf(default)- ENV variables:
- CM_ML_MODEL_DATA_LAYOUT:
NHWC - CM_ML_MODEL_NORMALIZE_DATA:
yes - CM_ML_MODEL_SUBTRACT_MEANS:
no - CM_ML_MODEL_INPUT_LAYER_NAME:
input
- CM_ML_MODEL_DATA_LAYOUT:
- ENV variables:
-
Group "kind"
Click here to expand this section.
_large- ENV variables:
- CM_ML_MODEL_MOBILENET_KIND:
large
- CM_ML_MODEL_MOBILENET_KIND:
- ENV variables:
_large-minimalistic- ENV variables:
- CM_ML_MODEL_MOBILENET_KIND:
large-minimalistic
- CM_ML_MODEL_MOBILENET_KIND:
- ENV variables:
_small- ENV variables:
- CM_ML_MODEL_MOBILENET_KIND:
small
- CM_ML_MODEL_MOBILENET_KIND:
- ENV variables:
_small-minimalistic- ENV variables:
- CM_ML_MODEL_MOBILENET_KIND:
small-minimalistic
- CM_ML_MODEL_MOBILENET_KIND:
- ENV variables:
-
Group "multiplier"
Click here to expand this section.
_multiplier-0.25- ENV variables:
- CM_ML_MODEL_MOBILENET_MULTIPLIER:
0.25 - CM_ML_MODEL_MOBILENET_MULTIPLIER_PERCENTAGE:
25
- CM_ML_MODEL_MOBILENET_MULTIPLIER:
- ENV variables:
_multiplier-0.35- ENV variables:
- CM_ML_MODEL_MOBILENET_MULTIPLIER:
0.35 - CM_ML_MODEL_MOBILENET_MULTIPLIER_PERCENTAGE:
35
- CM_ML_MODEL_MOBILENET_MULTIPLIER:
- ENV variables:
_multiplier-0.5- ENV variables:
- CM_ML_MODEL_MOBILENET_MULTIPLIER:
0.5 - CM_ML_MODEL_MOBILENET_MULTIPLIER_PERCENTAGE:
50
- CM_ML_MODEL_MOBILENET_MULTIPLIER:
- ENV variables:
_multiplier-0.75- ENV variables:
- CM_ML_MODEL_MOBILENET_MULTIPLIER:
0.75 - CM_ML_MODEL_MOBILENET_MULTIPLIER_PERCENTAGE:
75
- CM_ML_MODEL_MOBILENET_MULTIPLIER:
- ENV variables:
_multiplier-1.0- ENV variables:
- CM_ML_MODEL_MOBILENET_MULTIPLIER:
1.0 - CM_ML_MODEL_MOBILENET_MULTIPLIER_PERCENTAGE:
100
- CM_ML_MODEL_MOBILENET_MULTIPLIER:
- ENV variables:
-
Group "opset-version"
Click here to expand this section.
_opset-11- ENV variables:
- CM_ML_MODEL_ONNX_OPSET:
11
- CM_ML_MODEL_ONNX_OPSET:
- ENV variables:
_opset-8- ENV variables:
- CM_ML_MODEL_ONNX_OPSET:
8
- CM_ML_MODEL_ONNX_OPSET:
- ENV variables:
-
Group "precision"
Click here to expand this section.
_fp32(default)- ENV variables:
- CM_ML_MODEL_INPUTS_DATA_TYPE:
fp32 - CM_ML_MODEL_PRECISION:
fp32 - CM_ML_MODEL_WEIGHTS_DATA_TYPE:
fp32 - CM_ML_MODEL_MOBILENET_PRECISION:
float
- CM_ML_MODEL_INPUTS_DATA_TYPE:
- ENV variables:
_int8- ENV variables:
- CM_ML_MODEL_INPUTS_DATA_TYPE:
int8 - CM_ML_MODEL_PRECISION:
int8 - CM_ML_MODEL_WEIGHTS_DATA_TYPE:
int8 - CM_ML_MODEL_MOBILENET_PRECISION:
int8
- CM_ML_MODEL_INPUTS_DATA_TYPE:
- ENV variables:
_uint8- ENV variables:
- CM_ML_MODEL_INPUTS_DATA_TYPE:
uint8 - CM_ML_MODEL_PRECISION:
uint8 - CM_ML_MODEL_WEIGHTS_DATA_TYPE:
uint8 - CM_ML_MODEL_MOBILENET_PRECISION:
uint8
- CM_ML_MODEL_INPUTS_DATA_TYPE:
- ENV variables:
-
Group "resolution"
Click here to expand this section.
_resolution-128- ENV variables:
- CM_ML_MODEL_MOBILENET_RESOLUTION:
128 - CM_ML_MODEL_IMAGE_HEIGHT:
128 - CM_ML_MODEL_IMAGE_WIDTH:
128 - CM_DATASET_PREPROCESSED_IMAGENET_DEP_TAGS:
_resolution.128
- CM_ML_MODEL_MOBILENET_RESOLUTION:
- ENV variables:
_resolution-160- ENV variables:
- CM_ML_MODEL_MOBILENET_RESOLUTION:
160 - CM_ML_MODEL_IMAGE_HEIGHT:
160 - CM_ML_MODEL_IMAGE_WIDTH:
160 - CM_DATASET_PREPROCESSED_IMAGENET_DEP_TAGS:
_resolution.160
- CM_ML_MODEL_MOBILENET_RESOLUTION:
- ENV variables:
_resolution-192- ENV variables:
- CM_ML_MODEL_MOBILENET_RESOLUTION:
192 - CM_ML_MODEL_IMAGE_HEIGHT:
192 - CM_ML_MODEL_IMAGE_WIDTH:
192 - CM_DATASET_PREPROCESSED_IMAGENET_DEP_TAGS:
_resolution.192
- CM_ML_MODEL_MOBILENET_RESOLUTION:
- ENV variables:
_resolution-224- ENV variables:
- CM_ML_MODEL_MOBILENET_RESOLUTION:
224 - CM_ML_MODEL_IMAGE_HEIGHT:
224 - CM_ML_MODEL_IMAGE_WIDTH:
224 - CM_DATASET_PREPROCESSED_IMAGENET_DEP_TAGS:
_resolution.224
- CM_ML_MODEL_MOBILENET_RESOLUTION:
- ENV variables:
-
Group "source"
Click here to expand this section.
_from.google- ENV variables:
- CM_DOWNLOAD_SOURCE:
google
- CM_DOWNLOAD_SOURCE:
- ENV variables:
_from.zenodo- ENV variables:
- CM_DOWNLOAD_SOURCE:
zenodo
- CM_DOWNLOAD_SOURCE:
- ENV variables:
-
Group "version"
Click here to expand this section.
_v1- ENV variables:
- CM_ML_MODEL_MOBILENET_VERSION:
1 - CM_ML_MODEL_FULL_NAME:
mobilenet-v1-precision_<<<CM_ML_MODEL_MOBILENET_PRECISION>>>-<<<CM_ML_MODEL_MOBILENET_MULTIPLIER>>>-<<<CM_ML_MODEL_MOBILENET_RESOLUTION>>>
- CM_ML_MODEL_MOBILENET_VERSION:
- ENV variables:
_v2- ENV variables:
- CM_ML_MODEL_MOBILENET_VERSION:
2 - CM_ML_MODEL_VER:
2 - CM_ML_MODEL_FULL_NAME:
mobilenet-v2-precision_<<<CM_ML_MODEL_MOBILENET_PRECISION>>>-<<<CM_ML_MODEL_MOBILENET_MULTIPLIER>>>-<<<CM_ML_MODEL_MOBILENET_RESOLUTION>>>
- CM_ML_MODEL_MOBILENET_VERSION:
- ENV variables:
_v3(default)- ENV variables:
- CM_ML_MODEL_MOBILENET_VERSION:
3 - CM_ML_MODEL_VER:
3 - CM_ML_MODEL_FULL_NAME:
mobilenet-v3-precision_<<<CM_ML_MODEL_MOBILENET_PRECISION>>>-<<<CM_ML_MODEL_MOBILENET_KIND>>>-<<<CM_ML_MODEL_MOBILENET_RESOLUTION>>>
- CM_ML_MODEL_MOBILENET_VERSION:
- ENV variables:
Default variations
_fp32,_tf,_v3
Default environment
These keys can be updated via --env.KEY=VALUE or env dictionary in @input.json or using script flags.
- CM_ML_MODEL:
mobilenet - CM_ML_MODEL_DATASET:
imagenet2012-val - CM_ML_MODEL_RETRAINING:
no - CM_ML_MODEL_WEIGHT_TRANSFORMATIONS:
no - CM_ML_MODEL_INPUTS_DATA_TYPE:
fp32 - CM_ML_MODEL_WEIGHTS_DATA_TYPE:
fp32 - CM_ML_MODEL_MOBILENET_NAME_SUFFIX: ``
Script output
cmr "get ml-model mobilenet raw ml-model-mobilenet image-classification [variations]" -j