IntenseWebs/openvino
3
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Replace 'quantized' with 'compressed' in MO help (#7607)

Browse Source 
* Replace 'quantized' with 'compressed' in MO help

Signed-off-by: Andrei Kochin <andrei.kochin@intel.com>

* Add UG changes to reflect new help text

Signed-off-by: Andrei Kochin <andrei.kochin@intel.com>
This commit is contained in:
Andrei Kochin 2021-09-24 13:34:09 +03:00 committed by GitHub
parent ce9a229313
commit 0efc1a0763
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
docs/MO_DG/prepare_model/convert_model/Converting_Model_General.md
View File

@ -99,7 +99,7 @@ Framework-agnostic parameters:
--data_type {FP16,FP32,half,float} --data_type {FP16,FP32,half,float}
Data type for all intermediate tensors and weights. If Data type for all intermediate tensors and weights. If
original model is in FP32 and --data_type=FP16 is original model is in FP32 and --data_type=FP16 is
specified, all model weights and biases are quantized specified, all model weights and biases are compressed
to FP16. to FP16.
--disable_fusing Turn off fusing of linear operations to Convolution --disable_fusing Turn off fusing of linear operations to Convolution
--disable_resnet_optimization --disable_resnet_optimization

2
model-optimizer/mo/utils/cli_parser.py
View File

@ -275,7 +275,7 @@ def get_common_cli_parser(parser: argparse.ArgumentParser = None):
common_group.add_argument('--data_type', common_group.add_argument('--data_type',
help='Data type for all intermediate tensors and weights. ' + help='Data type for all intermediate tensors and weights. ' +
'If original model is in FP32 and --data_type=FP16 is specified, all model weights ' + 'If original model is in FP32 and --data_type=FP16 is specified, all model weights ' +
'and biases are quantized to FP16.', 'and biases are compressed to FP16.',
choices=["FP16", "FP32", "half", "float"], choices=["FP16", "FP32", "half", "float"],
default='float') default='float')
common_group.add_argument('--transform', common_group.add_argument('--transform',