module cli.optimize
#
Short summary#
module mlprodict.cli.optimize
Command line about model optimisation.
Functions#
function |
truncated documentation |
---|---|
Optimizes an ONNX model. |
|
Computes statistics on an ONNX model. |
Documentation#
Command line about model optimisation.
- mlprodict.cli.optimize.onnx_optim(name, outfile=None, recursive=True, options=None, verbose=0, fLOG=None)#
Optimizes an ONNX model.
- Parameters:
name – filename
outfile – output filename
recursive – processes the main graph and the subgraphs
options – options, kind of optimize to do
verbose – display statistics before and after the optimisation
fLOG – logging function
Optimizes an ONNX graph
The command optimizes an ONNX model.
<<<
python -m mlprodict onnx_optim --help
>>>
usage: onnx_optim [-h] [-n NAME] [-o OUTFILE] [-r RECURSIVE] [-op OPTIONS] [-v VERBOSE] Optimizes an ONNX model. optional arguments: -h, --help show this help message and exit -n NAME, --name NAME filename (default: None) -o OUTFILE, --outfile OUTFILE output filename (default: ) -r RECURSIVE, --recursive RECURSIVE processes the main graph and the subgraphs (default: True) -op OPTIONS, --options OPTIONS options, kind of optimize to do (default: ) -v VERBOSE, --verbose VERBOSE display statistics before and after the optimisation (default: 0)
- mlprodict.cli.optimize.onnx_stats(name, optim=False, kind=None)#
Computes statistics on an ONNX model.
- Parameters:
name – filename
optim – computes statistics before an after optimisation was done
kind – kind of statistics, if left unknown, prints out the metadata, possible values: * io: prints input and output name, type, shapes * node: prints the distribution of node types * text: printts a text summary
Computes statistics on an ONNX graph
The command computes statistics on an ONNX model.
<<<
python -m mlprodict onnx_stats --help
>>>
usage: onnx_stats [-h] [-n NAME] [-o OPTIM] [-k KIND] Computes statistics on an ONNX model. optional arguments: -h, --help show this help message and exit -n NAME, --name NAME filename (default: None) -o OPTIM, --optim OPTIM computes statistics before an after optimisation was done (default: False) -k KIND, --kind KIND kind of statistics, if left unknown, prints out the metadata, possible values: * `io`: prints input and output name, type, shapes * `node`: prints the distribution of node types * `text`: printts a text summary (default: )