def predict(self, *predict_data):
"""
Generates output predictions for the input samples.
Data could be single tensor, or list of tensor, tuple of tensor.
Note:
Batch data should be put together in one tensor.
Args:
predict_data (Tensor): Tensor of predict data. can be array, list or tuple.
Returns:
Tensor, array(s) of predictions.
Examples:
>>> input_data = Tensor(np.random.randint(0, 255, [1, 3, 224, 224]), mindspore.float32)
>>> model = Model(Net())
>>> model.predict(input_data)
"""
self._predict_network.set_train(False)
check_input_data(*predict_data, data_class=Tensor)
result = self._predict_network(*predict_data)
check_output_data(result)
return result
def export(net, *inputs, file_name, file_format='AIR', **kwargs):
"""
Export the MindSpore prediction model to a file in the specified format.
Args:
net (Cell): MindSpore network.
inputs (Tensor): Inputs of the `net`.
file_name (str): File name of the model to be exported.
file_format (str): MindSpore currently supports 'AIR', 'ONNX' and 'MINDIR' format for exported model.
- AIR: Ascend Intermediate Representation. An intermediate representation format of Ascend model.
Recommended suffix for output file is '.air'.
- ONNX: Open Neural Network eXchange. An open format built to represent machine learning models.
Recommended suffix for output file is '.onnx'.
- MINDIR: MindSpore Native Intermediate Representation for Anf. An intermediate representation format
for MindSpore models.
Recommended suffix for output file is '.mindir'.
kwargs (dict): Configuration options dictionary.
- quant_mode: The mode of quant.
- mean: Input data mean. Default: 127.5.
- std_dev: Input data variance. Default: 127.5.
"""
logger.info("exporting model file:%s format:%s.", file_name, file_format)
check_input_data(*inputs, data_class=Tensor)
if not isinstance(file_name, str):
raise ValueError(
"Args file_name {} must be string, please check it".format(
file_name))
Validator.check_file_name_by_regular(file_name)
net = _quant_export(net, *inputs, file_format=file_format, **kwargs)
_export(net, file_name, file_format, *inputs)
def export(net, *inputs, file_name, file_format='GEIR'):
"""
Exports MindSpore predict model to file in specified format.
Args:
net (Cell): MindSpore network.
inputs (Tensor): Inputs of the `net`.
file_name (str): File name of model to export.
file_format (str): MindSpore currently supports 'GEIR', 'ONNX' 'LITE' and 'BINARY' format for exported model.
- GEIR: Graph Engine Intermidiate Representation. An intermidiate representation format of
Ascend model.
- ONNX: Open Neural Network eXchange. An open format built to represent machine learning models.
- LITE: Huawei model format for mobile. A lite model only for the MindSpore Lite
- BINARY: Binary format for model. An intermidiate representation format for models.
"""
logger.info("exporting model file:%s format:%s.", file_name, file_format)
check_input_data(*inputs, data_class=Tensor)
supported_formats = ['GEIR', 'ONNX', 'LITE', 'BINARY']
if file_format not in supported_formats:
raise ValueError(
f'Illegal file format {file_format}, it must be one of {supported_formats}'
)
# switch network mode to infer when it is training
is_training = net.training
if is_training:
net.set_train(mode=False)
# export model
if file_format == 'GEIR':
_executor.compile(net, *inputs, phase='export')
_executor.export(net, file_name, file_format)
elif file_format == 'ONNX': # file_format is 'ONNX'
# NOTICE: the pahse name `export_onnx` is used for judging whether is exporting onnx in the compile pipeline,
# do not change it to other values.
phase_name = 'export_onnx'
graph_id, _ = _executor.compile(net,
*inputs,
phase=phase_name,
do_convert=False)
onnx_stream = _executor._get_func_graph_proto(graph_id)
with open(file_name, 'wb') as f:
os.chmod(file_name, stat.S_IWUSR | stat.S_IRUSR)
f.write(onnx_stream)
elif file_format == 'BINARY': # file_format is 'BINARY'
phase_name = 'export_binary'
graph_id, _ = _executor.compile(net,
*inputs,
phase=phase_name,
do_convert=False)
onnx_stream = _executor._get_func_graph_proto(graph_id, 'binary_ir')
with open(file_name, 'wb') as f:
os.chmod(file_name, stat.S_IWUSR | stat.S_IRUSR)
f.write(onnx_stream)
elif file_format == 'LITE': # file_format is 'LITE'
context.set_context(save_ms_model=True, save_ms_model_path=file_name)
net(*inputs)
# restore network training mode
if is_training:
net.set_train(mode=True)
def _export(net, file_name, file_format, *inputs):
"""
It is an internal conversion function. Export the MindSpore prediction model to a file in the specified format.
"""
logger.info("exporting model file:%s format:%s.", file_name, file_format)
check_input_data(*inputs, data_class=Tensor)
if file_format == 'GEIR':
logger.warning(
f"Format 'GEIR' is deprecated, it would be removed in future release, use 'AIR' instead."
)
file_format = 'AIR'
supported_formats = ['AIR', 'ONNX', 'MINDIR']
if file_format not in supported_formats:
raise ValueError(
f'Illegal file format {file_format}, it must be one of {supported_formats}'
)
# When dumping ONNX file, switch network mode to infer when it is training(NOTE: ONNX only designed for prediction)
is_dump_onnx_in_training = net.training and file_format == 'ONNX'
if is_dump_onnx_in_training:
net.set_train(mode=False)
net.init_parameters_data()
if file_format == 'AIR':
phase_name = 'export.air'
graph_id, _ = _executor.compile(net, *inputs, phase=phase_name)
if not file_name.endswith('.air'):
file_name += ".air"
_executor.export(file_name, graph_id)
elif file_format == 'ONNX':
phase_name = 'export.onnx'
graph_id, _ = _executor.compile(net,
*inputs,
phase=phase_name,
do_convert=False)
onnx_stream = _executor._get_func_graph_proto(net, graph_id)
if not file_name.endswith('.onnx'):
file_name += ".onnx"
with open(file_name, 'wb') as f:
os.chmod(file_name, stat.S_IWUSR | stat.S_IRUSR)
f.write(onnx_stream)
elif file_format == 'MINDIR':
phase_name = 'export.mindir'
graph_id, _ = _executor.compile(net,
*inputs,
phase=phase_name,
do_convert=False)
onnx_stream = _executor._get_func_graph_proto(net, graph_id, 'mind_ir')
if not file_name.endswith('.mindir'):
file_name += ".mindir"
with open(file_name, 'wb') as f:
os.chmod(file_name, stat.S_IWUSR | stat.S_IRUSR)
f.write(onnx_stream)
if is_dump_onnx_in_training:
net.set_train(mode=True)
def export(net, *inputs, file_name, file_format='AIR'):
"""
Export the MindSpore prediction model to a file in the specified format.
Args:
net (Cell): MindSpore network.
inputs (Tensor): Inputs of the `net`.
file_name (str): File name of the model to be exported.
file_format (str): MindSpore currently supports 'AIR', 'ONNX' and 'MINDIR' format for exported model.
- AIR: Ascend Intermidiate Representation. An intermidiate representation format of Ascend model.
Recommended suffix for output file is '.air'.
- ONNX: Open Neural Network eXchange. An open format built to represent machine learning models.
Recommended suffix for output file is '.onnx'.
- MINDIR: MindSpore Native Intermidiate Representation for Anf. An intermidiate representation format
for MindSpore models.
Recommended suffix for output file is '.mindir'.
"""
logger.info("exporting model file:%s format:%s.", file_name, file_format)
check_input_data(*inputs, data_class=Tensor)
if file_format == 'GEIR':
logger.warning(f"Format 'GEIR' is deprecated, it would be removed in future release, use 'AIR' instead.")
file_format = 'AIR'
supported_formats = ['AIR', 'ONNX', 'MINDIR']
if file_format not in supported_formats:
raise ValueError(f'Illegal file format {file_format}, it must be one of {supported_formats}')
# When dumping ONNX file, switch network mode to infer when it is training(NOTE: ONNX only designed for prediction)
is_dump_onnx_in_training = net.training and file_format == 'ONNX'
if is_dump_onnx_in_training:
net.set_train(mode=False)
# export model
net.init_parameters_data()
if file_format == 'AIR':
phase_name = 'export.air'
graph_id, _ = _executor.compile(net, *inputs, phase=phase_name)
_executor.export(file_name, graph_id)
elif file_format == 'ONNX': # file_format is 'ONNX'
phase_name = 'export.onnx'
graph_id, _ = _executor.compile(net, *inputs, phase=phase_name, do_convert=False)
onnx_stream = _executor._get_func_graph_proto(graph_id)
with open(file_name, 'wb') as f:
os.chmod(file_name, stat.S_IWUSR | stat.S_IRUSR)
f.write(onnx_stream)
elif file_format == 'MINDIR': # file_format is 'MINDIR'
phase_name = 'export.mindir'
graph_id, _ = _executor.compile(net, *inputs, phase=phase_name, do_convert=False)
onnx_stream = _executor._get_func_graph_proto(graph_id, 'mind_ir')
with open(file_name, 'wb') as f:
os.chmod(file_name, stat.S_IWUSR | stat.S_IRUSR)
f.write(onnx_stream)
# restore network training mode
if is_dump_onnx_in_training:
net.set_train(mode=True)
