Page History

...

For example,

•  Gluon

mx.gluon.import_from(input_file)

mx.gluon.export_to(format=’onnx’, filename_prefix=”model_name”)

...

sym, params = mx.mod.Module.import_from(input_file, in_format=‘onnx’)

mx.mod.Module.export_to(format=‘onnx’, filename_prefix=”model_name”)

...

# This will internally call serde package API `serde.export`
mx.mod.Module.export_to(sym, params, format=‘onnx’, filename=”model.onnx”)

# OR save into different format using module directly

mx.mod.Module.export_to(format=‘onnx’, filename=”model.onnx”)

...

sym, params = mxnet.mod.Module.import_from(input_file, in_format=‘onnx’)

# create module for inference
mod = mx.mod.Module(symbol=sym, data_names=..., context=mx.cpu(), label_names=None)
mod.bind(for_training=False, data_shapes=..., label_shapes=None)

# set parameters
mod.set_params(arg_params=params, aux_params=None, allow_missing=True)

# forward on the provided data batch
mod.forward(Batch([data_batch]))

...