def __call__(self, inputs):
with scope_guard(self._scope):
if self._compiled_program is None:
self._compile()
return self._run(self._build_feed(inputs))
def save_inference_model(self, dirname, feed=None, fetch=None):
"""
Save the TracedLayer to a model for inference. The saved
inference model can be loaded by C++ inference APIs.
Args:
dirname (str): the directory to save the inference model.
feed (list[int], optional): the input variable indices of the saved
inference model. If None, all input variables of the
TracedLayer object would be the inputs of the saved inference
model. Default None.
fetch (list[int], optional): the output variable indices of the
saved inference model. If None, all output variables of the
TracedLayer object would be the outputs of the saved inference
model. Default None.
Returns:
None
Examples:
.. code-block:: python:
import paddle.fluid as fluid
from paddle.fluid.dygraph import Linear, to_variable, TracedLayer
import numpy as np
class ExampleLayer(fluid.dygraph.Layer):
def __init__(self):
super(ExampleLayer, self).__init__()
self._fc = Linear(3, 10)
def forward(self, input):
return self._fc(input)
save_dirname = './saved_infer_model'
in_np = np.random.random([2, 3]).astype('float32')
with fluid.dygraph.guard():
layer = ExampleLayer()
in_var = to_variable(in_np)
out_dygraph, static_layer = TracedLayer.trace(layer, inputs=[in_var])
static_layer.save_inference_model(save_dirname, feed=[0], fetch=[0])
place = fluid.CPUPlace()
exe = fluid.Executor(place)
program, feed_vars, fetch_vars = fluid.io.load_inference_model(save_dirname,
exe)
fetch, = exe.run(program, feed={feed_vars[0]: in_np}, fetch_list=fetch_vars)
print(fetch.shape) # (2, 10)
"""
from paddle.fluid.io import save_inference_model
def get_feed_fetch(all_vars, partial_vars):
if partial_vars is None:
return all_vars
return [all_vars[idx] for idx in partial_vars]
with scope_guard(self._scope):
feeded_var_names = get_feed_fetch(self._feed_names, feed)
target_var_names = get_feed_fetch(self._fetch_names, fetch)
target_vars = []
for name in target_var_names:
target_var = self._program.global_block().vars.get(name, None)
assert target_var is not None, "{} cannot be found".format(name)
target_vars.append(target_var)
save_inference_model(
dirname=dirname,
feeded_var_names=feeded_var_names,
target_vars=target_vars,
executor=self._exe,
main_program=self._program.clone())
def save_inference_model(self, dirname, feed=None, fetch=None):
"""
Save the TracedLayer to an model for inference. The saved
inference model can be loaded by C++ inference APIs.
Args:
dirname (str): the directory to save the inference model.
feed (list[int], optional): the input variable indices of the saved
inference model. If None, all input variables of the
TracedLayer object would be the inputs of the saved inference
model. Default None.
fetch (list[int], optional): the output variable indices of the
saved inference model. If None, all output variables of the
TracedLayer object would be the outputs of the saved inference
model. Default None.
Returns:
The fetch variables' name list
Return Type:
list(str)
Examples:
.. code-block:: python:
import paddle.fluid as fluid
from paddle.fluid.dygraph import FC, to_variable, TracedLayer
import paddle.fluid.dygraph.jit as jit
import numpy as np
class ExampleLayer(fluid.dygraph.Layer):
def __init__(self, name_scope):
super(ExampleLayer, self).__init__(name_scope)
self._fc = FC(self.full_name(), 10)
def forward(self, input):
return self._fc(input)
with fluid.dygraph.guard():
layer = ExampleLayer("example_layer")
in_np = np.random.random([2, 3]).astype('float32')
in_var = to_variable(in_np)
out_dygraph, static_layer = TracedLayer.trace(layer, inputs=[in_var])
static_layer.save_inference_model('./saved_infer_model')
"""
def get_feed_fetch(all_vars, partial_vars):
if partial_vars is None:
return all_vars
return [all_vars[idx] for idx in partial_vars]
with scope_guard(self._scope):
feeded_var_names = get_feed_fetch(self._feed_names, feed)
target_var_names = get_feed_fetch(self._fetch_names, fetch)
target_vars = []
for name in target_var_names:
target_var = self._program.global_block().vars.get(name, None)
assert target_var is not None, "{} cannot be found".format(
name)
target_vars.append(target_var)
return fluid_io.save_inference_model(
dirname=dirname,
feeded_var_names=feeded_var_names,
target_vars=target_vars,
executor=self._exe,
main_program=self._program.clone())