def train(self, to_static=False):
prog_trans = ProgramTranslator()
prog_trans.enable(to_static)
with fluid.dygraph.guard(PLACE):
net = NetWithDictPop()
ret = net(z=0, x=self.x, y=True)
return ret.numpy()
def _run(self, to_static):
prog_trans = ProgramTranslator()
prog_trans.enable(to_static)
result = self.dygraph_func(self.input)
return result.numpy()
def train(self, to_static=False):
prog_trans = ProgramTranslator()
prog_trans.enable(to_static)
with fluid.dygraph.guard(PLACE):
net = MainNetWithDict(batch_size=self.batch_size)
ret = net(self.x)
return ret.numpy()
def _run(self, mode, to_static):
prog_trans = ProgramTranslator()
prog_trans.enable(to_static)
net = self.Net(mode)
ret = net(self.x, self.y)
return ret.numpy()
def test_export_deploy_model(self):
for dynamic in [True, False]:
fluid.enable_dygraph() if dynamic else None
# paddle.disable_static() if dynamic else None
prog_translator = ProgramTranslator()
prog_translator.enable(False) if not dynamic else None
net = LeNetDeclarative()
inputs = [InputSpec([None, 1, 28, 28], 'float32', 'x')]
model = Model(net, inputs)
model.prepare()
save_dir = tempfile.mkdtemp()
if not os.path.exists(save_dir):
os.makedirs(save_dir)
tensor_img = np.array(np.random.random((1, 1, 28, 28)),
dtype=np.float32)
ori_results = model.test_batch(tensor_img)
model.save(save_dir, training=False)
fluid.disable_dygraph() if dynamic else None
place = fluid.CPUPlace(
) if not fluid.is_compiled_with_cuda() else fluid.CUDAPlace(0)
new_scope = fluid.Scope()
with fluid.scope_guard(new_scope):
exe = fluid.Executor(place)
[inference_program, feed_target_names, fetch_targets
] = (fluid.io.load_inference_model(dirname=save_dir,
executor=exe))
results = exe.run(inference_program,
feed={feed_target_names[0]: tensor_img},
fetch_list=fetch_targets)
np.testing.assert_allclose(results,
ori_results,
rtol=1e-5,
atol=1e-7)
shutil.rmtree(save_dir)
def _run(self, to_static=False):
prog_trans = ProgramTranslator()
prog_trans.enable(to_static)
with fluid.dygraph.guard(place):
net = self.Net()
x_v = fluid.dygraph.to_variable(self.x)
ret = net(x_v)
return ret.numpy()
