def test_initial_states_type():
cell = GRUCell(hidden_size, name="GRUCell_for_rnn")
error_initial_states = np.random.random(
(batch_size, hidden_size)).astype("float32")
dynamic_rnn(cell=cell,
inputs=inputs_dynamic_rnn,
initial_states=error_initial_states,
sequence_length=sequence_length,
is_reverse=False)
def test_run(self):
inputs = fluid.data(name='inputs',
shape=[None, self.input_size],
dtype='float32')
pre_hidden = layers.data(name='pre_hidden',
shape=[None, self.hidden_size],
append_batch_size=False,
dtype='float32')
cell = GRUCell(self.hidden_size)
gru_hidden_new, _ = cell(inputs, pre_hidden)
gru_unit = contrib.layers.rnn_impl.BasicGRUUnit(
"basicGRU", self.hidden_size, None, None, None, None, "float32")
gru_hidden = gru_unit(inputs, pre_hidden)
if core.is_compiled_with_cuda():
place = core.CUDAPlace(0)
else:
place = core.CPUPlace()
exe = Executor(place)
exe.run(framework.default_startup_program())
inputs_np = np.random.uniform(
-0.1, 0.1, (self.batch_size, self.input_size)).astype('float32')
pre_hidden_np = np.random.uniform(
-0.1, 0.1, (self.batch_size, self.hidden_size)).astype('float32')
param_names = [
["GRUCell/BasicGRUUnit_0.w_0", "basicGRU/BasicGRUUnit_0.w_0"],
["GRUCell/BasicGRUUnit_0.w_1", "basicGRU/BasicGRUUnit_0.w_1"],
["GRUCell/BasicGRUUnit_0.b_0", "basicGRU/BasicGRUUnit_0.b_0"],
["GRUCell/BasicGRUUnit_0.b_1", "basicGRU/BasicGRUUnit_0.b_1"]
]
for names in param_names:
param = np.array(fluid.global_scope().find_var(
names[0]).get_tensor())
param = np.random.uniform(-0.1, 0.1,
size=param.shape).astype('float32')
fluid.global_scope().find_var(names[0]).get_tensor().set(
param, place)
fluid.global_scope().find_var(names[1]).get_tensor().set(
param, place)
out = exe.run(feed={
'inputs': inputs_np,
'pre_hidden': pre_hidden_np
},
fetch_list=[gru_hidden_new, gru_hidden])
self.assertTrue(np.allclose(out[0], out[1], rtol=1e-4, atol=0))
def test_errors(self):
with program_guard(Program(), Program()):
batch_size, input_size, hidden_size = 4, 16, 16
inputs = fluid.data(
name='inputs', shape=[None, input_size], dtype='float32')
pre_hidden = layers.data(
name='pre_hidden',
shape=[None, hidden_size],
append_batch_size=False,
dtype='float32')
cell = GRUCell(hidden_size)
def test_input_Variable():
np_input = np.random.random(
(batch_size, input_size)).astype("float32")
cell(np_input, pre_hidden)
self.assertRaises(TypeError, test_input_Variable)
def test_pre_hidden_Variable():
np_pre_hidden = np.random.random(
(batch_size, hidden_size)).astype("float32")
cell(inputs, np_pre_hidden)
self.assertRaises(TypeError, test_pre_hidden_Variable)
def test_input_type():
error_inputs = fluid.data(
name='error_inputs',
shape=[None, input_size],
dtype='int32')
cell(error_inputs, pre_hidden)
self.assertRaises(TypeError, test_input_type)
def test_pre_hidden_type():
error_pre_hidden = fluid.data(
name='error_pre_hidden',
shape=[None, hidden_size],
dtype='int32')
cell(inputs, error_pre_hidden)
self.assertRaises(TypeError, test_pre_hidden_type)
def test_dtype():
# the input type must be Variable
GRUCell(hidden_size, dtype="int32")
self.assertRaises(TypeError, test_dtype)
def test_dtype():
# the input type must be Variable
GRUCell(hidden_size, dtype="int32")