def check_grad_with_place(self,
place,
inputs_to_check,
output_names,
no_grad_set=None,
numeric_grad_delta=0.005,
in_place=False,
max_relative_error=0.005,
user_defined_grads=None,
check_dygraph=True,
transpose_input_list=[]):
self.scope = core.Scope()
op_inputs = self.inputs if hasattr(self, "inputs") else dict()
op_outputs = self.outputs if hasattr(self, "outputs") else dict()
op_attrs = self.attrs if hasattr(self, "attrs") else dict()
self._check_grad_helper()
cache_list = None
if hasattr(self, "cache_name_list"):
cache_list = self.cache_name_list
self.op = create_op(self.scope,
self.op_type,
op_inputs,
op_outputs,
op_attrs,
cache_list=cache_list)
if no_grad_set is None:
no_grad_set = set()
for input_to_check in inputs_to_check:
set_input(self.scope, self.op, self.inputs, place)
tensor_to_check = self.scope.find_var(input_to_check).get_tensor()
tensor_size = six.moves.reduce(lambda a, b: a * b,
tensor_to_check.shape(), 1)
if tensor_size < 100:
self.__class__.input_shape_is_large = False
if not type(output_names) is list:
output_names = [output_names]
numeric_grads = user_defined_grads or [
self.get_numeric_gradient(
place,
self.scope,
self.op,
self.inputs,
input_to_check,
output_names,
delta=numeric_grad_delta,
in_place=in_place,
transpose_input_list=transpose_input_list)
for input_to_check in inputs_to_check
]
analytic_grads = self._get_gradient(inputs_to_check, place,
output_names, no_grad_set)
self._assert_is_close(numeric_grads, analytic_grads, inputs_to_check,
max_relative_error,
"Gradient Check On %s" % str(place))
def check_grad_with_place(self,
place,
inputs_to_check,
output_names,
no_grad_set=None,
numeric_grad_delta=0.005,
in_place=False,
max_relative_error=0.005,
user_defined_grads=None):
self.scope = core.Scope()
op_inputs = self.inputs if hasattr(self, "inputs") else dict()
op_outputs = self.outputs if hasattr(self, "outputs") else dict()
op_attrs = self.attrs if hasattr(self, "attrs") else dict()
cache_list = None
if hasattr(self, "cache_name_list"):
cache_list = self.cache_name_list
self.op = create_op(self.scope,
self.op_type,
op_inputs,
op_outputs,
op_attrs,
cache_list=cache_list)
if no_grad_set is None:
no_grad_set = set()
if not type(output_names) is list:
output_names = [output_names]
numeric_grads = user_defined_grads or [
get_numeric_gradient(place,
self.scope,
self.op,
self.inputs,
input_to_check,
output_names,
delta=numeric_grad_delta,
in_place=in_place)
for input_to_check in inputs_to_check
]
analytic_grads = self._get_gradient(inputs_to_check, place,
output_names, no_grad_set)
self._assert_is_close(numeric_grads, analytic_grads, inputs_to_check,
max_relative_error,
"Gradient Check On %s" % str(place))
def do_compare_between_place(self):
if not core.is_compiled_with_cuda(): return
place = core.CPUPlace()
place2 = core.CUDAPlace(0)
self.scope = core.Scope()
op_inputs = self.inputs if hasattr(self, "inputs") else dict()
op_outputs = self.outputs if hasattr(self, "outputs") else dict()
op_attrs = self.attrs if hasattr(self, "attrs") else dict()
self.op = create_op(self.scope, self.op_type, op_inputs, op_outputs,
op_attrs)
inputs_to_check = set(['X', 'Scale', 'Bias'])
output_names = 'Y'
cpu_grads = self._get_gradient(inputs_to_check, place, output_names,
None)
gpu_grads = self._get_gradient(inputs_to_check, place2, output_names,
None)
self._assert_is_close(cpu_grads, gpu_grads, inputs_to_check, 0.005,
"Gradient Check On %s" % str(place))
def get_grad_with_place(self,
place,
inputs_to_check,
output_names,
no_grad_set=None,
numeric_grad_delta=0.005,
in_place=False,
max_relative_error=0.005,
user_defined_grads=None,
check_dygraph=True):
self.scope = core.Scope()
op_inputs = self.inputs if hasattr(self, "inputs") else dict()
op_outputs = self.outputs if hasattr(self, "outputs") else dict()
op_attrs = self.attrs if hasattr(self, "attrs") else dict()
self._check_grad_helper()
if self.dtype == np.float64 and \
self.op_type not in op_threshold_white_list.NEED_FIX_FP64_CHECK_GRAD_THRESHOLD_OP_LIST:
numeric_grad_delta = 1e-5
max_relative_error = 1e-7
cache_list = None
if hasattr(self, "cache_name_list"):
cache_list = self.cache_name_list
# oneDNN numeric gradient should use CPU kernel
use_onednn = False
if "use_mkldnn" in op_attrs and op_attrs["use_mkldnn"] == True:
op_attrs["use_mkldnn"] = False
use_onednn = True
self.op = create_op(
self.scope,
self.op_type,
op_inputs,
op_outputs,
op_attrs,
cache_list=cache_list)
if use_onednn:
op_attrs["use_mkldnn"] = True
if no_grad_set is None:
no_grad_set = set()
else:
if (self.op_type not in no_grad_set_white_list.NEED_TO_FIX_OP_LIST
) and (
self.op_type not in no_grad_set_white_list.NOT_CHECK_OP_LIST
) and (not self.is_bfloat16_op()):
raise AssertionError("no_grad_set must be None, op_type is " +
self.op_type + " Op.")
for input_to_check in inputs_to_check:
set_input(self.scope, self.op, self.inputs, place)
tensor_to_check = self.scope.find_var(input_to_check).get_tensor()
tensor_size = six.moves.reduce(lambda a, b: a * b,
tensor_to_check.shape(), 1)
if tensor_size < 100:
self.__class__.input_shape_is_large = False
if not type(output_names) is list:
output_names = [output_names]
analytic_grads = self._get_gradient(inputs_to_check, place,
output_names, no_grad_set)
return analytic_grads
def check_grad_with_place(self,
place,
inputs_to_check,
output_names,
no_grad_set=None,
numeric_grad_delta=0.005,
in_place=False,
max_relative_error=0.005,
user_defined_grads=None,
check_dygraph=True):
self.scope = core.Scope()
op_inputs = self.inputs if hasattr(self, "inputs") else dict()
op_outputs = self.outputs if hasattr(self, "outputs") else dict()
op_attrs = self.attrs if hasattr(self, "attrs") else dict()
prog = Program()
block = prog.global_block()
op_init = block.append_op(
type="mpc_init",
#inputs=inputs,
#outputs=outputs,
attrs={"protocol_name": "privc"})
op_init.desc.infer_shape(block.desc)
mpc_protocol_index = MpcProtocols["PRIVC"].value
fluid.global_scope().var("mpc_protocol_index").get_tensor().set(
np.array((mpc_protocol_index)), fluid.CPUPlace())
self._check_grad_helper()
cache_list = None
if hasattr(self, "cache_name_list"):
cache_list = self.cache_name_list
self.op = create_op(self.scope,
self.op_type,
op_inputs,
op_outputs,
op_attrs,
cache_list=cache_list)
if no_grad_set is None:
no_grad_set = set()
for input_to_check in inputs_to_check:
set_input(self.scope, self.op, self.inputs, place)
tensor_to_check = self.scope.find_var(input_to_check).get_tensor()
tensor_size = six.moves.reduce(lambda a, b: a * b,
tensor_to_check.shape(), 1)
if tensor_size < 100:
self.__class__.input_shape_is_large = False
if not type(output_names) is list:
output_names = [output_names]
numeric_grads = user_defined_grads or [
self.get_numeric_gradient(place,
self.scope,
self.op,
self.inputs,
input_to_check,
output_names,
delta=numeric_grad_delta,
in_place=in_place)
for input_to_check in inputs_to_check
]
analytic_grads = self._get_gradient(inputs_to_check, place,
output_names, no_grad_set)
self._assert_is_close(numeric_grads, analytic_grads, inputs_to_check,
max_relative_error,
"Gradient Check On %s" % str(place))
