Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

【Hackathon 6th No.26】API improvement for nn.initializer.XavierNormal and nn.initializer.XavierUniform 易用性提升 #63134

Merged
merged 3 commits into from
Apr 3, 2024
Merged

【Hackathon 6th No.26】API improvement for nn.initializer.XavierNormal and nn.initializer.XavierUniform 易用性提升 #63134

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
b6482b6
add param gain to xavier
NKNaN Mar 31, 2024
fefccb0
fix test
NKNaN Apr 1, 2024
0e0ca61
fix test
NKNaN Apr 1, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
40 changes: 25 additions & 15 deletions python/paddle/nn/initializer/xavier.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -41,14 +41,14 @@ class XavierInitializer(Initializer):

.. math::

x = \sqrt{\\frac{6.0}{fan\_in + fan\_out}}
x = gain \times \sqrt{\\frac{6.0}{fan\_in + fan\_out}}

In case of Normal distribution, the mean is 0 and the standard deviation
is

.. math::

\sqrt{\\frac{2.0}{fan\_in + fan\_out}}
gain \times \sqrt{\\frac{2.0}{fan\_in + fan\_out}}


Args:
Expand All @@ -57,21 +57,25 @@ class XavierInitializer(Initializer):
inferred from the variable. Default is None.
fan_out (float, optional): fan_out for Xavier initialization. If None, it is
inferred from the variable. Default is None.
gain (float, optional): Scaling Tensor. Default is 1.0.
seed (int, optional): Random seed. Default is 0.

Note:
It is recommended to set fan_in and fan_out to None for most cases.

"""

def __init__(self, uniform=True, fan_in=None, fan_out=None, seed=0):
def __init__(
self, uniform=True, fan_in=None, fan_out=None, seed=0, gain=1.0
):
assert uniform is not None
assert seed is not None
super().__init__()
self._uniform = uniform
self._fan_in = fan_in
self._fan_out = fan_out
self._seed = seed
self._gain = gain

def forward(self, var, block=None):
"""Initialize the input tensor with Xavier initialization.
Expand Down Expand Up @@ -136,7 +140,7 @@ def forward(self, var, block=None):

if in_dygraph_mode():
if self._uniform:
limit = math.sqrt(6.0 / float(fan_in + fan_out))
limit = self._gain * math.sqrt(6.0 / float(fan_in + fan_out))
out_var = _C_ops.uniform(
out_var_shape,
out_dtype,
Expand All @@ -146,7 +150,7 @@ def forward(self, var, block=None):
_current_expected_place(),
)
else:
std = math.sqrt(2.0 / float(fan_in + fan_out))
std = self._gain * math.sqrt(2.0 / float(fan_in + fan_out))

place = _current_expected_place()
out_var = _C_ops.gaussian(
Expand All @@ -173,7 +177,7 @@ def forward(self, var, block=None):
return None
elif in_pir_mode():
if self._uniform:
limit = math.sqrt(6.0 / float(fan_in + fan_out))
limit = self._gain * math.sqrt(6.0 / float(fan_in + fan_out))
out_var = paddle._pir_ops.uniform(
out_var.shape,
out_dtype,
Expand All @@ -183,7 +187,7 @@ def forward(self, var, block=None):
_current_expected_place(),
)
else:
std = math.sqrt(2.0 / float(fan_in + fan_out))
std = self._gain * math.sqrt(2.0 / float(fan_in + fan_out))
out_var = _C_ops.gaussian(
out_var.shape,
0.0,
Expand All @@ -202,7 +206,7 @@ def forward(self, var, block=None):
return out_var
else:
if self._uniform:
limit = math.sqrt(6.0 / float(fan_in + fan_out))
limit = self._gain * math.sqrt(6.0 / float(fan_in + fan_out))
op = block.append_op(
type="uniform_random",
inputs={},
Expand All @@ -217,7 +221,7 @@ def forward(self, var, block=None):
stop_gradient=True,
)
else:
std = math.sqrt(2.0 / float(fan_in + fan_out))
std = self._gain * math.sqrt(2.0 / float(fan_in + fan_out))
op = block.append_op(
type="gaussian_random",
outputs={"Out": out_var},
Expand Down Expand Up @@ -254,14 +258,15 @@ class XavierNormal(XavierInitializer):

.. math::

\sqrt{\frac{2.0}{fan\_in + fan\_out}}.
gain \times \sqrt{\frac{2.0}{fan\_in + fan\_out}}.


Args:
fan_in (float, optional): fan_in for Xavier initialization, which is
inferred from the Tensor. Default is None.
fan_out (float, optional): fan_out for Xavier initialization, which is
inferred from the Tensor. Default is None.
gain (float, optional): Scaling Tensor. Default is 1.0.
name (str, optional): For details, please refer to :ref:`api_guide_Name`. Generally, no setting is required. Default: None.

Returns:
Expand Down Expand Up @@ -299,8 +304,10 @@ class XavierNormal(XavierInitializer):
[[1.13615966, 0.89018601]]])
"""

def __init__(self, fan_in=None, fan_out=None, name=None):
super().__init__(uniform=False, fan_in=fan_in, fan_out=fan_out, seed=0)
def __init__(self, fan_in=None, fan_out=None, gain=1.0, name=None):
super().__init__(
uniform=False, fan_in=fan_in, fan_out=fan_out, seed=0, gain=gain
)


class XavierUniform(XavierInitializer):
Expand All @@ -316,13 +323,14 @@ class XavierUniform(XavierInitializer):

.. math::

x = \sqrt{\frac{6.0}{fan\_in + fan\_out}}.
x = gain \times \sqrt{\frac{6.0}{fan\_in + fan\_out}}.

Args:
fan_in (float, optional): fan_in for Xavier initialization, which is
inferred from the Tensor. Default is None.
fan_out (float, optional): fan_out for Xavier initialization, which is
inferred from the Tensor. Default is None.
gain (float, optional): Scaling Tensor. Default is 1.0.
name (str, optional): For details, please refer to :ref:`api_guide_Name`. Generally, no setting is required. Default: None.

Returns:
Expand Down Expand Up @@ -359,5 +367,7 @@ class XavierUniform(XavierInitializer):
[[-1.02494967, 0.67544925]]])
"""

def __init__(self, fan_in=None, fan_out=None, name=None):
super().__init__(uniform=True, fan_in=fan_in, fan_out=fan_out, seed=0)
def __init__(self, fan_in=None, fan_out=None, gain=1.0, name=None):
super().__init__(
uniform=True, fan_in=fan_in, fan_out=fan_out, seed=0, gain=gain
)
37 changes: 33 additions & 4 deletions test/legacy_test/test_initializer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -543,7 +543,7 @@ def test_xavier_initializer_supplied_arguments(
lod_level=0,
name="param",
initializer=paddle.nn.initializer.XavierInitializer(
uniform=uniform, fan_in=12, fan_out=23, seed=134
uniform=uniform, fan_in=12, fan_out=23, seed=134, gain=0.2
),
)
num_ops = (
Expand All @@ -555,7 +555,7 @@ def test_xavier_initializer_supplied_arguments(
init_op = block.ops[0]
if uniform:
self.assertEqual(init_op.type, 'uniform_random')
limit = np.sqrt(6.0 / (12 + 23))
limit = 0.2 * np.sqrt(6.0 / (12 + 23))
self.assertAlmostEqual(init_op.attr('min'), -limit, delta=DELTA)
self.assertAlmostEqual(init_op.attr('max'), limit, delta=DELTA)
else:
Expand Down Expand Up @@ -741,7 +741,11 @@ def test_xavier_initializer_supplied_arguments(
shape=[5, 10],
name="param",
initializer=paddle.nn.initializer.XavierInitializer(
uniform=uniform, fan_in=12, fan_out=23, seed=134
uniform=uniform,
fan_in=12,
fan_out=23,
seed=134,
gain=0.2,
),
)
block = startup.global_block()
Expand All @@ -755,7 +759,7 @@ def test_xavier_initializer_supplied_arguments(
self.assertEqual(len(checked_ops), 1)
init_op = checked_ops[0]
if uniform:
limit = np.sqrt(6.0 / (12 + 23))
limit = 0.2 * np.sqrt(6.0 / (12 + 23))
min = self.get_operand_definition_op_attrs(
init_op, "min", "value"
)
Expand Down Expand Up @@ -1553,6 +1557,31 @@ def test_xavier_initializer(self, dtype="float32"):
paddle.enable_static()


class TestXavierInitializerDygraph2(unittest.TestCase):
def test_xavier_initializer_with_gain(self, dtype="float32"):
"""
In dygraph mode, we can use initializer directly to initialize a tensor.
"""
paddle.disable_static()

tensor = paddle.zeros([1024, 1024, 16])
tensor.stop_gradient = False

xavier_ = paddle.nn.initializer.XavierNormal(
fan_in=3, fan_out=5, gain=2.5
)
xavier_(tensor)

hist, _ = output_hist(tensor.numpy())

hist2, _ = output_hist(
np.random.normal(0, 2.5 * np.sqrt(2.0 / (3 + 5)), [1024, 1024, 16])
)

np.testing.assert_allclose(hist, hist2, rtol=0, atol=0.01)
paddle.enable_static()


class TestMSRAInitializerDygraph(unittest.TestCase):
def test_msra_initializer(self, dtype="float32"):
"""
Expand Down