def func(self, place):
# the shape of input variable should be clearly specified, not inlcude -1.
shape = [2, 3, 4, 5]
eps = 0.0001
dtype = np.float64
x = layers.data('x', shape, False, dtype)
y = layers.data('y', shape, False, dtype)
x.persistable = True
y.persistable = True
out = layers.elementwise_div(x, y, axis=0)
x_arr = np.random.uniform(-1, 1, shape).astype(dtype)
y_arr = np.random.uniform(-1, 1, shape).astype(dtype)
y_arr[np.abs(y_arr) < 0.005] = 0.02
gradient_checker.double_grad_check([x, y],
out,
x_init=[x_arr, y_arr],
place=place,
eps=eps,
atol=1e-3)
gradient_checker.double_grad_check_for_dygraph(self.divide_wrapper,
[x, y],
out,
x_init=[x_arr, y_arr],
place=place,
atol=1e-3)
def func(self, place):
prog = fluid.Program()
with fluid.program_guard(prog):
np.random.seed()
dtype = "float32"
eps = 0.005
atol = 1e-4
x = layers.create_parameter(dtype=dtype,
shape=self.shape,
name='x')
z = fluid.layers.batch_norm(input=x,
data_layout=self.data_layout,
use_global_stats=self.use_global_stats)
x_arr = np.random.uniform(-1, 1, self.shape).astype(dtype)
gradient_checker.double_grad_check([x],
z,
x_init=x_arr,
atol=atol,
place=place,
eps=eps)
gradient_checker.double_grad_check_for_dygraph(
self.batch_norm_wrapper, [x],
z,
x_init=x_arr,
atol=atol,
place=place)
def func(self, place):
shape = [2, 4, 3, 3]
eps = 0.005
dtype = np.float64
if core.is_compiled_with_rocm():
dtype = np.float32
x = layers.data('x', shape, False, dtype)
y = layers.conv2d_transpose(
x, 2, filter_size=1, groups=1, bias_attr=False)
x_arr = np.random.uniform(-1, 1, shape).astype(dtype)
w = fluid.default_main_program().global_block().all_parameters()
w_arr = []
for p in w:
w_arr.append(np.random.uniform(-1, 1, p.shape).astype(dtype))
if core.is_compiled_with_rocm():
# HIP will sometimes fail if no atol
gradient_checker.double_grad_check(
[x] + w,
y,
x_init=[x_arr] + w_arr,
place=place,
eps=eps,
atol=1e-4)
else:
gradient_checker.double_grad_check(
[x] + w, y, x_init=[x_arr] + w_arr, place=place, eps=eps)
gradient_checker.double_grad_check_for_dygraph(
self.conv_transpose_wrapper, [x] + w,
y,
x_init=[x_arr] + w_arr,
place=place)
def func(self, place):
prog = fluid.Program()
with fluid.program_guard(prog):
np.random.seed()
shape = [2, 3, 4, 5]
dtype = "float32"
eps = 0.005
atol = 1e-4
x = layers.create_parameter(dtype=dtype, shape=shape, name='x')
z = paddle.nn.functional.instance_norm(x)
x_arr = np.random.uniform(-1, 1, shape).astype(dtype)
# check for static mode
gradient_checker.double_grad_check([x],
z,
x_init=x_arr,
atol=atol,
place=place,
eps=eps)
# check for eager mode
gradient_checker.double_grad_check_for_dygraph(
self.instance_norm_wrapper, [x],
z,
x_init=x_arr,
atol=atol,
place=place)
def func(self, place):
x_shape = [2, 4, 3, 3]
w_shape = [4, 1, 3, 3]
eps = 0.005
dtype = np.float32 if fluid.core.is_compiled_with_rocm(
) else np.float64
x = layers.data('x', x_shape, False, dtype)
w = layers.data('w', w_shape, False, dtype)
# condition of depthwise conv:
# use_cudnn == False
# groups == filters
# num_filters % num_channels == 0
y = paddle.nn.functional.conv2d(x, w, groups=4)
x_arr = np.random.uniform(-1, 1, x_shape).astype(dtype)
w_arr = np.random.uniform(-1, 1, w_shape).astype(dtype)
gradient_checker.double_grad_check([x, w],
y,
x_init=[x_arr, w_arr],
place=place,
eps=eps)
gradient_checker.double_grad_check_for_dygraph(
self.depthwise_conv2d_wrapper, [x, w],
y,
x_init=[x_arr, w_arr],
place=place)
def func(self, place):
x_shape = [2, 4, 10]
dtype = np.float64
x = layers.data('x', x_shape, False, dtype)
x.persistable = True
out = paddle.clip(x, min=-1., max=1.)
x_arr = np.random.uniform(-5., 5., x_shape).astype(dtype)
gradient_checker.double_grad_check([x], out, x_init=x_arr, place=place)
gradient_checker.double_grad_check_for_dygraph(
self.clip_wrapper, [x], out, x_init=x_arr, place=place)
def func(self, place):
x_shape = [2, 3, 4, 5]
pad = [1, 1, 1, 1]
eps = 0.005
dtype = np.float64
x = layers.data('x', x_shape, False, dtype)
x.persistable = True
out = paddle.nn.functional.pad(x, pad)
x_arr = np.random.uniform(-1, 1, x_shape).astype(dtype)
gradient_checker.double_grad_check(
[x], out, x_init=x_arr, place=place, eps=eps)
gradient_checker.double_grad_check_for_dygraph(
self.pad_wrapper, [x], out, x_init=x_arr, place=place)
def func(self, place):
shape = [2, 3, 7, 9]
eps = 0.0001
dtype = np.float64
x = layers.data('x', shape, False, dtype)
x.persistable = True
y = layers.rsqrt(x)
x_arr = np.random.uniform(0.1, 1, shape).astype(dtype)
gradient_checker.double_grad_check(
[x], y, x_init=x_arr, place=place, eps=eps)
gradient_checker.double_grad_check_for_dygraph(
self.rsqrt_wrapper, [x], y, x_init=x_arr, place=place)
def func(self, place):
x_shape = [3, 40]
axes = [1, 2]
eps = 0.005
dtype = np.float64
x = layers.data('x', x_shape, False, dtype)
x.persistable = True
out = paddle.unsqueeze(x, axes)
x_arr = np.random.uniform(-1, 1, x_shape).astype(dtype)
gradient_checker.double_grad_check(
[x], out, x_init=x_arr, place=place, eps=eps)
gradient_checker.double_grad_check_for_dygraph(
self.unsqueeze_wrapper, [x], out, x_init=x_arr, place=place)
def func(self, place):
shape = [2, 3, 7, 9]
eps = 0.0005
dtype = np.float64
x = layers.data('x', shape, False, dtype=dtype)
x.persistable = True
y = layers.sigmoid(x)
x_arr = np.random.uniform(-1, 1, shape).astype(dtype)
x_arr[np.abs(x_arr) < 0.005] = 0.002
gradient_checker.double_grad_check(
[x], y, x_init=x_arr, place=place, eps=eps)
fluid.set_flags({"FLAGS_retain_grad_for_all_tensor": True})
gradient_checker.double_grad_check_for_dygraph(
self.sigmoid_wrapper, [x], y, x_init=x_arr, place=place)
fluid.set_flags({"FLAGS_retain_grad_for_all_tensor": False})
def func(self, place):
input_NCHW = fluid.layers.data(
name="input_NCHW",
shape=[2, 3, 5, 5],
append_batch_size=False,
dtype="float32")
input_NCHW.persistable = True
y = layers.pool2d(input_NCHW, pool_size=[4, 4], pool_type="avg")
y = paddle.nn.functional.avg_pool2d(input_NCHW, kernel_size=[4, 4])
x_arr = np.random.uniform(-1, 1, [2, 3, 5, 5]).astype(np.float32)
gradient_checker.double_grad_check(
[input_NCHW], y, x_init=x_arr, place=place, eps=0.05)
gradient_checker.double_grad_check_for_dygraph(
self.pool2d_wrapper, [input_NCHW], y, x_init=x_arr, place=place)
def func(self, place):
input_NHWC = fluid.layers.data(
name="input_NHWC",
shape=[2, 5, 5, 3],
append_batch_size=False,
dtype="float32")
input_NHWC.persistable = True
y = paddle.nn.functional.avg_pool2d(
input_NHWC, kernel_size=2, data_format="NHWC")
x_arr = np.random.uniform(-1, 1, [2, 5, 5, 3]).astype(np.float32)
gradient_checker.double_grad_check(
[input_NHWC], y, x_init=x_arr, place=place, eps=0.05)
gradient_checker.double_grad_check_for_dygraph(
self.pool2d_wrapper, [input_NHWC], y, x_init=x_arr, place=place)
def func(self, place):
shape = [2, 3, 7, 9]
eps = 0.005
alpha = 0.2
dtype = np.float64
x = layers.data('x', shape, False, dtype)
x.persistable = True
y = layers.leaky_relu(x, alpha=alpha)
x_arr = np.random.uniform(-1, 1, shape).astype(dtype)
x_arr[np.abs(x_arr) < 0.005] = 0.02
gradient_checker.double_grad_check(
[x], y, x_init=x_arr, place=place, eps=eps)
gradient_checker.double_grad_check_for_dygraph(
self.leaky_relu_wrapper, [x], y, x_init=x_arr, place=place)
def func(self, place):
# the shape of input variable should be clearly specified, not inlcude -1.
shape = [2, 3, 7, 9]
eps = 0.005
dtype = np.float64
x = layers.data('x', shape, False, dtype)
x.persistable = True
y = layers.square(x)
x_arr = np.random.uniform(-1, 1, shape).astype(dtype)
gradient_checker.double_grad_check(
[x], y, x_init=x_arr, place=place, eps=eps)
fluid.set_flags({"FLAGS_retain_grad_for_all_tensor": True})
gradient_checker.double_grad_check_for_dygraph(
self.square_wrapper, [x], y, x_init=x_arr, place=place)
fluid.set_flags({"FLAGS_retain_grad_for_all_tensor": False})
def func(self, place):
shape = [2, 4, 4, 4]
eps = 1e-6
alpha = 0.2
dtype = np.float64
SEED = 0
x = layers.data('x', shape, False, dtype)
x.persistable = True
y = F.celu(x, alpha=alpha)
np.random.RandomState(SEED)
x_arr = np.random.uniform(-1, 1, shape).astype(dtype)
gradient_checker.double_grad_check(
[x], y, x_init=x_arr, place=place, eps=eps)
fluid.set_flags({"FLAGS_retain_grad_for_all_tensor": True})
gradient_checker.double_grad_check_for_dygraph(
self.celu_wrapper, [x], y, x_init=x_arr, place=place)
fluid.set_flags({"FLAGS_retain_grad_for_all_tensor": False})
def func(self, place):
x_shape = [2, 3, 4, 5]
pad = [1, 1, 1, 1]
dtype = np.float64
x1 = layers.data('x', x_shape, False, dtype)
x2 = layers.data('x', x_shape, False, dtype)
x1.persistable = True
x2.persistable = True
out = paddle.concat([x1, x2], axis=0)
x2_arr = np.random.uniform(-1, 1, x_shape).astype(dtype)
x1_arr = np.random.uniform(-1, 1, x_shape).astype(dtype)
gradient_checker.double_grad_check(
[x1, x2], out, x_init=[x1_arr, x2_arr], place=place)
gradient_checker.double_grad_check_for_dygraph(
self.concat_wrapper, [x1, x2],
out,
x_init=[x1_arr, x2_arr],
place=place)
def func(self, place):
x_shape = [2, 3, 8, 8, 8]
w_shape = [6, 3, 3, 3, 3]
eps = 0.005
dtype = np.float32 if fluid.core.is_compiled_with_rocm(
) else np.float64
x = layers.data('x', x_shape, False, dtype)
w = layers.data('w', w_shape, False, dtype)
x.persistable = True
w.persistable = True
y = paddle.nn.functional.conv3d(x, w)
x_arr = np.random.uniform(-1, 1, x_shape).astype(dtype)
w_arr = np.random.uniform(-1, 1, w_shape).astype(dtype)
gradient_checker.double_grad_check([x, w],
y,
x_init=[x_arr, w_arr],
place=place,
eps=eps)
gradient_checker.double_grad_check_for_dygraph(self.conv3d_wrapper,
[x, w],
y,
x_init=[x_arr, w_arr],
place=place)
def func(self, place):
# the shape of input variable should be clearly specified, not inlcude -1.
shape = [2, 3, 4, 5]
eps = 0.005
dtype = np.float64
x = layers.data('x', shape, False, dtype)
y = layers.data('y', shape, False, dtype)
x.persistable = True
y.persistable = True
out = layers.elementwise_sub(x, y)
x_arr = np.random.uniform(-1, 1, shape).astype(dtype)
y_arr = np.random.uniform(-1, 1, shape).astype(dtype)
gradient_checker.double_grad_check([x, y],
out,
x_init=[x_arr, y_arr],
place=place,
eps=eps)
gradient_checker.double_grad_check_for_dygraph(self.subtract_wrapper,
[x, y],
out,
x_init=[x_arr, y_arr],
place=place)
