def test_name_type():
# name type must be string.
x4 = paddle.static.data(name="x4",
shape=[3, 2],
dtype="float32")
res = paddle.is_empty(x=x4, name=1)
def test_dygraph(self):
paddle.disable_static(paddle.NPUPlace(0))
input = paddle.rand(shape=[4, 32, 32], dtype='float32')
res = paddle.is_empty(x=input)
def test_type():
# dtype must be float32, float16 in NPU
x3 = paddle.static.data(name="x3",
shape=[4, 32, 32],
dtype="bool")
res = paddle.is_empty(x=x3)
def test_Variable():
# the input type must be Variable
paddle.is_empty(x=input_data)
def test_tensor_patch_method(self):
paddle.disable_static()
x_np = np.random.uniform(-1, 1, [2, 3]).astype(self.dtype)
y_np = np.random.uniform(-1, 1, [2, 3]).astype(self.dtype)
z_np = np.random.uniform(-1, 1, [6, 9]).astype(self.dtype)
x = paddle.to_tensor(x_np)
y = paddle.to_tensor(y_np)
z = paddle.to_tensor(z_np)
a = paddle.to_tensor([[1, 1], [2, 2], [3, 3]])
b = paddle.to_tensor([[1, 1], [2, 2], [3, 3]])
# 1. Unary operation for Tensor
self.assertEqual(x.dim(), 2)
self.assertEqual(x.ndimension(), 2)
self.assertEqual(x.ndim, 2)
self.assertEqual(x.size, 6)
self.assertEqual(x.numel(), 6)
self.assertTrue(np.array_equal(x.exp().numpy(), paddle.exp(x).numpy()))
self.assertTrue(
np.array_equal(x.tanh().numpy(),
paddle.tanh(x).numpy()))
self.assertTrue(
np.array_equal(x.atan().numpy(),
paddle.atan(x).numpy()))
self.assertTrue(np.array_equal(x.abs().numpy(), paddle.abs(x).numpy()))
m = x.abs()
self.assertTrue(
np.array_equal(m.sqrt().numpy(),
paddle.sqrt(m).numpy()))
self.assertTrue(
np.array_equal(m.rsqrt().numpy(),
paddle.rsqrt(m).numpy()))
self.assertTrue(
np.array_equal(x.ceil().numpy(),
paddle.ceil(x).numpy()))
self.assertTrue(
np.array_equal(x.floor().numpy(),
paddle.floor(x).numpy()))
self.assertTrue(np.array_equal(x.cos().numpy(), paddle.cos(x).numpy()))
self.assertTrue(
np.array_equal(x.acos().numpy(),
paddle.acos(x).numpy()))
self.assertTrue(
np.array_equal(x.asin().numpy(),
paddle.asin(x).numpy()))
self.assertTrue(np.array_equal(x.sin().numpy(), paddle.sin(x).numpy()))
self.assertTrue(
np.array_equal(x.sinh().numpy(),
paddle.sinh(x).numpy()))
self.assertTrue(
np.array_equal(x.cosh().numpy(),
paddle.cosh(x).numpy()))
self.assertTrue(
np.array_equal(x.round().numpy(),
paddle.round(x).numpy()))
self.assertTrue(
np.array_equal(x.reciprocal().numpy(),
paddle.reciprocal(x).numpy()))
self.assertTrue(
np.array_equal(x.square().numpy(),
paddle.square(x).numpy()))
self.assertTrue(
np.array_equal(x.rank().numpy(),
paddle.rank(x).numpy()))
self.assertTrue(
np.array_equal(x[0].t().numpy(),
paddle.t(x[0]).numpy()))
self.assertTrue(
np.array_equal(x.asinh().numpy(),
paddle.asinh(x).numpy()))
### acosh(x) = nan, need to change input
t_np = np.random.uniform(1, 2, [2, 3]).astype(self.dtype)
t = paddle.to_tensor(t_np)
self.assertTrue(
np.array_equal(t.acosh().numpy(),
paddle.acosh(t).numpy()))
self.assertTrue(
np.array_equal(x.atanh().numpy(),
paddle.atanh(x).numpy()))
d = paddle.to_tensor([[1.2285208, 1.3491015, 1.4899898],
[1.30058, 1.0688717, 1.4928783],
[1.0958099, 1.3724753, 1.8926544]])
d = d.matmul(d.t())
# ROCM not support cholesky
if not fluid.core.is_compiled_with_rocm():
self.assertTrue(
np.array_equal(d.cholesky().numpy(),
paddle.cholesky(d).numpy()))
self.assertTrue(
np.array_equal(x.is_empty().numpy(),
paddle.is_empty(x).numpy()))
self.assertTrue(
np.array_equal(x.isfinite().numpy(),
paddle.isfinite(x).numpy()))
self.assertTrue(
np.array_equal(
x.cast('int32').numpy(),
paddle.cast(x, 'int32').numpy()))
self.assertTrue(
np.array_equal(
x.expand([3, 2, 3]).numpy(),
paddle.expand(x, [3, 2, 3]).numpy()))
self.assertTrue(
np.array_equal(
x.tile([2, 2]).numpy(),
paddle.tile(x, [2, 2]).numpy()))
self.assertTrue(
np.array_equal(x.flatten().numpy(),
paddle.flatten(x).numpy()))
index = paddle.to_tensor([0, 1])
self.assertTrue(
np.array_equal(
x.gather(index).numpy(),
paddle.gather(x, index).numpy()))
index = paddle.to_tensor([[0, 1], [1, 2]])
self.assertTrue(
np.array_equal(
x.gather_nd(index).numpy(),
paddle.gather_nd(x, index).numpy()))
self.assertTrue(
np.array_equal(
x.reverse([0, 1]).numpy(),
paddle.reverse(x, [0, 1]).numpy()))
self.assertTrue(
np.array_equal(
a.reshape([3, 2]).numpy(),
paddle.reshape(a, [3, 2]).numpy()))
self.assertTrue(
np.array_equal(
x.slice([0, 1], [0, 0], [1, 2]).numpy(),
paddle.slice(x, [0, 1], [0, 0], [1, 2]).numpy()))
self.assertTrue(
np.array_equal(
x.split(2)[0].numpy(),
paddle.split(x, 2)[0].numpy()))
m = paddle.to_tensor(
np.random.uniform(-1, 1, [1, 6, 1, 1]).astype(self.dtype))
self.assertTrue(
np.array_equal(
m.squeeze([]).numpy(),
paddle.squeeze(m, []).numpy()))
self.assertTrue(
np.array_equal(
m.squeeze([1, 2]).numpy(),
paddle.squeeze(m, [1, 2]).numpy()))
m = paddle.to_tensor([2, 3, 3, 1, 5, 3], 'float32')
self.assertTrue(
np.array_equal(m.unique()[0].numpy(),
paddle.unique(m)[0].numpy()))
self.assertTrue(
np.array_equal(
m.unique(return_counts=True)[1],
paddle.unique(m, return_counts=True)[1]))
self.assertTrue(np.array_equal(x.flip([0]), paddle.flip(x, [0])))
self.assertTrue(np.array_equal(x.unbind(0), paddle.unbind(x, 0)))
self.assertTrue(np.array_equal(x.roll(1), paddle.roll(x, 1)))
self.assertTrue(np.array_equal(x.cumsum(1), paddle.cumsum(x, 1)))
m = paddle.to_tensor(1)
self.assertTrue(np.array_equal(m.increment(), paddle.increment(m)))
m = x.abs()
self.assertTrue(np.array_equal(m.log(), paddle.log(m)))
self.assertTrue(np.array_equal(x.pow(2), paddle.pow(x, 2)))
self.assertTrue(np.array_equal(x.reciprocal(), paddle.reciprocal(x)))
# 2. Binary operation
self.assertTrue(
np.array_equal(x.divide(y).numpy(),
paddle.divide(x, y).numpy()))
self.assertTrue(
np.array_equal(
x.matmul(y, True, False).numpy(),
paddle.matmul(x, y, True, False).numpy()))
self.assertTrue(
np.array_equal(
x.norm(p='fro', axis=[0, 1]).numpy(),
paddle.norm(x, p='fro', axis=[0, 1]).numpy()))
self.assertTrue(
np.array_equal(x.dist(y).numpy(),
paddle.dist(x, y).numpy()))
self.assertTrue(
np.array_equal(x.cross(y).numpy(),
paddle.cross(x, y).numpy()))
m = x.expand([2, 2, 3])
n = y.expand([2, 2, 3]).transpose([0, 2, 1])
self.assertTrue(
np.array_equal(m.bmm(n).numpy(),
paddle.bmm(m, n).numpy()))
self.assertTrue(
np.array_equal(
x.histogram(5, -1, 1).numpy(),
paddle.histogram(x, 5, -1, 1).numpy()))
self.assertTrue(
np.array_equal(x.equal(y).numpy(),
paddle.equal(x, y).numpy()))
self.assertTrue(
np.array_equal(
x.greater_equal(y).numpy(),
paddle.greater_equal(x, y).numpy()))
self.assertTrue(
np.array_equal(
x.greater_than(y).numpy(),
paddle.greater_than(x, y).numpy()))
self.assertTrue(
np.array_equal(
x.less_equal(y).numpy(),
paddle.less_equal(x, y).numpy()))
self.assertTrue(
np.array_equal(
x.less_than(y).numpy(),
paddle.less_than(x, y).numpy()))
self.assertTrue(
np.array_equal(
x.not_equal(y).numpy(),
paddle.not_equal(x, y).numpy()))
self.assertTrue(
np.array_equal(
x.equal_all(y).numpy(),
paddle.equal_all(x, y).numpy()))
self.assertTrue(
np.array_equal(
x.allclose(y).numpy(),
paddle.allclose(x, y).numpy()))
m = x.expand([2, 2, 3])
self.assertTrue(
np.array_equal(
x.expand_as(m).numpy(),
paddle.expand_as(x, m).numpy()))
index = paddle.to_tensor([2, 1, 0])
self.assertTrue(
np.array_equal(
a.scatter(index, b).numpy(),
paddle.scatter(a, index, b).numpy()))
# 3. Bool tensor operation
x = paddle.to_tensor([[True, False], [True, False]])
y = paddle.to_tensor([[False, False], [False, True]])
self.assertTrue(
np.array_equal(
x.logical_and(y).numpy(),
paddle.logical_and(x, y).numpy()))
self.assertTrue(
np.array_equal(
x.logical_not(y).numpy(),
paddle.logical_not(x, y).numpy()))
self.assertTrue(
np.array_equal(
x.logical_or(y).numpy(),
paddle.logical_or(x, y).numpy()))
self.assertTrue(
np.array_equal(
x.logical_xor(y).numpy(),
paddle.logical_xor(x, y).numpy()))
self.assertTrue(
np.array_equal(
x.logical_and(y).numpy(),
paddle.logical_and(x, y).numpy()))
a = paddle.to_tensor([[1, 2], [3, 4]])
b = paddle.to_tensor([[4, 3], [2, 1]])
self.assertTrue(
np.array_equal(
x.where(a, b).numpy(),
paddle.where(x, a, b).numpy()))
x_np = np.random.randn(3, 6, 9, 7)
x = paddle.to_tensor(x_np)
x_T = x.T
self.assertTrue(x_T.shape, [7, 9, 6, 3])
self.assertTrue(np.array_equal(x_T.numpy(), x_np.T))
self.assertTrue(inspect.ismethod(a.dot))
self.assertTrue(inspect.ismethod(a.logsumexp))
self.assertTrue(inspect.ismethod(a.multiplex))
self.assertTrue(inspect.ismethod(a.prod))
self.assertTrue(inspect.ismethod(a.scale))
self.assertTrue(inspect.ismethod(a.stanh))
self.assertTrue(inspect.ismethod(a.add_n))
self.assertTrue(inspect.ismethod(a.max))
self.assertTrue(inspect.ismethod(a.maximum))
self.assertTrue(inspect.ismethod(a.min))
self.assertTrue(inspect.ismethod(a.minimum))
self.assertTrue(inspect.ismethod(a.floor_divide))
self.assertTrue(inspect.ismethod(a.remainder))
self.assertTrue(inspect.ismethod(a.floor_mod))
self.assertTrue(inspect.ismethod(a.multiply))
self.assertTrue(inspect.ismethod(a.logsumexp))
self.assertTrue(inspect.ismethod(a.inverse))
self.assertTrue(inspect.ismethod(a.log1p))
self.assertTrue(inspect.ismethod(a.erf))
self.assertTrue(inspect.ismethod(a.addmm))
self.assertTrue(inspect.ismethod(a.clip))
self.assertTrue(inspect.ismethod(a.trace))
self.assertTrue(inspect.ismethod(a.kron))
self.assertTrue(inspect.ismethod(a.isinf))
self.assertTrue(inspect.ismethod(a.isnan))
self.assertTrue(inspect.ismethod(a.concat))
self.assertTrue(inspect.ismethod(a.broadcast_to))
self.assertTrue(inspect.ismethod(a.scatter_nd_add))
self.assertTrue(inspect.ismethod(a.scatter_nd))
self.assertTrue(inspect.ismethod(a.shard_index))
self.assertTrue(inspect.ismethod(a.chunk))
self.assertTrue(inspect.ismethod(a.stack))
self.assertTrue(inspect.ismethod(a.strided_slice))
self.assertTrue(inspect.ismethod(a.unsqueeze))
self.assertTrue(inspect.ismethod(a.unstack))
self.assertTrue(inspect.ismethod(a.argmax))
self.assertTrue(inspect.ismethod(a.argmin))
self.assertTrue(inspect.ismethod(a.argsort))
self.assertTrue(inspect.ismethod(a.masked_select))
self.assertTrue(inspect.ismethod(a.topk))
self.assertTrue(inspect.ismethod(a.index_select))
self.assertTrue(inspect.ismethod(a.nonzero))
self.assertTrue(inspect.ismethod(a.sort))
self.assertTrue(inspect.ismethod(a.index_sample))
self.assertTrue(inspect.ismethod(a.mean))
self.assertTrue(inspect.ismethod(a.std))
self.assertTrue(inspect.ismethod(a.numel))
def test_tensor_patch_method(self):
paddle.disable_static()
x_np = np.random.uniform(-1, 1, [2, 3]).astype(self.dtype)
y_np = np.random.uniform(-1, 1, [2, 3]).astype(self.dtype)
z_np = np.random.uniform(-1, 1, [6, 9]).astype(self.dtype)
x = paddle.to_tensor(x_np)
y = paddle.to_tensor(y_np)
z = paddle.to_tensor(z_np)
a = paddle.to_tensor([[1, 1], [2, 2], [3, 3]])
b = paddle.to_tensor([[1, 1], [2, 2], [3, 3]])
# 1. Unary operation for Tensor
self.assertEqual(x.dim(), 2)
self.assertEqual(x.ndimension(), 2)
self.assertEqual(x.ndim, 2)
self.assertEqual(x.size(), [2, 3])
self.assertTrue(
np.array_equal(x.sigmoid().numpy(),
fluid.layers.sigmoid(x).numpy()))
self.assertTrue(
np.array_equal(x.logsigmoid().numpy(),
fluid.layers.logsigmoid(x).numpy()))
self.assertTrue(np.array_equal(x.exp().numpy(), paddle.exp(x).numpy()))
self.assertTrue(
np.array_equal(x.tanh().numpy(),
paddle.tanh(x).numpy()))
self.assertTrue(
np.array_equal(x.atan().numpy(),
paddle.atan(x).numpy()))
self.assertTrue(
np.array_equal(x.tanh_shrink().numpy(),
fluid.layers.tanh_shrink(x).numpy()))
self.assertTrue(np.array_equal(x.abs().numpy(), paddle.abs(x).numpy()))
m = x.abs()
self.assertTrue(
np.array_equal(m.sqrt().numpy(),
paddle.sqrt(m).numpy()))
self.assertTrue(
np.array_equal(m.rsqrt().numpy(),
paddle.rsqrt(m).numpy()))
self.assertTrue(
np.array_equal(x.ceil().numpy(),
paddle.ceil(x).numpy()))
self.assertTrue(
np.array_equal(x.floor().numpy(),
paddle.floor(x).numpy()))
self.assertTrue(np.array_equal(x.cos().numpy(), paddle.cos(x).numpy()))
self.assertTrue(
np.array_equal(x.acos().numpy(),
paddle.acos(x).numpy()))
self.assertTrue(
np.array_equal(x.asin().numpy(),
paddle.asin(x).numpy()))
self.assertTrue(np.array_equal(x.sin().numpy(), paddle.sin(x).numpy()))
self.assertTrue(
np.array_equal(x.sinh().numpy(),
paddle.sinh(x).numpy()))
self.assertTrue(
np.array_equal(x.cosh().numpy(),
paddle.cosh(x).numpy()))
self.assertTrue(
np.array_equal(x.round().numpy(),
paddle.round(x).numpy()))
self.assertTrue(
np.array_equal(x.reciprocal().numpy(),
paddle.reciprocal(x).numpy()))
self.assertTrue(
np.array_equal(x.square().numpy(),
paddle.square(x).numpy()))
self.assertTrue(
np.array_equal(x.softplus().numpy(),
fluid.layers.softplus(x).numpy()))
self.assertTrue(
np.array_equal(x.softsign().numpy(),
fluid.layers.softsign(x).numpy()))
self.assertTrue(
np.array_equal(x.rank().numpy(),
paddle.rank(x).numpy()))
self.assertTrue(
np.array_equal(x[0].t().numpy(),
paddle.t(x[0]).numpy()))
m = paddle.to_tensor(np.random.uniform(1, 2, [3, 3]), 'float32')
m = m.matmul(m.t())
self.assertTrue(
np.array_equal(m.cholesky().numpy(),
paddle.cholesky(m).numpy()))
self.assertTrue(
np.array_equal(x.is_empty().numpy(),
paddle.is_empty(x).numpy()))
self.assertTrue(
np.array_equal(x.isfinite().numpy(),
paddle.isfinite(x).numpy()))
self.assertTrue(
np.array_equal(
x.cast('int32').numpy(),
paddle.cast(x, 'int32').numpy()))
self.assertTrue(
np.array_equal(
x.expand([3, 2, 3]).numpy(),
paddle.expand(x, [3, 2, 3]).numpy()))
self.assertTrue(
np.array_equal(
x.tile([2, 2]).numpy(),
paddle.tile(x, [2, 2]).numpy()))
self.assertTrue(
np.array_equal(x.flatten().numpy(),
paddle.flatten(x).numpy()))
index = paddle.to_tensor([0, 1])
self.assertTrue(
np.array_equal(
x.gather(index).numpy(),
paddle.gather(x, index).numpy()))
index = paddle.to_tensor([[0, 1], [1, 2]])
self.assertTrue(
np.array_equal(
x.gather_nd(index).numpy(),
paddle.gather_nd(x, index).numpy()))
self.assertTrue(
np.array_equal(
x.reverse([0, 1]).numpy(),
paddle.reverse(x, [0, 1]).numpy()))
self.assertTrue(
np.array_equal(
a.reshape([3, 2]).numpy(),
paddle.reshape(a, [3, 2]).numpy()))
self.assertTrue(
np.array_equal(
x.slice([0, 1], [0, 0], [1, 2]).numpy(),
paddle.slice(x, [0, 1], [0, 0], [1, 2]).numpy()))
self.assertTrue(
np.array_equal(
x.split(2)[0].numpy(),
paddle.split(x, 2)[0].numpy()))
m = paddle.to_tensor(
np.random.uniform(-1, 1, [1, 6, 1, 1]).astype(self.dtype))
self.assertTrue(
np.array_equal(
m.squeeze([]).numpy(),
paddle.squeeze(m, []).numpy()))
self.assertTrue(
np.array_equal(
m.squeeze([1, 2]).numpy(),
paddle.squeeze(m, [1, 2]).numpy()))
m = paddle.to_tensor([2, 3, 3, 1, 5, 3], 'float32')
self.assertTrue(
np.array_equal(m.unique()[0].numpy(),
paddle.unique(m)[0].numpy()))
self.assertTrue(
np.array_equal(m.unique_with_counts()[2],
paddle.unique_with_counts(m)[2]))
self.assertTrue(np.array_equal(x.flip([0]), paddle.flip(x, [0])))
self.assertTrue(np.array_equal(x.unbind(0), paddle.unbind(x, 0)))
self.assertTrue(np.array_equal(x.roll(1), paddle.roll(x, 1)))
self.assertTrue(np.array_equal(x.cumsum(1), paddle.cumsum(x, 1)))
m = paddle.to_tensor(1)
self.assertTrue(np.array_equal(m.increment(), paddle.increment(m)))
m = x.abs()
self.assertTrue(np.array_equal(m.log(), paddle.log(m)))
self.assertTrue(np.array_equal(x.pow(2), paddle.pow(x, 2)))
self.assertTrue(np.array_equal(x.reciprocal(), paddle.reciprocal(x)))
# 2. Binary operation
self.assertTrue(
np.array_equal(
x.matmul(y, True, False).numpy(),
paddle.matmul(x, y, True, False).numpy()))
self.assertTrue(
np.array_equal(
x.norm(p='fro', axis=[0, 1]).numpy(),
paddle.norm(x, p='fro', axis=[0, 1]).numpy()))
self.assertTrue(
np.array_equal(x.dist(y).numpy(),
paddle.dist(x, y).numpy()))
self.assertTrue(
np.array_equal(x.cross(y).numpy(),
paddle.cross(x, y).numpy()))
m = x.expand([2, 2, 3])
n = y.expand([2, 2, 3]).transpose([0, 2, 1])
self.assertTrue(
np.array_equal(m.bmm(n).numpy(),
paddle.bmm(m, n).numpy()))
self.assertTrue(
np.array_equal(
x.histogram(5, -1, 1).numpy(),
paddle.histogram(x, 5, -1, 1).numpy()))
self.assertTrue(
np.array_equal(x.equal(y).numpy(),
paddle.equal(x, y).numpy()))
self.assertTrue(
np.array_equal(
x.greater_equal(y).numpy(),
paddle.greater_equal(x, y).numpy()))
self.assertTrue(
np.array_equal(
x.greater_than(y).numpy(),
paddle.greater_than(x, y).numpy()))
self.assertTrue(
np.array_equal(
x.less_equal(y).numpy(),
paddle.less_equal(x, y).numpy()))
self.assertTrue(
np.array_equal(
x.less_than(y).numpy(),
paddle.less_than(x, y).numpy()))
self.assertTrue(
np.array_equal(
x.not_equal(y).numpy(),
paddle.not_equal(x, y).numpy()))
self.assertTrue(
np.array_equal(
x.equal_all(y).numpy(),
paddle.equal_all(x, y).numpy()))
self.assertTrue(
np.array_equal(
x.allclose(y).numpy(),
paddle.allclose(x, y).numpy()))
m = x.expand([2, 2, 3])
self.assertTrue(
np.array_equal(
x.expand_as(m).numpy(),
paddle.expand_as(x, m).numpy()))
index = paddle.to_tensor([2, 1, 0])
self.assertTrue(
np.array_equal(
a.scatter(index, b).numpy(),
paddle.scatter(a, index, b).numpy()))
# 3. Bool tensor operation
x = paddle.to_tensor([[True, False], [True, False]])
y = paddle.to_tensor([[False, False], [False, True]])
self.assertTrue(
np.array_equal(x.reduce_all().numpy(),
paddle.reduce_all(x).numpy()))
self.assertTrue(
np.array_equal(x.reduce_any().numpy(),
paddle.reduce_any(x).numpy()))
self.assertTrue(
np.array_equal(
x.logical_and(y).numpy(),
paddle.logical_and(x, y).numpy()))
self.assertTrue(
np.array_equal(
x.logical_not(y).numpy(),
paddle.logical_not(x, y).numpy()))
self.assertTrue(
np.array_equal(
x.logical_or(y).numpy(),
paddle.logical_or(x, y).numpy()))
self.assertTrue(
np.array_equal(
x.logical_xor(y).numpy(),
paddle.logical_xor(x, y).numpy()))
self.assertTrue(
np.array_equal(
x.logical_and(y).numpy(),
paddle.logical_and(x, y).numpy()))
def forward(self, inputs, use_cache=False, cache=None):
"""
Args:
inputs (dict): include src_ids.
pos_ids, input_mask and max_dec_len are optional.
"""
######### forward context #########
input_ids = inputs['src_ids']
position_ids = inputs['pos_ids'] if 'pos_ids' in inputs else None
attention_mask = inputs[
'input_mask'] if 'input_mask' in inputs else None
causal_mask = paddle.tensor.triu(paddle.ones(
(paddle.shape(input_ids)[-1], paddle.shape(input_ids)[-1])) * -1e4,
diagonal=1)
if attention_mask is not None:
tgt_pos = paddle.sum(attention_mask, axis=-1,
keepdim=True).astype('int64')
if len(attention_mask.shape) == 2:
attention_mask = paddle.unsqueeze(attention_mask, axis=[1, 2])
encode_mask = attention_mask + causal_mask
else:
encode_mask = causal_mask
# if cached_kvs are assigned to next step in _prepare_qkv of MultiHeadAttention,
# need to init the global caches here
gen_caches = self._init_generation_caches(input_ids)
logits, cached_kvs = self.model(input_ids,
position_ids,
encode_mask,
use_cache=True,
cache=gen_caches)
next_id = paddle.argmax(logits[:, -1, :], axis=-1).reshape([-1, 1])
####################################
if 'max_dec_len' not in inputs:
max_len = layers.fill_constant([1],
dtype=int_type,
value=self.max_dec_len,
force_cpu=True)
else:
max_len = inputs['max_dec_len']
min_len = layers.fill_constant(shape=[1],
dtype=int_type,
value=self.min_dec_len,
force_cpu=True)
step_idx = layers.fill_constant(shape=[1],
value=0,
dtype='int64',
force_cpu=True)
placehold_ids = layers.fill_constant_batch_size_like(
input=inputs["src_ids"],
value=0,
shape=[-1, 1],
dtype=next_id.dtype)
ids = layers.array_write(next_id, step_idx)
if 'max_dec_len' in inputs:
max_len = paddle.tensor.creation._memcpy(max_len,
place=paddle.CPUPlace())
cond_int = paddle.full([1], 0, dtype=int_type, name="cond_int")
cond = paddle.less_than(step_idx, max_len)
if attention_mask is not None:
append_mask = layers.fill_constant_batch_size_like(
input=next_id,
value=1,
shape=[-1, 1, 1, 1],
dtype=attention_mask.dtype)
while_op = layers.While(cond, is_test=True)
with while_op.block():
pre_ids = layers.array_read(array=ids, i=step_idx)
if attention_mask:
decode_mask = paddle.concat([attention_mask, append_mask],
axis=-1)
tgt_pos = tgt_pos + step_idx
att_mask = (1 - decode_mask) * -1e4
else:
att_mask = None
tgt_pos = None
layers.increment(x=step_idx, value=1.0, in_place=True)
layers.array_write(placehold_ids, i=step_idx, array=ids)
logits, decode_cached_kvs = self.model(pre_ids,
tgt_pos,
att_mask,
use_cache=True,
cache=cached_kvs)
logits = paddle.reshape(logits, shape=(-1, self.vocab_size))
probs = F.softmax(logits / self.temperature)
if self.decoding_strategy.startswith("sampling"):
sampling_ids = layers.sampling_id(probs, dtype="int")
elif self.decoding_strategy.startswith("topk_sampling"):
probs, sampling_ids = self.topk_sampling(probs)
elif self.decoding_strategy.startswith("topp_sampling"):
probs, sampling_ids = self.topp_sampling(probs)
else:
raise ValueError(self.decoding_strategy)
selected_ids = paddle.unsqueeze(sampling_ids, -1)
layers.array_write(selected_ids, i=step_idx, array=ids)
length_cond = paddle.less_than(x=step_idx,
y=max_len,
name="length_cond")
finish_cond = paddle.logical_not(paddle.is_empty(x=selected_ids),
name="finish_cond")
paddle.logical_and(x=length_cond,
y=finish_cond,
out=cond,
name="logical_and_cond")
paddle.assign(layers.cast(cond, dtype='bool'), cond)
if attention_mask:
paddle.assign(decode_mask, attention_mask)
for i in range(len(decode_cached_kvs)):
if self._fuse:
paddle.assign(decode_cached_kvs[i].kv, cached_kvs[i].kv)
else:
paddle.assign(decode_cached_kvs[i].k, cached_kvs[i].k)
paddle.assign(decode_cached_kvs[i].v, cached_kvs[i].v)
ids, _ = layers.tensor_array_to_tensor(ids)
return ids