实际上，为 Embedding 层设置 mask_zero=True 不会导致返回零向量。相反，嵌入层的行为不会改变，它会返回索引为零的嵌入向量。您可以通过检查嵌入层权重来确认这一点（即在您提到的示例中它将是m.layers[0].get_weights()）。相反，它会影响后续层（例如 RNN 层）的行为。
如果你检查嵌入层的源代码，你会看到一个名为compute_mask的方法：
def compute_mask(self, inputs, mask=None):
if not self.mask_zero:
return None
output_mask = K.not_equal(inputs, 0)
return output_mask
此输出掩码将作为mask 参数传递给支持掩码的以下层。这已经在基础层的__call__方法中实现了，Layer：
# Handle mask propagation.
previous_mask = _collect_previous_mask(inputs)
user_kwargs = copy.copy(kwargs)
if not is_all_none(previous_mask):
# The previous layer generated a mask.
if has_arg(self.call, 'mask'):
if 'mask' not in kwargs:
# If mask is explicitly passed to __call__,
# we should override the default mask.
kwargs['mask'] = previous_mask
这使得下面的层忽略（即在他们的计算中不考虑）这个输入步骤。这是一个最小的例子：
data_in = np.array([
[1, 0, 2, 0]
])
x = Input(shape=(4,))
e = Embedding(5, 5, mask_zero=True)(x)
rnn = LSTM(3, return_sequences=True)(e)
m = Model(inputs=x, outputs=rnn)
m.predict(data_in)
array([[[-0.00084503, -0.00413611, 0.00049972],
[-0.00084503, -0.00413611, 0.00049972],
[-0.00144554, -0.00115775, -0.00293898],
[-0.00144554, -0.00115775, -0.00293898]]], dtype=float32)
如您所见，LSTM 层的第二个和第四个时间步的输出分别与第一个和第三个时间步的输出相同。这意味着这些时间步已被屏蔽。
更新：在计算损失时也会考虑掩码，因为损失函数在内部被扩充以支持使用weighted_masked_objective 进行掩码：
def weighted_masked_objective(fn):
"""Adds support for masking and sample-weighting to an objective function.
It transforms an objective function `fn(y_true, y_pred)`
into a sample-weighted, cost-masked objective function
`fn(y_true, y_pred, weights, mask)`.
# Arguments
fn: The objective function to wrap,
with signature `fn(y_true, y_pred)`.
# Returns
A function with signature `fn(y_true, y_pred, weights, mask)`.
"""
when compiling the model:
weighted_losses = [weighted_masked_objective(fn) for fn in loss_functions]
您可以使用以下示例验证这一点：
data_in = np.array([[1, 2, 0, 0]])
data_out = np.arange(12).reshape(1,4,3)
x = Input(shape=(4,))
e = Embedding(5, 5, mask_zero=True)(x)
d = Dense(3)(e)
m = Model(inputs=x, outputs=d)
m.compile(loss='mse', optimizer='adam')
preds = m.predict(data_in)
loss = m.evaluate(data_in, data_out, verbose=0)
print(preds)
print('Computed Loss:', loss)
[[[ 0.009682 0.02505393 -0.00632722]
[ 0.01756451 0.05928303 0.0153951 ]
[-0.00146054 -0.02064196 -0.04356086]
[-0.00146054 -0.02064196 -0.04356086]]]
Computed Loss: 9.041069030761719
# verify that only the first two outputs
# have been considered in the computation of loss
print(np.square(preds[0,0:2] - data_out[0,0:2]).mean())
9.041070036475277