Question

我想在训练时从每批批次的顺序Keras模型中的退出层中提取并存储退出掩码[1/0的数组]。我想知道在Keras中是否有直接的方法可以做到这一点，或者我是否需要切换到张量流（How to get the dropout mask in Tensorflow）。

将感谢您的帮助！我是TensorFlow和Keras的新手。

我尝试使用了辍学层的几个函数（dropout_layer.get_output_mask（），dropout_layer.get_input_mask（）），但是在调用上一层后得到了None。

model = tf.keras.Sequential()
model.add(tf.keras.layers.Flatten(name="flat", input_shape=(28, 28, 1)))
model.add(tf.keras.layers.Dense(
    512,
    activation='relu',
    name = 'dense_1',
    kernel_initializer=tf.keras.initializers.GlorotUniform(seed=123),
    bias_initializer='zeros'))
dropout = tf.keras.layers.Dropout(0.2, name = 'dropout') #want this layer's mask

model.add(dropout)
x = dropout.output_mask
y = dropout.input_mask
model.add(tf.keras.layers.Dense(
    10,
    activation='softmax',
    name='dense_2',
    kernel_initializer=tf.keras.initializers.GlorotUniform(seed=123),
    bias_initializer='zeros'))

model.compile(...)
model.fit(...)

Answer 1

在Keras中不容易暴露。它一直深入到调用Tensorflow退出。

因此，尽管您使用的是Keras，但它也将是图中可以通过名称获得的张量（找到其名称：In Tensorflow, get the names of all the Tensors in a graph）。

当然，此选项将缺少一些keras信息，您可能必须在Lambda层中执行此操作，以便Keras向张量添加某些信息。而且您必须格外小心，因为即使不进行训练（跳过蒙版），张量也将存在

现在，您还可以使用一种不太hacky的方式，这可能会花费一些时间：

def getMask(x):
    boolMask = tf.not_equal(x, 0)
    floatMask = tf.cast(boolMask, tf.float32) #or tf.float64
    return floatMask

使用Lambda(getMasc)(output_of_dropout_layer)

但是，您将需要功能性的API Sequential，而不是使用Model模型。

inputs = tf.keras.layers.Input((28, 28, 1))
outputs = tf.keras.layers.Flatten(name="flat")(inputs)
outputs = tf.keras.layers.Dense(
    512,
    #    activation='relu', #relu will be a problem here
    name = 'dense_1',
    kernel_initializer=tf.keras.initializers.GlorotUniform(seed=123),
    bias_initializer='zeros')(outputs)

outputs = tf.keras.layers.Dropout(0.2, name = 'dropout')(outputs)
mask = Lambda(getMask)(outputs)
#there isn't "input_mask"


#add the missing relu: 
outputs = tf.keras.layers.Activation('relu')(outputs)
outputs = tf.keras.layers.Dense(
    10,
    activation='softmax',
    name='dense_2',
    kernel_initializer=tf.keras.initializers.GlorotUniform(seed=123),
    bias_initializer='zeros')(outputs)

model = Model(inputs, outputs)
model.compile(...)
model.fit(...)

训练和预测

由于您无法训练遮罩（这没有任何意义），因此它不应作为训练模型的输出。

现在，我们可以尝试一下：

trainingModel = Model(inputs, outputs)    
predictingModel = Model(inputs, [output, mask])

但是在预测中不存在遮罩，因为辍学仅应用于训练。因此，这最终不会给我们带来任何好处。

然后训练的唯一方法是使用虚拟损失和虚拟目标：

def dummyLoss(y_true, y_pred):
    return y_true #but this might evoke a "None" gradient problem since it's not trainable, there is no connection to any weights, etc.    

model.compile(loss=[loss_for_main_output, dummyLoss], ....)

model.fit(x_train, [y_train, np.zeros((len(y_Train),) + mask_shape), ...)

不能保证它们会起作用。

Answer 2

我发现通过简单地扩展所提供的辍学层来做到这一点非常hacker。（几乎来自TF的所有代码。）

class MyDR(tf.keras.layers.Layer):
def __init__(self,rate,**kwargs):
    super(MyDR, self).__init__(**kwargs)

    self.noise_shape = None
    self.rate = rate


def _get_noise_shape(self,x, noise_shape=None):
    # If noise_shape is none return immediately.
    if noise_shape is None:
        return array_ops.shape(x)
    try:
        # Best effort to figure out the intended shape.
        # If not possible, let the op to handle it.
        # In eager mode exception will show up.
        noise_shape_ = tensor_shape.as_shape(noise_shape)
    except (TypeError, ValueError):
        return noise_shape

    if x.shape.dims is not None and len(x.shape.dims) == len(noise_shape_.dims):
        new_dims = []
        for i, dim in enumerate(x.shape.dims):
            if noise_shape_.dims[i].value is None and dim.value is not None:
                new_dims.append(dim.value)
            else:
                new_dims.append(noise_shape_.dims[i].value)
        return tensor_shape.TensorShape(new_dims)

    return noise_shape

def build(self, input_shape):
    self.noise_shape = input_shape
    print(self.noise_shape)
    super(MyDR,self).build(input_shape)

@tf.function
def call(self,input):
    self.noise_shape = self._get_noise_shape(input)
    random_tensor = tf.random.uniform(self.noise_shape, seed=1235, dtype=input.dtype)
    keep_prob = 1 - self.rate
    scale = 1 / keep_prob
    # NOTE: if (1.0 + rate) - 1 is equal to rate, then we want to consider that
    # float to be selected, hence we use a >= comparison.
    self.keep_mask = random_tensor >= self.rate
    #NOTE: here is where I save the binary masks. 
    #the file grows quite big!
    tf.print(self.keep_mask,output_stream="file://temp/droput_mask.txt")

    ret = input * scale * math_ops.cast(self.keep_mask, input.dtype)
    return ret

从keras滤除层中提取滤除蒙版？

2 个答案:

训练和预测