Question

很抱歉出现一个小问题：

拥有在fit_generator模式下训练的NN，像这样：

Lambda(...)

或

Dense(...)

和自定义损失函数，什么是输入张量？如果是Lambda图层，我是否正确期望（批处理大小，上一层的输出）？如果自定义损失函数如下所示，它将是相同的（批大小，数据）吗？

triplet_loss(y_true, y_pred)

y_true，y_pred是（batch，上一层的输出）和（batch，我们馈送到NN的真实“预期”数据）格式吗？

Answer 1

我可能会复制密集层。代替具有2个128个单位的层，而具有4个64个单位的层。结果是相同的，但是您将能够更好地执行叉积。

from keras.models import Model

#create dense layers and store their output tensors, they use the output of models 1 and to as input    
d1 = Dense(64, ....)(Model_1.output)   
d2 = Dense(64, ....)(Model_1.output)   
d3 = Dense(64, ....)(Model_2.output)   
d4 = Dense(64, ....)(Model_2.output)   

cross1 = Lambda(myFunc, output_shape=....)([d1,d4])
cross2 = Lambda(myFunc, output_shape=....)([d2,d3])

#I don't really know what kind of "merge" you want, so I used concatenate, there are 
Add, Multiply and others....
output = Concatenate()([cross1,cross2])
#use the "axis" attribute of the concatenate layer to define better which axis will 
be doubled due to the concatenation    

model = Model([Model_1.input,Model_2.input], output)

现在，使用lambda函数：

import keras.backend as K

def myFunc(x):
    return x[0] * x[1]

Answer 2

自定义损失函数，什么是输入张量？

这取决于您如何定义模型outputs。

例如，让我们定义一个简单的模型，使输入保持不变。

model = Sequential([Lambda(lambda x: x, input_shape=(1,))])

让我们使用虚拟输入X和标签Y

x = [[0]]
x = np.array(x)

y = [[4]]
y = np.array(y)

如果我们的自定义损失功能如下所示

def mce(y_true, y_pred):
  print(y_true.shape)
  print(y_pred.shape)
  return K.mean(K.pow(K.abs(y_true - y_pred), 3))

model.compile('sgd', mce)

然后我们可以看到y_true和y_pred的形状

y_true:  (?, ?)
y_pred:  (?, 1)

但是，对于triplet loss，也可以像这样接收损失函数的输入-

ALPHA = 0.2
def triplet_loss(x):
    anchor, positive, negative = x

    pos_dist = tf.reduce_sum(tf.square(tf.subtract(anchor, positive)), 1)
    neg_dist = tf.reduce_sum(tf.square(tf.subtract(anchor, negative)), 1)

    basic_loss = tf.add(tf.subtract(pos_dist, neg_dist), ALPHA)
    loss = tf.reduce_mean(tf.maximum(basic_loss, 0.0), 0)

    return loss
# Source: https://github.com/davidsandberg/facenet/blob/master/src/facenet.py

def build_model(input_shape):
    # Standardizing the input shape order
    K.set_image_dim_ordering('th')

    positive_example = Input(shape=input_shape)
    negative_example = Input(shape=input_shape)
    anchor_example = Input(shape=input_shape)

    # Create Common network to share the weights along different examples (+/-/Anchor)
    embedding_network = faceRecoModel(input_shape)

    positive_embedding = embedding_network(positive_example)
    negative_embedding = embedding_network(negative_example)
    anchor_embedding = embedding_network(anchor_example)

    loss = merge([anchor_embedding, positive_embedding, negative_embedding],
                 mode=triplet_loss, output_shape=(1,))
    model = Model(inputs=[anchor_example, positive_example, negative_example],
                  outputs=loss)
    model.compile(loss='mean_absolute_error', optimizer=Adam())

    return model

Keras图层和自定义功能的输入是什么？

2 个答案: