Question

我想在tf keras中采样softmax损失。我通过子类化keras Model定义了自己的模型。在初始化中，我指定需要的层，包括最后一个Dense投影层。但是，在训练中不应调用此Dense层，因为我想对softmax进行采样，而仅使用其权重和偏差。然后，我定义损耗函数：

class SampledSoftmax:
    def init( self,
              num_sampled,
              num_classes,
              projection,
              bias,
              hidden_size):
        self.weights = tf.transpose(projection)
        self.bias = bias
        self.num_classes = num_classes
        self.num_sampled = num_sampled
        self.hidden_size = hidden_size

    def call(self, y_true, input):
        """ reshaping of y_true and input to make them fit each other """
        input = tf.reshape(input, (-1,self.hidden_size))
        y_true = tf.reshape(y_true, (-1,1))

        return tf.nn.sampled_softmax_loss(
                   weights=self.weights,
                   biases=self.bias,
                   labels=y_true,
                   inputs=input,
                   num_sampled=self.num_sampled,
                   num_classes=self.num_classes,
                   partition_strategy='div')

它需要初始化所需的参数，而类调用将是所需的采样softmax损失函数。要注意的是，要增加模型编译的损失，我需要最后一次密集的权重等。但是1）在训练中，模型中不包含Dense，2）即使包含，Dense层也只会与输入连接，因此在我的自定义模型调用中会得到其输入尺寸等。简而言之，权重等在编译模型之前将不可用。谁能提供一些帮助以指出正确的方向？

现在，使它失败的代码。我首先将模型分类如下：

class LanguageModel(tf.keras.Model):
    def __init__(self, 
                 vocal_size=15003, 
                 embedding_size=512
                 input_len=64)
       self.embedding = Embedding(vocal_size, embedding_size, 
                                  input_length=input_len)
       self.lstm = LSTM(hidden_size, return_sequences=True)
       self.dense = Dense(vocal_size, activation='softmax')

   def call(self, inputs, training=False):
       emb_out = self.embedding(inputs)
       lstm_out = self.lstm(embrace_out)
       res = self.dense(lstm_out)
       if (training)
           ''' shouldn't use the last dense as we want to do sampling'''
           return lstm_out
       return res

然后按照以下步骤训练模型

sampled_loss = SampledSoftmax(num_sampled, vocal_size, 
                   model.dense.kernel, model.dense.bias,
                   hidden_size)

model.compile(optimizer=tf.train.RMSPropOptimizer(lr),
              loss=sampled_loss)

但是它将失败，因为我无法解决它，因为由于在编译模型时无法访问model.dense.kernel，因此尚未在调用方法中初始化密集层。错误消息如下：

Traceback (most recent call last):
  File "/usr/lib/python3.5/runpy.py", line 184, in _run_module_as_main
    "__main__", mod_spec)
  File "/usr/lib/python3.5/runpy.py", line 85, in _run_code
    exec(code, run_globals)
  File "/home/wuxinyu/workspace/nlu/lm/main.py", line 72, in <module>
    train_main()
  File "/home/wuxinyu/workspace/nlu/lm/main.py", line 64, in train_main
    train_model.build_lm_model()
  File "/home/wuxinyu/workspace/nlu/lm/main.py", line 26, in build_lm_model
self.model.dense.kernel,
AttributeError: 'Dense' object has no attribute 'kernel'

顺便说一句，上面定义的损失将在如下所示的小型测试案例中起作用。

x = Input(shape=(10,), name='input_x')
emb_out = Embedding(10000,200,input_length=10)(x)
lstm_out = LSTM(200, return_sequences=True)(emb_out)

dense = Dense(10000, activation='sigmoid')
output = dense(lstm_out)

sl = SampledSoftmax(10, 10000, dense.kernel, dense.bias)

model = Model(inputs=x, outputs=lstm_out)
model.compile(optimizer='adam', loss=sl)
model.summary()
model.fit(dataset, epochs=20, steps_per_epoch=5)

张量流keras中的softmax采样

0 个答案: