2017-04-26 107 views
1

我有以下功能:InvalidArgumentError上SOFTMAX在tensorflow

def forward_propagation(self, x): 
       # The total number of time steps 
       T = len(x) 
       # During forward propagation we save all hidden states in s because need them later. 
       # We add one additional element for the initial hidden, which we set to 0 
       s = tf.zeros([T+1, self.hidden_dim]) 
       # The outputs at each time step. Again, we save them for later. 
       o = tf.zeros([T, self.word_dim]) 


       a = tf.placeholder(tf.float32) 
       b = tf.placeholder(tf.float32) 
       c = tf.placeholder(tf.float32) 

       s_t = tf.nn.tanh(a + tf.reduce_sum(tf.multiply(b, c))) 
       o_t = tf.nn.softmax(tf.reduce_sum(tf.multiply(a, b))) 
       # For each time step... 
       with tf.Session() as sess: 
         s = sess.run(s) 
         o = sess.run(o) 
         for t in range(T): 
           # Note that we are indexing U by x[t]. This is the same as multiplying U with a one-hot vector. 
           s[t] = sess.run(s_t, feed_dict={a: self.U[:, x[t]], b: self.W, c: s[t-1]}) 
           o[t] = sess.run(o_t, feed_dict={a: self.V, b: s[t]}) 
       return [o, s] 

self.U,self.V,和self.W是numpy的阵列。我试图让SOFTMAX上

o_t = tf.nn.softmax(tf.reduce_sum(tf.multiply(a, b))) 

图,它给我的错误在这条线:

o[t] = sess.run(o_t, feed_dict={a: self.V, b: s[t]}) 

的错误是:

InvalidArgumentError (see above for traceback): Expected begin[0] == 0 (got -1) and size[0] == 0 (got 1) when input.dim_size(0) == 0
[[Node: Slice = Slice[Index=DT_INT32, T=DT_INT32, _device="/job:localhost/replica:0/task:0/cpu:0"](Shape_1, Slice/begin, Slice/size)]]

如何,我应该得到SOFTMAX在tensorflow?

回答

2

问题出现是因为您在tf.nn.softmax的参数上致电tf.reduce_sum。结果,softmax函数失败,因为标量不是有效的输入参数。您的意思是使用tf.matmul而不是tf.reduce_sumtf.multiply的组合吗?

编辑:开箱即用的Tensorflow不提供等效的np.dot。如果要计算矩阵和向量的点积,则需要明确地总和索引:

# equivalent to np.dot(a, b) if a.ndim == 2 and b.ndim == 1 
c = tf.reduce_sum(a * b, axis=1) 
+0

我正在尝试制作a和b的点生成。 – yusuf

+1

在这种情况下,您应该使用'tf.matmul'(如果两个参数都是矩阵),或者您必须指定要求和的轴。例如,如果'a'具有形状'(n,k)'而'b'具有形状'(k,)',则可以使用'tf.reduce_sum(a * b,axis = 1)'计算点积。 –

+0

tm matmul给了我这个错误:形状必须是等级2,但是'MatMul'(op:'MatMul')的等级为1,输入形状为[8000,100],[100]。我已经使用了o [t] .assign(tf.nn.softmax(tf.matmul(self.V,s [t]))) – yusuf

相关问题