张量流变量分配广播

Question

tensorflow中有没有什么方法可以实现对矩阵的广播赋值(tf.Variable) 类似于下面的代码....

a    = tf.Variable(np.zeros([10,10,10,10], np.int32))

# creating a mask and trying to assign the 2nd, 3rd dimension of a
mask = tf.ones([10,10])

# 1) which is work in this case, but only assign one block
op = a[0,:,:,0].assign(mask)

# 2) attempting to broadcasting while not work, size mismatch
op = a[0].assign(mask)

对我来说，当前的解决方案可能会迭代所有其他维度，但可能会遇到嵌套循环，如 1) 或者必须有更聪明的方法，谢谢！

Answer 1

不是通用解决方案（大量硬编码张量形状），但希望这能为您的示例提供要点：

a = tf.Variable(np.zeros([10,10,10,10], np.int32))
mask = tf.ones([10,10],dtype=tf.int32)
mask_reshaped = tf.reshape(mask,[1,10,10,1]) # make the number of dims match
mask_broadcast = tf.tile(mask_reshaped, [10, 1, 1, 10]) # do the actual broadcast
op = a.assign(mask_broadcast)

张量流变量分配广播

tensorflow variable assign broadcasting

python

broadcasting

assign

tensorflow