tf怎么使用if

tf中用if是不行的，用==也是不行的

因为是先建图，建图的时候也只是用tensor来进行判断

You're correct that the if statement doesn't work here, because the condition is evaluated at graph construction time, whereas presumably you want the condition to depend on the value fed to the placeholder at runtime. (In fact, it will always take the first branch, because condition > 0evaluates to a Tensor, which is "truthy" in Python.)

To support conditional control flow, TensorFlow provides the tf.cond() operator, which evaluates one of two branches, depending on a boolean condition. To show you how to use it, I'll rewrite your program so that condition is a scalar tf.int32 value for simplicity:

x = tf.placeholder(tf.float32, shape=[None, ins_size**2*3], name="x_input")
condition = tf.placeholder(tf.int32, shape=[], name="condition")
W = tf.Variable(tf.zeros([ins_size**2 * 3, label_option]), name="weights")
b = tf.Variable(tf.zeros([label_option]), name="bias")

y = tf.cond(condition > 0, lambda: tf.matmul(x, W) + b, lambda: tf.matmul(x, W) - b)

这是求if条件下变量的值，如果想if判断自后运行一段函数呢？

现在想到的办法是：无论要不要求，都先求出这个函数的返回值，然后if判断要不要用