如何在 Tensorflow 中检查张量是否为空

Question

我的部分代码如下：

class_label = tf.placeholder(tf.float32, [None], name="condition_checking")
row_index = tf.where(class_label > 0)

我想检查一下row_index什么时候为空写下面的

loss_f_G_filtered = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(
    logits=y1_filterred, labels=y__filtered), name="filtered_reg")

if row_index == []:
  loss_f_G_filtered = tf.constant(0, tf.float32)

但是，我不知道如何检查 row_index 是否为空张量。

Answer 1

您可以使用 tf.cond:

idx0 = tf.shape(row_index)[0]
loss_f_G_filtered = tf.cond(idx0 == 0,
                            lambda: tf.constant(0, tf.float32),
                            lambda: ...another function...)

Answer 2

    loss_f_G = 

tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=y1_filterred, labels=y__filtered), name = "filtered_reg")
    idx0 = tf.shape(row_index)[0]
    loss_f_G_filtered = tf.cond(tf.cast(idx0 == 0, tf.bool), lambda: tf.constant(0, tf.float32), lambda:loss_f_G)

问题是 idx0 == 0 永远不会为真，即使 row_index = [].

Answer 3

is_empty = tf.equal(tf.size(row_index), 0)

如何在 Tensorflow 中检查张量是否为空

How to check if a tensor is empty in Tensorflow

tensorflow

tensor