python-3.x - 如何在 while 循环中打印张量的值？

Question

我对 tensorflow 很陌生，我搞不懂这个。

我有这个 while 循环:

def process_tree_tf(n_child, reprs, weights, bias, embed_dim, activation = tf.nn.relu):
    n_child, reprs = n_child, reprs
    parent_idxs = generate_parents_numpy(n_child)
    loop_idx = reprs.shape[0] - 1
    loop_vars = loop_idx, reprs, parent_idxs, weights, embed_dim

    def  loop_condition(loop_ind, *_):
        return tf.greater(0, loop_idx)

    def loop_body(loop_ind, reprs, parent_idxs, weights, embed_dim):
        x = reprs[loop_ind]
        x_expanded = tf.expand_dims(x, axis=-1)
        w = weights
        out = tf.squeeze(tf.add(tf.matmul(x_expanded,w,transpose_a=True), bias))
        activated = activation(out)
        par_idx = parent_idxs[loop_ind]
        reprs = update_parent(reprs, par_idx, embed_dim, activated)
        reprs = tf.Print(reprs, [reprs]) #This doesn't work
        loop_ind = loop_ind-1
        return loop_ind, reprs, parent_idxs, weights, embed_dim

    return tf.while_loop(loop_condition, loop_body, loop_vars)

我是这样评价的:

embed_dim = 2
hidden_dim = 2
n_nodes = 4
batch = 2
reprs = np.ones((n_nodes, embed_dim+hidden_dim))
n_child = np.array([1, 1, 1, 0])
weights = np.ones((embed_dim+hidden_dim, hidden_dim))
bias = np.ones(hidden_dim)
with tf.Session() as sess:
    _, r, *_ = process_tree_tf(n_child, reprs,  weights, bias, embed_dim, activation=tf.nn.relu)
    print(r.eval())

我想在 while 循环中检查 reprs 的值，但是 tf.Print 似乎不起作用，并且 print只是告诉我它是一个张量并给我它的形状。我该怎么做？

非常感谢!

Answer 1

看看这个网页:https://www.tensorflow.org/api_docs/python/tf/Print

您可以看到 tf.Print 是一个身份运算符，在评估时具有打印数据的副作用。因此，您应该使用这一行来打印:

reprs = tf.Print(reprs, [reprs])

希望这对您有所帮助，祝您好运!