Question

此Tensorflow脚本训练了逻辑回归模型，但出现错误。此代码段摘自《用于深度学习的Tensorflow》（第74页）一书。

with tf.name_scope("placeholders"):
    x = tf.compat.v1.placeholder(tf.float32, (N,2))
    y = tf.compat.v1.placeholder(tf.float32, (N,))
with tf.name_scope("weights"):
    W = tf.Variable(tf.random.normal((2,1)))
    b = tf.Variable(tf.random.normal((1,)))
with tf.name_scope("prediction"):
    y_logit = tf.squeeze(tf.matmul(x,W)+b)
    y_one_prob = tf.sigmoid(y_logit)
    y_pred = tf.round(y_one_prob)
with tf.name_scope("loss"):
    entropy = tf.compat.v1.nn.sigmoid_cross_entropy_with_logits(logits=y_logit, labels=y)
    l = tf.reduce_sum(entropy)
with tf.name_scope("optim"):
    train_op = tf.compat.v1.train.AdamOptimizer(.01).minimize(l)

    merged = tf.compat.v1.summary.merge_all()
    train_writer = tf.compat.v1.summary.FileWriter("/tmp/logistic-train", tf.compat.v1.get_default_graph())

n_steps = 10000
with tf.compat.v1.Session() as sess:
    sess.run(tf.compat.v1.global_variables_initializer())
    for i in range(n_steps):
        feed_dict = {x: x_np, y: y_np}
        _, summary, loss = sess.run([train_op, merged, l], feed_dict=feed_dict)
        print("Step %d, loss: %f" % (i, loss))
        train_writer.add_summary(summary, i)

错误消息是：

...
  File "/Users/wkgreat/Library/Python/3.6/lib/python/site-packages/tensorflow_core/python/client/session.py", line 263, in for_fetch
    (fetch, type(fetch)))
TypeError: Fetch argument None has invalid type <class 'NoneType'>

错误原因是什么？

Tensorflow Logistic回归TypeError：获取参数None具有无效的类型<class'NoneType'>

0 个答案: