tensorflow - 无法使用 tensorflow 创建数组

Question

在将batch_xs输入x时，我 reshape 了batch_xs，因为BATCH_SIZE为1。 这是我的来源。 我不确定是什么导致了 ValueError。

with tf.name_scope("input") as scope:
    x = tf.placeholder(tf.float32, shape=[1, 784])

BATCH_SIZE = 1
DROP_OUT_RATE = 0.4
EPOCH = 1
MEMORIZE = 10
accuracy_array = []
loss = tf.nn.l2_loss(y - x) / BATCH_SIZE
train_step = tf.train.AdamOptimizer(1e-4).minimize(loss)

mnist = input_data.read_data_sets('MNIST_data', one_hot=True)
mnist_list = make_mnist_train_list(55000, 10)
test_list = make_mnist_test_list(5000, 10)
sess = tf.Session()
sess.run(tf.initialize_all_variables())

for i in range(EPOCH):
    for j in range(5500/BATCH_SIZE):
        batch_xs = tf.reshape(mnist_list[0][j*BATCH_SIZE:j*BATCH_SIZE+1], [1, 784])
        sess.run(train_step, feed_dict={x: batch_xs, keep_prob: (1.0 - DROP_OUT_RATE), r_keep_prob: (1.0 - DROP_OUT_RATE)})
        if (i +1)% MEMORIZE == 0:
            accuracy_array.append(loss.eval(session=sess, feed_dict={x: batch_xs, keep_prob: 1.0, r_keep_prob: 1.0}))
            print(accuracy_array[ int(math.floor((i+1)/MEMORIZE -1))])

这给了我值错误，这对我来说没有意义。

ValueError:参数必须是稠密张量

Answer 1

来自文档here :

Each key in feed_dict can be one of the following types:

• If the key is a Tensor, the value may be a Python scalar, string, list, or numpy ndarray that can be converted to the same dtype as that tensor. Additionally, if the key is a placeholder, the shape of the value will be checked for compatibility with the placeholder.

• If the key is a SparseTensor, the value should be a SparseTensorValue.

可以用作 feed_dict 中键的“值”的类型应该是 Python 原始类型或 numpy 数组。您正在使用 tf.reshape 的结果，它是 TensorFlow 张量类型。如果您想提供重新整形的数组，您可以简单地使用np.reshape。