为什么在我的张量流代码中总是得到操作属性错误

我试着用tensorflow建立一个神经网络的隐藏层,但是我一直收到错误信息

“Operation”对象没有“dtype”属性。

这是代码抛出错误的地方:

codings = tf.layers.dense(X, n_hidden, name="hidden")

import numpy as np
import tensorflow as tf
from PIL import Image

data = []
test2 = Image.open("./ters/test2.jpg")
prepared_data = np.asarray(test2.resize((800, 1000), Image.ANTIALIAS))
data.append(prepared_data)
data = np.asarray(data)

saver = tf.train.import_meta_graph("./my_model.ckpt.meta")

batch_size, height, width, channels = data.shape

n_hidden = 400
X = tf.get_default_graph().get_operation_by_name("Placeholder")
training_op = tf.get_default_graph().get_operation_by_name("train/Adam")
codings = tf.layers.dense(X, n_hidden, tf.float32)

n_iterations = 5

with tf.Session() as sess:
saver.restore(sess, "./my_model.ckpt")
sess.run(training_op)
test_img = codings.eval(feed_dict={X: X_test})

print(test_img)

注: 我已经训练过这个模型并命名了它 我的模型.ckpt 这是错误消息:

Traceback (most recent call last):
 File "using_img_cleaner.py", line 36, in <module>
    codings = tf.layers.dense(X, n_hidden, tf.float32)
  File "/home/exceptions/env/lib/python3.5/site-packages/tensorflow/python/layers/core.py", line 250, in dense
    dtype=inputs.dtype.base_dtype,
AttributeError: 'Operation' object has no attribute 'dtype'