尝试在从.pb文件加载的网络上运行推理时出现占位符错误

Question

我从一个.pb文件中加载了一个AlexNet，并试图在推理模式下运行它，但是出现了这个错误：

InvalidArgumentError (see above for traceback): You must feed a value for placeholder tensor 'graph_def/Placeholder' with dtype float and shape [?,227,227,3]
     [[Node: graph_def/Placeholder = Placeholder[dtype=DT_FLOAT, shape=[?,227,227,3], _device="/job:localhost/replica:0/task:0/device:CPU:0"]()]]

这是我的代码：

import tensorflow as tf
from tensorflow.python.platform import gfile
import numpy as np
import cv2

#mean of imagenet dataset in BGR
imagenet_mean = np.array([104., 117., 124.], dtype=np.float32)

image = cv2.imread("test.jpg")

GRAPH_PB_PATH = 'alexnet_frozen.pb'

#placeholder for input and dropout rate
x = tf.placeholder(tf.float32, [1, 227, 227, 3])
keep_prob = tf.placeholder(tf.float32)


with tf.Session() as sess:
    with gfile.FastGFile(GRAPH_PB_PATH, 'rb') as f:
        graph_def = tf.GraphDef()
        graph_def.ParseFromString(f.read())
        sess.graph.as_default()
        tf.import_graph_def(graph_def, name='graph_def')

    # Initialize all variables
    sess.run(tf.global_variables_initializer())

    # Convert image to float32 and resize to (227x227)
    img = cv2.resize(image.astype(np.float32), (227, 227))

    # Subtract the ImageNet mean
    img -= imagenet_mean

    # Reshape as needed to feed into model
    img = img.reshape((1, 227, 227, 3))

    softmax_op = sess.graph.get_operation_by_name("graph_def/Softmax")

    # Run the session and calculate the class probability
    probs = sess.run(softmax_op, feed_dict={x: img, keep_prob: 1})

以某种方式，除了我定义的两个占位符外，还有第三个占位符，其形状为[-1, 227, 227, 3]。在运行时，我可以在会话图的nodes_by_id列表中看到它。但是我不知道它来自哪里，或者是什么导致我的错误。