无法将数据馈入张量流图

时间:2019-03-03 13:56:14

标签: python tensorflow mnist

我已经使用tutorial中提供的脚本MNISTmnist_3.1_convolutional_bigger_dropout.py数据集上训练了神经网络模型。

我想在自定义数据集上测试经过训练的模型,因此我编写了一个小脚本predict.py,该脚本加载了经过训练的模型并将数据提供给它。我尝试了2种预处理图像的方法,以使其与MNIST格式兼容。

  • 方法1 :将图像调整为28x28
  • 方法2 :使用了here中提到的技术

这两种方法均会导致错误

  

InvalidArgumentError(请参阅上面的回溯):您必须使用dtype float输入占位符张量“ Placeholder_2”的值

predict.py

# Importing libraries
from scipy.misc import imread
import tensorflow as tf
import numpy as np
import cv2 as cv
import glob

from test import imageprepare

files = glob.glob('data2/*.*')
#print(files)

# Method 1
'''
img_data = []
for fl in files:
    img = imageprepare(fl)
    img = img.reshape(img.shape[0], img.shape[1], 1)
    img_data.append(img)
'''

# Method 2
dig_cont = [cv.imread(fl, 0) for fl in files]
#print(len(dig_cont))

img_data = []
for i in range(len(dig_cont)):
    img = cv.resize(dig_cont[i], (28, 28))
    img = img.reshape(img.shape[0], img.shape[1], 1)
    img_data.append(img)


print("Restoring Model ...")

sess = tf.Session()

# Step-1: Recreate the network graph. At this step only graph is created.
tf_saver = tf.train.import_meta_graph('model/model.meta')

# Step-2: Now let's load the weights saved using the restore method.
tf_saver.restore(sess, tf.train.latest_checkpoint('model'))

print("Model restored")

x = tf.get_default_graph().get_tensor_by_name('X:0')
print('x :', x.shape)
y = tf.get_default_graph().get_tensor_by_name('Y:0')
print('y :', y.shape)

dict_data = {x: img_data}

result = sess.run(y, feed_dict=dict_data)
print(result)
print(result.shape)

sess.close()

1 个答案:

答案 0 :(得分:0)

问题已解决,我忘记传递变量pkeep的值。我必须进行以下更改才能使其正常工作。

dict_data = {x: img_data, pkeep: 1.0}

代替

dict_data = {x: img_data}