首页 文章

如何在张量流中测试模型?

提问于
浏览
1

我正在学习本教程:

https://www.tensorflow.org/versions/r0.9/tutorials/mnist/beginners/index.html#mnist-for-ml-beginners

我希望能够做的是传入一个测试图像x - 作为一个numpy数组,并查看最终的softmax分类值 - 可能是另一个numpy数组 . 我在网上找到的关于测试张量流模型的一切都可以通过传入测试值和测试标签以及输出精度来实现 . 就我而言,我想根据测试值输出模型标签 .

这就是我尝试的:导入tensorflow作为tf导入numpy作为np从skimage导入颜色,io

from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)

x = tf.placeholder(tf.float32, [None, 784])
W = tf.Variable(tf.zeros([784, 10]))
b = tf.Variable(tf.zeros([10]))
y = tf.nn.softmax(tf.matmul(x, W) + b)
y_ = tf.placeholder(tf.float32, [None, 10])
cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(y), reduction_indices=[1]))
train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)
init = tf.initialize_all_variables()
sess = tf.Session()
sess.run(init)

for i in range(1000):
  batch_xs, batch_ys = mnist.train.next_batch(100)
  sess.run(train_step, feed_dict={x: batch_xs, y_: batch_ys})

#so now its trained successfully, and W and b should be the stored "model" 

#now to load in a test image

greyscale_test = color.rgb2gray(io.imread('4.jpeg'))
greyscale_expanded = np.expand_dims(greyscale_test,axis=0)    #now shape (1,28,28)
x = np.reshape(greyscale_expanded,(1,784))     #now same dimensions as mnist.train.images

#initialize the variable
init_op = tf.initialize_all_variables()

#run the graph
with tf.Session() as sess:
    sess.run(init_op) #execute init_op
    print (sess.run(feed_dict={x:x}))    #this is pretty much just a shot in the dark. What would go here?

现在它导致了这个:

TypeError                                 Traceback (most recent call last)
<ipython-input-116-f232a17507fb> in <module>()
     36     sess.run(init_op) #execute init_op
---> 37     print (sess.run(feed_dict={x:x}))    #this is pretty much just a shot in the dark. What would go here?

TypeError: unhashable type: 'numpy.ndarray'

所以在训练时,sess.run会传递一个train_step和一个feed_dict . 当我试图评估张量x时,这是否会在Feed字典中出现?我甚至会使用sess.run(看似我必须),但是train_step会是什么?有“test_step”或“evaluate_step”吗?

2 回答

  • 3

    你得到 TypeError 因为你使用(可变) numpy.ndarray 作为你的字典的键,但键应该是 tf.placeholder ,值是 numpy 数组 .

    以下调整修复了此问题:

    x_placeholder = tf.placeholder(tf.float32, [None, 784])
    # ...
    x = np.reshape(greyscale_expanded,(1,784))
    # ...
    print(sess.run([inference_step], feed_dict={x_placeholder:x}))
    

    如果您只想对模型执行推理,则会打印带有预测的 numpy 数组 .

    如果您想评估您的模型(例如计算准确度),您还需要输入相应的地面实况标签 y ,如下所示:

    accuracy = sess.run([accuracy_op], feed_dict={x_placeholder:x, y_placeholder:y}
    

    在您的情况下, accuracy_op 可以定义如下:

    correct_predictions = tf.equal(tf.argmax(predictions, 1), tf.cast(labels, tf.int64))
    accuracy_op = tf.reduce_mean(tf.cast(correct_predictions, tf.float32))
    

    这里, predictions 是模型的输出张量 .

  • 0

    你的tf.Session.run op需要一个提取tf.Session.run(fetches,feed_dict = None,options = None,run_metadata = None)

    https://www.tensorflow.org/versions/r0.9/api_docs/python/client.html#session-management

    print(sess.run(train_step,feed_dict = {x:x}))但是它还需要一个feed_dict给y_

    你是什么意思:

    打印我们采样的随机值

相关问题