4

I am learning TensorFLow. So to understand how to make something, I tried to copy some code from a source and execute it. But I'm hitting an error message. So I tried some solution from this website but it does not work (I kept my test in comments). 

    """programme 1 """
import tensorflow as tf 
import numpy as np

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, 28, 28, 1]) #28 * 28 taille image 1 = 1pixel car noir et blanc "X" valeur
W = tf.Variable(tf.zeros([784, 10])) # 28*28 = 784 , 10 -> 0 à 9  "W" = weight = poid
b = tf.Variable(tf.zeros([10])) #chiffre de 0 à 9 a reconnaitre "b" = constante 
init = tf.initialize_all_variables()

#model
Y = tf.nn.softmax(tf.matmul(tf.reshape(X,[-1, 784]), W) + b) #fonction "matmul": produit matriciel "-1": reussite obligatoire

#Place holder
Y_ = tf.placeholder(tf.float32, [None, 10])

#loss function
cross_entropy = -1 * tf.reduce_sum(Y_ * tf.log(Y)) #formule

# % of correct annwer found in batch
is_correct = tf.equal(tf.argmax(Y,1),tf.argmax(Y_,1))
accuracy = tf.reduce_mean(tf.cast(is_correct,tf.float32))

#training step
optimizer = tf.train.GradientDescentOptimizer(0.003) #petit pas
train_step = optimizer.minimize(cross_entropy)

sess = tf.Session()
sess.run(init) 

for i in range(10000):
    #load batch of image and ocrrects answer
    batch_X, batch_Y = mnist.train.next_batch(100)
    batch_X = np.reshape(batch_X, (-1, 784))
    #batch_Y = np.reshape(batch_Y, (-1, 784))

    train_data = {X: batch_X, Y_: batch_Y}

    #train
    sess.run(train_step, feed_dict=train_data)

    a,c = sess.run([accuracy,cross_entropy],feed = train_data)

    test_data = {X:mnist.test.images, Y_:mnist.test.labels}
    a,c = sess.run([accuracy,cross_entropy],feed = test_data)

the log :

    Traceback (most recent call last):
  File "d:\tensorflow\test1.py", line 46, in <module>
    sess.run(train_step, feed_dict=train_data)
  File "C:\Users\Proprietaire\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\client\session.py", line 895, in run
    run_metadata_ptr)
  File "C:\Users\Proprietaire\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\client\session.py", line 1100, in _run
    % (np_val.shape, subfeed_t.name, str(subfeed_t.get_shape())))
ValueError: Cannot feed value of shape (100, 784) for Tensor 'Placeholder:0', which has shape '(?, 28, 28, 1)'
2017-08-30 19:07:37.406994: W C:\tf_jenkins\home\workspace\rel-win\M\windows\PY\35\tensorflow\core\platform\cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX instructions, but these are available on your machine and could speed up CPU computations.

line 46 is 

sess.run(train_step, feed_dict=train_data)

What can I do to resolve this error?

Zev
  • 3,423
  • 1
  • 20
  • 41
Oytoch
  • 153
  • 1
  • 1
  • 15

3 Answers3

1

You are getting that error because there is a mismatch between the shape of what you are feeding in and what the TensorFlow is expecting. To fix the issue, you might want to reshape your data at placeholder:0 which is batch_X to (?, 28, 28, 1). For example, you would do the following:

batch_X = np.reshape(batch_X, (-1, 28, 28, 1))
Zev
  • 3,423
  • 1
  • 20
  • 41
Heapify
  • 2,581
  • 17
  • 17
0

You need to reshape X.

    X = tf.placeholder(tf.float32 , [None ,28 , 28 , 1])
    X = tf.reshape(X , [-1 , 784])
Karthik ziffer
  • 11
  • 4
-1

When you define a placeholder in TensorFlow, the shape of the input during the session should be the same as the shape of the placeholder.

In batch_X, batch_Y = mnist.train.next_batch(100), the batch_x is a 2D array of pixel values, which will have a shape of [batch_size, 28*28].

In X = tf.placeholder(tf.float32,[None, 28, 28, 1]), the input placeholder is defined to have a 4D shape of [batch_size, 28, 28, 1]

You can either 1) reshape batch_x before the feeding to TensorFlow. e.g.batch_x = np.reshape(batch_x, [-1, 28, 28, 1]) or 2) Change the shape of the placeholder. e.g. X = tf.placeholder(tf.float32,[None, 784])

I would recommend 2), since this saves you from doing any reshaping operations both in and outside of the TensorFlow graph.

ppyht2
  • 43
  • 8