Shapes must be equal rank, but are 2 and 1 - tensorflow

Question

I'm following the example of Sentdex on youtube and here is the code I have
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("/tmp/data/", one_hot = True)
n_nodes_hl1 = 500
n_nodes_hl2 = 500
n_nodes_hl3 = 500
n_classes = 10
batch_size = 100
x = tf.placeholder('float', [None, 784])
y = tf.placeholder('float')
def neural_network_model(data):
hidden_1_layer = {'weights':tf.Variable(tf.random_normal([784, n_nodes_hl1])),
'biases':tf.Variable(tf.random_normal([n_nodes_hl1]))}
hidden_2_layer = {'weights':tf.Variable(tf.random_normal([n_nodes_hl1, n_nodes_hl2])),
'biases':tf.Variable(tf.random_normal([n_nodes_hl2]))}
hidden_3_layer = {'weights':tf.Variable(tf.random_normal([n_nodes_hl2, n_nodes_hl3])),
'biases':tf.Variable(tf.random_normal([n_nodes_hl3]))}
output_layer = {'weights':tf.Variable(tf.random_normal([n_nodes_hl3, n_classes])),
'biases':tf.Variable(tf.random_normal([n_classes])),}
l1 = tf.add(tf.matmul(data,hidden_1_layer['weights']), hidden_1_layer['biases'])
l1 = tf.nn.relu(l1)
l2 = tf.add(tf.matmul(l1,hidden_2_layer['weights']), hidden_2_layer['biases'])
l2 = tf.nn.relu(l2)
l3 = tf.add(tf.matmul(l2,hidden_3_layer['weights']), hidden_3_layer['biases'])
l3 = tf.nn.relu(l3)
output = tf.matmul(l3,output_layer['weights']) + output_layer['biases']
return output
def train_neural_network(x):
prediction = neural_network_model(x)
# OLD VERSION:
#cost = tf.reduce_mean( tf.nn.softmax_cross_entropy_with_logits(prediction,y) )
# NEW:
cost = tf.reduce_mean( tf.nn.softmax_cross_entropy_with_logits(logits=prediction, labels=y) )
optimizer = tf.train.AdamOptimizer().minimize(cost)
hm_epochs = 10
with tf.Session() as sess:
# OLD:
#sess.run(tf.initialize_all_variables())
# NEW:
sess.run(tf.global_variables_initializer())
for epoch in range(hm_epochs):
epoch_loss = 0
for _ in range(int(mnist.train.num_examples/batch_size)):
epoch_x, epoch_y = mnist.train.next_batch(batch_size)
_, c = sess.run([optimizer, cost], feed_dict={x: epoch_x, y: epoch_y})
epoch_loss += c
print('Epoch', epoch, 'completed out of',hm_epochs,'loss:',epoch_loss)
correct = tf.equal(tf.argmax(prediction, 1), tf.argmax(y, 1))
accuracy = tf.reduce_mean(tf.cast(correct, 'float'))
print('Accuracy:',accuracy.eval({x:mnist.test.images, y:mnist.test.labels}))
train_neural_network(x)
It raises this error :
ValueError: Shapes must be equal rank, but are 2 and 1
From merging shape 0 with other shapes. for 'SparseSoftmaxCrossEntropyWithLogits/packed' (op: 'Pack') with input shapes: [?,10], [10].
on this line:
cost = tf.reduce_mean( tf.nn.softmax_cross_entropy_with_logits(logits=prediction, labels=y) )
I think it is about the size of y that induced the error, I tried using
cost = tf.reduce_mean(tf.nn.sparse_softmax_cross_entropy_with_logits(
prediction, tf.squeeze(y)))
I'm pretty sure this means that the cost function induces the error (shown above) prediction and y are not the same shape, but I don't understand TensorFlow well enough to know how to fix it. I don't even really understand where y is being set, I got most of this code from a tutorial and fiddled with it to apply it to a different dataset. How can I fix this error?
ps I tried to print out prediction, it gives me two outputs and i guess thats where the error comes from:
prediction
(<tf.Tensor 'MatMul_39:0' shape=(?, 10) dtype=float32>,
<tf.Variable 'Variable_79:0' shape=(10,) dtype=float32_ref>)

Answer 1

Since you are using one_hot=True while reading the input data, just define correct shape for the y placeholder
# redefine the label and input with exact data type and shape
x = tf.placeholder(tf.float32, [None, 784])
y = tf.placeholder(tf.float32, shape=[None, n_classes])

Answer 2

You have a comma between the closing parenthesis and the dict bracket in this statement:
output_layer = {'weights':tf.Variable(tf.random_normal([n_nodes_hl3, n_classes])),'biases':tf.Variable(tf.random_normal([n_classes])),}
just before the close bracket:
...([n_classes])),}

Answer 3

#WORKING CODE
#I had the same problem as you, (not counting the comma) and i´m sorry i don´t remember the things i changed, but hopefully this will work
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
mnist= input_data.read_data_sets("/tmp/data/", one_hot=True)
#10 clasees, 0-9
n_nodes_hl1=500
n_nodes_hl2=500
n_nodes_hl3=500
n_classes=10
batch_size=100
x=tf.placeholder('float',[None,784])
y=tf.placeholder('float')
def neural(data):
hidden_1_layer={'weights':tf.Variable(tf.random_normal([784, n_nodes_hl1])),
'biases':tf.Variable(tf.random_normal([n_nodes_hl1]))}
hidden_2_layer={'weights':tf.Variable(tf.random_normal([n_nodes_hl1, n_nodes_hl2])),
'biases':tf.Variable(tf.random_normal([n_nodes_hl2]))}
hidden_3_layer={'weights':tf.Variable(tf.random_normal([n_nodes_hl2, n_nodes_hl3])),
'biases':tf.Variable(tf.random_normal([n_nodes_hl3]))}
output_layer={'weights':tf.Variable(tf.random_normal([n_nodes_hl3, n_classes])),
'biases':tf.Variable(tf.random_normal([n_classes]))}
l1=tf.add(tf.matmul(data, hidden_1_layer['weights']), hidden_1_layer['biases'])
li= tf.nn.relu(l1)
l2=tf.add(tf.matmul(l1, hidden_2_layer['weights']), hidden_2_layer['biases'])
l2= tf.nn.relu(l2)
l3=tf.add(tf.matmul(l2, hidden_3_layer['weights']), hidden_3_layer['biases'])
l3= tf.nn.relu(l3)
output= tf.matmul(l3, output_layer['weights'])+ output_layer['biases']
return output
def train(x):
prediction=neural(x)
cost= tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=prediction,labels=y))
optimizer=tf.train.AdamOptimizer().minimize(cost)
hm_epochs=20
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
for epoch in range(hm_epochs):
epoch_loss=0
for _ in range(int(mnist.train.num_examples/batch_size)):
epoch_x,epoch_y = mnist.train.next_batch(batch_size)
_,c=sess.run([optimizer,cost],feed_dict={x: epoch_x, y: epoch_y})
epoch_loss += c
print('Epoch', epoch, 'completed out of', hm_epochs, 'loss:',epoch_loss)
correct= tf.equal(tf.argmax(prediction,1), tf.argmax(y,1))
accuracy= tf.reduce_mean(tf.cast(correct,'float'))
print('Accuracy:',accuracy.eval({x:mnist.test.images, y:mnist.test.labels}))
train(x)