ValueError: Dimensions must be equal, but are 784 and 500 for 'MatMul_1' (op: 'MatMul') with input shapes: [?,784], [500,500]

Question

I'm new to tensorflow and I'm following a tutorial by sentdex. I keep on getting the error -

ValueError: Dimensions must be equal, but are 784 and 500 for 
'MatMul_1' (op: 'MatMul') with input shapes: [?,784], [500,500].

The snippet where I believe is causing the issue is -

l1 = tf.add(tf.matmul(data, hidden_1_layer['weights']), 
hidden_1_layer['biases'])
l1 = tf.nn.relu(l1)

l2 = tf.add(tf.matmul(data, hidden_2_layer['weights']), 
hidden_2_layer['biases'])
l2 = tf.nn.relu(l2)

l3 = tf.add(tf.matmul(data, hidden_3_layer['weights']), 
hidden_3_layer['biases'])
l3 = tf.nn.relu(l3)

output = tf.add(tf.matmul(l3, output_layer['weights']), 
output_layer['biases'])

return output

Although I'm a noob and may be wrong. My entire code is -

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(data, hidden_2_layer['weights']), 
hidden_2_layer['biases'])
l2 = tf.nn.relu(l2)

l3 = tf.add(tf.matmul(data, hidden_3_layer['weights']), 
hidden_3_layer['biases'])
l3 = tf.nn.relu(l3)

output = tf.add(tf.matmul(l3, output_layer['weights']), 
output_layer['biases'])

return output


def train_neural_network(x):
prediction = neural_network_model(x)
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:
    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)

Please help. By the way, I'm running on Mac in a virtual environment with Python 3.6.1 and Tensorflow 1.2. And I am using the IDE Pycharm CE. If any of that information is useful.

Molasses

Please fix your indentation, as it is, I am unable to even run your code to try and replicate the error – Zane

I would add in print(l1.get_shape().as_list()) between each line of the neural_network_model to try and find out what the problem is. – Urbanism

Answer 1

The problem is that you are referencing data instead of l1. Instead of

l2 = tf.add(tf.matmul(data, hidden_2_layer['weights']), 
                      hidden_2_layer['biases'])

your code should read

l2 = tf.add(tf.matmul(l1, hidden_2_layer['weights']), 
                      hidden_2_layer['biases'])

and ditto for l3. Instead of

l3 = tf.add(tf.matmul(data, hidden_3_layer['weights']), 
                      hidden_3_layer['biases'])

you should have

l3 = tf.add(tf.matmul(l2, hidden_3_layer['weights']), 
                      hidden_3_layer['biases'])

The following code ran without error for me:

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 print_shape(obj):
    print(obj.get_shape().as_list())

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]))}
    print_shape(data)
    l1 = tf.add(tf.matmul(data, hidden_1_layer['weights']),
                hidden_1_layer['biases'])
    print_shape(l1)
    l1 = tf.nn.relu(l1)
    print_shape(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.add(tf.matmul(l3, output_layer['weights']),
                    output_layer['biases'])

    return output


def train_neural_network(x):
    prediction = neural_network_model(x)
    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:
        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)

Urbanism

No worries :) if you like my answer, could you accept it please? – Urbanism

Sorry, forgot. :) – Molasses

Hi! I was working in the same code but running on my own dataset can anyone guide me about that? – Shopkeeper