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