Tensorflow MNIST: ValueError: Shape must be rank 4 but is rank 1 for 'Conv2D' (op: 'Conv2D') with input shapes: [?,28,28,1], [4]

Question

I'm new to machine learning and tensorflow. I started by following the MNIST tutorial on the tensorflow site. I got the simple version to work, but when I was following along with the deep CNN, I found an error.

ValueError: Shape must be rank 4 but is rank 1 for 'Conv2D' (op: 'Conv2D') with input shapes: [?,28,28,1], [4].

The problem seems to lie in the line:

x_image = tf.reshape(x, [-1, 28, 28, 1])

Thanks for any help, I'm a bit lost here.

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

import tensorflow as tf

x = tf.placeholder(tf.float32, [None, 784])
W = tf.Variable(tf.zeros([784, 10]))
b = tf.Variable(tf.zeros([10]))
y = tf.matmul(x, W) + b

y_ = tf.placeholder(tf.float32, [None, 10])

#improvements
def weight_variable(shape):
    initial = tf.truncated_normal(shape, stddev=0.1)
    return tf.Variable(initial)

def bias_variable(shape):
    initial = tf.constant(0.1, shape=shape)
    return tf.Variable(initial)

def conv2d(x, W):
    return tf.nn.conv2d(x, W, strides=[1,1,1,1], padding='SAME')

def max_pool_2x2(x):
    return tf.nn.max_pool(x, ksize=[1,2,2,1], strides=[1,2,2,1], padding='SAME')

#layer 1
W_conv1 = ([5,5,1,32])
b_conv1 = ([32])

x_image = tf.reshape(x, [-1, 28, 28, 1])

h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)
h_pool1 = max_pool_2x2(h_conv1)

#layer 2
W_conv2 = weight_variable([5, 5, 32, 64])
b_conv2 = bias_variable([64])

h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
h_pool2 = max_pool_2x2(h_conv2)

#fully connected layer
W_fc1 = weight_variable([3136, 1024])
b_fc1 = bias_variable([1024])

h_pool2_flat = tf.reshape(h_pool2, [-1, 3136])
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)

#dropout
keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)

#readout, similar to softmax
W_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])

y_conv = tf.matmul(h_fc1_drop, W_fc2) + b_fc2

#optimization
cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=y_conv))

#training
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
correct = tf.equal(tf.argmax(y_conv, 1), tf.argmax(y_, 1))

#evaluate
accuracy = tf.reduce_mean(tf.cast(correct, tf.float32))

#the session
with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    for i in range(20000):
        batch = mnist.train.next_batch(50)
        if i%100==0:
            training_accuracy = accuracy.eval(feed_dict={x: batch[0], y_: batch[1], keep_prob: 1.0})
            print("step: %i   accuracy: %a" % (i, training_accuracy))
        train_step.run(feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})
    print("test accuracy: %s" % accuracy.eval(feed_dict={x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0}))

Answer 1

Your error is in your 1st convolutional layer - your variables W_conv1 and b_conv1 are just lists (hence rank 1) since you have not used the weight_variable() and bias_variable() functions that you created!