ValueError: Cannot feed value of shape (10, 32, 32, 3) for Tensor 'Placeholder:0', which has shape '(25432, 32, 32, 3)'

Question

I have such code, which should train my neural network. But i can't understand why i have an error when I try to start test.

with graph.as_default():
    images_ph = tf.placeholder(tf.float32, [25432, 32, 32, 3])
    labels_ph = tf.placeholder(tf.int32, [25432])

    images_flat = tf.contrib.layers.flatten(images_ph)

    logits = tf.contrib.layers.fully_connected(images_flat, 68, tf.nn.relu)

    predicted_labels = tf.argmax(logits, 1)

    loss = tf.reduce_mean(tf.nn.sparse_softmax_cross_entropy_with_logits(logits=logits, labels=labels_ph))

    train = tf.train.AdamOptimizer(learning_rate=0.001, epsilon=0.00000001).minimize(loss)

    all_saver = tf.train.Saver()

    init = tf.global_variables_initializer()

session = tf.Session(graph=graph)

_ = session.run([init])

steps = 401
for i in range(steps):
    _, loss_value = session.run([train, loss], feed_dict={images_ph: images_a, labels_ph: labels_a})
    if i % 10 == 0:
        print("Loss: ", loss_value)

all_saver.save(session, output_graph, global_step=steps)

# Pick 10 random images
sample_indexes = random.sample(range(len(images32)), 10)
sample_images = [images32[i] for i in sample_indexes]
sample_labels = [labels[i] for i in sample_indexes]

predicted = session.run([predicted_labels], feed_dict={images_ph: sample_images})[0]

When you try to start, an error occurs after the network training phase. Namely, at the testing stage. What could be the problem?

Error: ValueError: Cannot feed value of shape (10, 32, 32, 3) for Tensor 'Placeholder:0', which has shape '(25432, 32, 32, 3)'

Line:

predicted = session.run([predicted_labels], feed_dict={images_ph: sample_images})[0]