Tensorflow: feed dict error: You must feed a value for placeholder tensor

Question

I have one bug I cannot find out the reason. Here is the code:

with tf.Graph().as_default():
        global_step = tf.Variable(0, trainable=False)

        images = tf.placeholder(tf.float32, shape = [FLAGS.batch_size,33,33,1])
        labels = tf.placeholder(tf.float32, shape = [FLAGS.batch_size,21,21,1])

        logits = inference(images)
        losses = loss(logits, labels)
        train_op = train(losses, global_step)
        saver = tf.train.Saver(tf.all_variables())
        summary_op = tf.merge_all_summaries()
        init = tf.initialize_all_variables()

        sess = tf.Session()
        sess.run(init)                                                 

        summary_writer = tf.train.SummaryWriter(FLAGS.train_dir, sess.graph)

        for step in xrange(FLAGS.max_steps):
            start_time = time.time()

            data_batch, label_batch = SRCNN_inputs.next_batch(np_data, np_label,
                                                              FLAGS.batch_size)


            _, loss_value = sess.run([train_op, losses], feed_dict={images: data_batch, labels: label_batch})

            duration = time.time() - start_time

def next_batch(np_data, np_label, batchsize, 
               training_number = NUM_EXAMPLES_PER_EPOCH_TRAIN):

    perm = np.arange(training_number)
    np.random.shuffle(perm)
    data = np_data[perm]
    label = np_label[perm]
    data_batch = data[0:batchsize,:]
    label_batch = label[0:batchsize,:]


return data_batch, label_batch

where np_data is the whole training samples read from hdf5 file, and the same to np_label.

After I run the code, I got the error like this :

2016-07-07 11:16:36.900831: step 0, loss = 55.22 (218.9 examples/sec; 0.585 sec/batch)
Traceback (most recent call last):

  File "<ipython-input-1-19672e1f8f12>", line 1, in <module>
    runfile('/home/kang/Documents/work_code_PC1/tf_SRCNN/SRCNN_train.py', wdir='/home/kang/Documents/work_code_PC1/tf_SRCNN')

  File "/usr/lib/python3/dist-packages/spyderlib/widgets/externalshell/sitecustomize.py", line 685, in runfile
    execfile(filename, namespace)

  File "/usr/lib/python3/dist-packages/spyderlib/widgets/externalshell/sitecustomize.py", line 85, in execfile
    exec(compile(open(filename, 'rb').read(), filename, 'exec'), namespace)

  File "/home/kang/Documents/work_code_PC1/tf_SRCNN/SRCNN_train.py", line 155, in <module>
    train_test()

  File "/home/kang/Documents/work_code_PC1/tf_SRCNN/SRCNN_train.py", line 146, in train_test
    summary_str = sess.run(summary_op)

  File "/usr/local/lib/python3.4/dist-packages/tensorflow/python/client/session.py", line 372, in run
    run_metadata_ptr)

  File "/usr/local/lib/python3.4/dist-packages/tensorflow/python/client/session.py", line 636, in _run
    feed_dict_string, options, run_metadata)

  File "/usr/local/lib/python3.4/dist-packages/tensorflow/python/client/session.py", line 708, in _do_run
    target_list, options, run_metadata)

  File "/usr/local/lib/python3.4/dist-packages/tensorflow/python/client/session.py", line 728, in _do_call
    raise type(e)(node_def, op, message)

InvalidArgumentError: You must feed a value for placeholder tensor 'Placeholder' with dtype float and shape [128,33,33,1]
     [[Node: Placeholder = Placeholder[dtype=DT_FLOAT, shape=[128,33,33,1], _device="/job:localhost/replica:0/task:0/gpu:0"]()]]
     [[Node: truediv/_74 = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/cpu:0", send_device="/job:localhost/replica:0/task:0/gpu:0", send_device_incarnation=1, tensor_name="edge_56_truediv", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/cpu:0"]()]]
Caused by op 'Placeholder', defined at:

So, It shows that for the step 0 it has the result, which means that the data has been fed into the Placeholders.

But why does it come the error of feeding data into Placeholder in the next time?

When I try to comment the code summary_op = tf.merge_all_summaries() and the code works fine. why is it the case?

Answer 1

When I try to comment the code summary_op = tf.merge_all_summaries() and the code works fine. why is it the case?

summary_op is an operation. If there exists (and this is true in your case) a summary operation related to the result of another operation that depends upon the values of the placeholders, you have to feed the graph the required values.

So, your line summary_str = sess.run(summary_op) needs the dictionary of the values to store.

Usually, instead of re-executing the operations to log the values, you run the operations and the summary_op once.

Do something like

if step % LOGGING_TIME_STEP == 0:
    _, loss_value, summary_str = sess.run([train_op, losses, summary_op], feed_dict={images: data_batch, labels: label_batch})
else:
    _, loss_value = sess.run([train_op, losses], feed_dict={images: data_batch, labels: label_batch})