InvalidArgumentError: You must feed a value for placeholder tensor 'Placeholder' with dtype float and shape [1000,625] - machine-learning

Question

I get the above unexpected error when trying to run this code:
# -*- coding: utf-8 -*-
"""
Created on Fri Jun 24 10:38:04 2016
#author: andrea
"""
# pylint: disable=missing-docstring
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import time
from six.moves import xrange # pylint: disable=redefined-builtin
import tensorflow as tf
from pylab import *
import argparse
import mlp
# Basic model parameters as external flags.
tf.app.flags.FLAGS = tf.python.platform.flags._FlagValues()
tf.app.flags._global_parser = argparse.ArgumentParser()
flags = tf.app.flags
FLAGS = flags.FLAGS
flags.DEFINE_float('learning_rate', 0.01, 'Initial learning rate.')
flags.DEFINE_integer('max_steps', 20, 'Number of steps to run trainer.')
flags.DEFINE_integer('batch_size', 1000, 'Batch size. Must divide evenly into the dataset sizes.')
flags.DEFINE_integer('num_samples', 100000, 'Total number of samples. Needed by the reader')
flags.DEFINE_string('training_set_file', 'godzilla_dataset_size625', 'Training set file')
flags.DEFINE_string('test_set_file', 'godzilla_testset_size625', 'Test set file')
flags.DEFINE_string('test_size', 1000, 'Test set size')
def placeholder_inputs(batch_size):
images_placeholder = tf.placeholder(tf.float32, shape=(batch_size, mlp.NUM_INPUT))
labels_placeholder = tf.placeholder(tf.float32, shape=(batch_size, mlp.NUM_OUTPUT))
return images_placeholder, labels_placeholder
def fill_feed_dict(data_set_file, images_pl, labels_pl):
for l in range(int(FLAGS.num_samples/FLAGS.batch_size)):
data_set = genfromtxt("../dataset/" + data_set_file, skip_header=l*FLAGS.batch_size, max_rows=FLAGS.batch_size)
data_set = reshape(data_set, [FLAGS.batch_size, mlp.NUM_INPUT + mlp.NUM_OUTPUT])
images = data_set[:, :mlp.NUM_INPUT]
labels_feed = reshape(data_set[:, mlp.NUM_INPUT:], [FLAGS.batch_size, mlp.NUM_OUTPUT])
images_feed = reshape(images, [FLAGS.batch_size, mlp.NUM_INPUT])
feed_dict = {
images_pl: images_feed,
labels_pl: labels_feed,
}
yield feed_dict
def reader(data_set_file, images_pl, labels_pl):
data_set = loadtxt("../dataset/" + data_set_file)
images = data_set[:, :mlp.NUM_INPUT]
labels_feed = reshape(data_set[:, mlp.NUM_INPUT:], [data_set.shape[0], mlp.NUM_OUTPUT])
images_feed = reshape(images, [data_set.shape[0], mlp.NUM_INPUT])
feed_dict = {
images_pl: images_feed,
labels_pl: labels_feed,
}
return feed_dict, labels_pl
def run_training():
tot_training_loss = []
tot_test_loss = []
tf.reset_default_graph()
with tf.Graph().as_default() as g:
images_placeholder, labels_placeholder = placeholder_inputs(FLAGS.batch_size)
test_images_pl, test_labels_pl = placeholder_inputs(FLAGS.test_size)
logits = mlp.inference(images_placeholder)
test_pred = mlp.inference(test_images_pl, reuse=True)
loss = mlp.loss(logits, labels_placeholder)
test_loss = mlp.loss(test_pred, test_labels_pl)
train_op = mlp.training(loss, FLAGS.learning_rate)
#summary_op = tf.merge_all_summaries()
init = tf.initialize_all_variables()
saver = tf.train.Saver()
sess = tf.Session()
#summary_writer = tf.train.SummaryWriter("./", sess.graph)
sess.run(init)
test_feed, test_labels_placeholder = reader(FLAGS.test_set_file, test_images_pl, test_labels_pl)
# Start the training loop.
for step in xrange(FLAGS.max_steps):
start_time = time.time()
feed_gen = fill_feed_dict(FLAGS.training_set_file, images_placeholder, labels_placeholder)
i=1
for feed_dict in feed_gen:
_, loss_value = sess.run([train_op, loss], feed_dict=feed_dict)
_, test_loss_val = sess.run([test_pred, test_loss], feed_dict=test_feed)
tot_training_loss.append(loss_value)
tot_test_loss.append(test_loss_val)
#if i % 10 == 0:
#print('%d minibatches analyzed...'%i)
i+=1
if step % 1 == 0:
duration = time.time() - start_time
print('Epoch %d (%.3f sec):\n training loss = %f \n test loss = %f ' % (step, duration, loss_value, test_loss_val))
predictions = sess.run(test_pred, feed_dict=test_feed)
savetxt("predictions", predictions)
savetxt("training_loss", tot_training_loss)
savetxt("test_loss", tot_test_loss)
plot(tot_training_loss)
plot(tot_test_loss)
figure()
scatter(test_feed[test_labels_placeholder], predictions)
#plot([.4, .6], [.4, .6])
run_training()
#if __name__ == '__main__':
# tf.app.run()
this is mlp:
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import math
import tensorflow as tf
NUM_OUTPUT = 1
NUM_INPUT = 625
NUM_HIDDEN = 5
def inference(images, reuse=None):
with tf.variable_scope('hidden1', reuse=reuse):
weights = tf.get_variable(name='weights', shape=[NUM_INPUT, NUM_HIDDEN], initializer=tf.contrib.layers.xavier_initializer())
weight_decay = tf.mul(tf.nn.l2_loss(weights), 0.00001, name='weight_loss')
tf.add_to_collection('losses', weight_decay)
biases = tf.Variable(tf.constant(0.0, name='biases', shape=[NUM_HIDDEN]))
hidden1_output = tf.nn.relu(tf.matmul(images, weights)+biases, name='hidden1')
with tf.variable_scope('output', reuse=reuse):
weights = tf.get_variable(name='weights', shape=[NUM_HIDDEN, NUM_OUTPUT], initializer=tf.contrib.layers.xavier_initializer())
weight_decay = tf.mul(tf.nn.l2_loss(weights), 0.00001, name='weight_loss')
tf.add_to_collection('losses', weight_decay)
biases = tf.Variable(tf.constant(0.0, name='biases', shape=[NUM_OUTPUT]))
output = tf.nn.relu(tf.matmul(hidden1_output, weights)+biases, name='output')
return output
def loss(outputs, labels):
rmse = tf.sqrt(tf.reduce_mean(tf.square(tf.sub(labels, outputs))), name="rmse")
tf.add_to_collection('losses', rmse)
return tf.add_n(tf.get_collection('losses'), name='total_loss')
def training(loss, learning_rate):
tf.scalar_summary(loss.op.name, loss)
optimizer = tf.train.GradientDescentOptimizer(learning_rate)
global_step = tf.Variable(0, name='global_step', trainable=False)
train_op = optimizer.minimize(loss, global_step=global_step)
return train_op
here the error:
Traceback (most recent call last):
File "<ipython-input-1-f16dfed3b99b>", line 1, in <module>
runfile('/home/andrea/test/python/main_mlp_yield.py', wdir='/home/andrea/test/python')
File "/usr/local/lib/python2.7/dist-packages/spyderlib/widgets/externalshell/sitecustomize.py", line 714, in runfile
execfile(filename, namespace)
File "/usr/local/lib/python2.7/dist-packages/spyderlib/widgets/externalshell/sitecustomize.py", line 81, in execfile
builtins.execfile(filename, *where)
File "/home/andrea/test/python/main_mlp_yield.py", line 127, in <module>
run_training()
File "/home/andrea/test/python/main_mlp_yield.py", line 105, in run_training
_, test_loss_val = sess.run([test_pred, test_loss], feed_dict=test_feed)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 372, in run
run_metadata_ptr)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 636, in _run
feed_dict_string, options, run_metadata)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 708, in _do_run
target_list, options, run_metadata)
File "/usr/local/lib/python2.7/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 [1000,625]
[[Node: Placeholder = Placeholder[dtype=DT_FLOAT, shape=[1000,625], _device="/job:localhost/replica:0/task:0/cpu:0"]()]]
Caused by op u'Placeholder', defined at:
File "/usr/local/lib/python2.7/dist-packages/spyderlib/widgets/externalshell/start_ipython_kernel.py", line 205, in <module>
__ipythonkernel__.start()
File "/usr/local/lib/python2.7/dist-packages/ipykernel/kernelapp.py", line 442, in start
ioloop.IOLoop.instance().start()
File "/usr/local/lib/python2.7/dist-packages/zmq/eventloop/ioloop.py", line 162, in start
super(ZMQIOLoop, self).start()
File "/usr/local/lib/python2.7/dist-packages/tornado/ioloop.py", line 883, in start
handler_func(fd_obj, events)
File "/usr/local/lib/python2.7/dist-packages/tornado/stack_context.py", line 275, in null_wrapper
return fn(*args, **kwargs)
File "/usr/local/lib/python2.7/dist-packages/zmq/eventloop/zmqstream.py", line 440, in _handle_events
self._handle_recv()
File "/usr/local/lib/python2.7/dist-packages/zmq/eventloop/zmqstream.py", line 472, in _handle_recv
self._run_callback(callback, msg)
File "/usr/local/lib/python2.7/dist-packages/zmq/eventloop/zmqstream.py", line 414, in _run_callback
callback(*args, **kwargs)
File "/usr/local/lib/python2.7/dist-packages/tornado/stack_context.py", line 275, in null_wrapper
return fn(*args, **kwargs)
File "/usr/local/lib/python2.7/dist-packages/ipykernel/kernelbase.py", line 276, in dispatcher
return self.dispatch_shell(stream, msg)
File "/usr/local/lib/python2.7/dist-packages/ipykernel/kernelbase.py", line 228, in dispatch_shell
handler(stream, idents, msg)
File "/usr/local/lib/python2.7/dist-packages/ipykernel/kernelbase.py", line 391, in execute_request
user_expressions, allow_stdin)
File "/usr/local/lib/python2.7/dist-packages/ipykernel/ipkernel.py", line 199, in do_execute
shell.run_cell(code, store_history=store_history, silent=silent)
File "/usr/local/lib/python2.7/dist-packages/IPython/core/interactiveshell.py", line 2723, in run_cell
interactivity=interactivity, compiler=compiler, result=result)
File "/usr/local/lib/python2.7/dist-packages/IPython/core/interactiveshell.py", line 2831, in run_ast_nodes
if self.run_code(code, result):
File "/usr/local/lib/python2.7/dist-packages/IPython/core/interactiveshell.py", line 2885, in run_code
exec(code_obj, self.user_global_ns, self.user_ns)
File "<ipython-input-1-f16dfed3b99b>", line 1, in <module>
runfile('/home/andrea/test/python/main_mlp_yield.py', wdir='/home/andrea/test/python')
File "/usr/local/lib/python2.7/dist-packages/spyderlib/widgets/externalshell/sitecustomize.py", line 714, in runfile
execfile(filename, namespace)
File "/usr/local/lib/python2.7/dist-packages/spyderlib/widgets/externalshell/sitecustomize.py", line 81, in execfile
builtins.execfile(filename, *where)
File "/home/andrea/test/python/main_mlp_yield.py", line 127, in <module>
run_training()
File "/home/andrea/test/python/main_mlp_yield.py", line 79, in run_training
images_placeholder, labels_placeholder = placeholder_inputs(FLAGS.batch_size)
File "/home/andrea/test/python/main_mlp_yield.py", line 37, in placeholder_inputs
images_placeholder = tf.placeholder(tf.float32, shape=(batch_size, mlp.NUM_INPUT))
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/array_ops.py", line 895, in placeholder
name=name)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/gen_array_ops.py", line 1238, in _placeholder
name=name)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/op_def_library.py", line 704, in apply_op
op_def=op_def)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 2260, in create_op
original_op=self._default_original_op, op_def=op_def)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 1230, in __init__
self._traceback = _extract_stack()
I really don't understand why. It looks to me that I'm feeding all the placeholders before using them. I also removed the "merge_all_summaries" since this problem is similar to other (this and this), but it didn't help
EDIT: training data: 100000 samples x 625 features
test data: 1000 samples x 625 features
num. output: 1

Answer 1

I think the problem is in this code:
def loss(outputs, labels):
rmse = tf.sqrt(tf.reduce_mean(tf.square(tf.sub(labels, outputs))), name="rmse")
tf.add_to_collection('losses', rmse)
return tf.add_n(tf.get_collection('losses'), name='total_loss')
You're adding up all the losses from collection 'losses', including both your training and test losses. In particular, in this code:
loss = mlp.loss(logits, labels_placeholder)
test_loss = mlp.loss(test_pred, test_labels_pl)
The first call to mlp.loss will add training losses to the 'losses' collection. The second call to mlp.loss will incorporate those values in its result. So when you try to compute the test_loss, Tensorflow complains that you didn't feed all of the inputs (the training placeholders).
Perhaps you meant something like this?
def loss(outputs, labels):
rmse = tf.sqrt(tf.reduce_mean(tf.square(tf.sub(labels, outputs))), name="rmse")
return rmse
I hope that helps!