In [1]:

    

#Reading data

with tf.Session():
  input = tf.placeholder(tf.float32)
  classifier = ...
  print(classifier.eval(feed_dict={input: my_python_preprocessing_fn()}))


    

    




  File "<ipython-input-1-7f9fd40e2a2e>", line 5
    classifier = ...
                 ^
SyntaxError: invalid syntax

In [ ]:

    

filename_queue = tf.train.string_input_producer(["file0.csv", "file1.csv"])

reader = tf.TextLineReader()
key, value = reader.read(filename_queue)

# Default values, in case of empty columns. Also specifies the type of the
# decoded result.
record_defaults = [[1], [1], [1], [1], [1]]
col1, col2, col3, col4, col5 = tf.decode_csv(
    value, record_defaults=record_defaults)
features = tf.stack([col1, col2, col3, col4])

with tf.Session() as sess:
  # Start populating the filename queue.
  coord = tf.train.Coordinator()
  threads = tf.train.start_queue_runners(coord=coord)

  for i in range(1200):
    # Retrieve a single instance:
    example, label = sess.run([features, col5])

  coord.request_stop()
  coord.join(threads)


    

In [ ]:

    

def read_my_file_format(filename_queue):
  reader = tf.SomeReader()
  key, record_string = reader.read(filename_queue)
  example, label = tf.some_decoder(record_string)
  processed_example = some_processing(example)
  return processed_example, label

def input_pipeline(filenames, batch_size, num_epochs=None):
  filename_queue = tf.train.string_input_producer(
      filenames, num_epochs=num_epochs, shuffle=True)
  example, label = read_my_file_format(filename_queue)
  # min_after_dequeue defines how big a buffer we will randomly sample
  #   from -- bigger means better shuffling but slower start up and more
  #   memory used.
  # capacity must be larger than min_after_dequeue and the amount larger
  #   determines the maximum we will prefetch.  Recommendation:
  #   min_after_dequeue + (num_threads + a small safety margin) * batch_size
  min_after_dequeue = 10000
  capacity = min_after_dequeue + 3 * batch_size
  example_batch, label_batch = tf.train.shuffle_batch(
      [example, label], batch_size=batch_size, capacity=capacity,
      min_after_dequeue=min_after_dequeue)
  return example_batch, label_batch


    

In [ ]:

    

#need more parallelism or shuffling of examples between files
def read_my_file_format(filename_queue):
  # Same as above

def input_pipeline(filenames, batch_size, read_threads, num_epochs=None):
  filename_queue = tf.train.string_input_producer(
      filenames, num_epochs=num_epochs, shuffle=True)
  example_list = [read_my_file_format(filename_queue)
                  for _ in range(read_threads)]
  min_after_dequeue = 10000
  capacity = min_after_dequeue + 3 * batch_size
  example_batch, label_batch = tf.train.shuffle_batch_join(
      example_list, batch_size=batch_size, capacity=capacity,
      min_after_dequeue=min_after_dequeue)
  return example_batch, label_batch


    

In [ ]:

    

# Create the graph, etc.
init_op = tf.global_variables_initializer()

# Create a session for running operations in the Graph.
sess = tf.Session()

# Initialize the variables (like the epoch counter).
sess.run(init_op)

# Start input enqueue threads.
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=sess, coord=coord)

try:
    while not coord.should_stop():
        # Run training steps or whatever
        sess.run(train_op)

except tf.errors.OutOfRangeError:
    print('Done training -- epoch limit reached')
finally:
    # When done, ask the threads to stop.
    coord.request_stop()

# Wait for threads to finish.
coord.join(threads)
sess.close()


    

In [ ]:

    

training_data = ...
training_labels = ...
with tf.Session():
  input_data = tf.constant(training_data)
  input_labels = tf.constant(training_labels)
  ...


    

In [ ]:

    

training_data = ...
training_labels = ...
with tf.Session() as sess:
  data_initializer = tf.placeholder(dtype=training_data.dtype,
                                    shape=training_data.shape)
  label_initializer = tf.placeholder(dtype=training_labels.dtype,
                                     shape=training_labels.shape)
  input_data = tf.Variable(data_initializer, trainable=False, collections=[])
  input_labels = tf.Variable(label_initializer, trainable=False, collections=[])
  ...
  sess.run(input_data.initializer,
           feed_dict={data_initializer: training_data})
  sess.run(input_labels.initializer,
           feed_dict={label_initializer: training_labels})