TensorFlow学习历程-1

def load_from_tfrecords(name, batch_size, num_epochs):
    file_name = name + '.tfrecords'
    filename_queue = tf.train.string_input_producer(file_name)], num_epochs=num_epochs)
    reader = tf.TFRecordReader()
    _, serialized_example = reader.read(filename_queue)  # return filename and files
    # Defaults are not specified since both keys are required.
    features = tf.parse_single_example(
        serialized_example,
        features={
            'label': tf.FixedLenFeature([], tf.int64),
            'image': tf.FixedLenFeature([], tf.string),
        })
    image = tf.decode_raw(features['image'], tf.float64)
    image = tf.reshape(image, [Utils.bands, Utils.patch_size, Utils.patch_size])
    label = tf.cast(features['label'], tf.int32)

    # Shuffle the examples and collect them into batch_size batches.
    # (Internally uses a RandomShuffleQueue.)
    # We run this in two threads to avoid being a bottleneck.
    '''
    images, labels = tf.train.shuffle_batch(
        [image, label], batch_size=batch_size, num_threads=4,
        capacity=1000 + 3 * batch_size,
        # Ensures a minimum amount of shuffling of examples.
        min_after_dequeue=1000)
    '''
    images, labels = tf.train.batch(
        [image, label], batch_size=batch_size, num_threads=4)

    images = tf.cast(images, tf.float32)
    images = tf.transpose(images, (0, 2, 3, 1))

    return images, labels

with tf.Graph().as_default():
    # Import training & test datasets from TFRecords
    with tf.name_scope('Inputs'):
        train_images, train_labels = load_from_tfrecords(
            'Train', batch_size=Utils.batch_size,
            num_epochs=Utils.max_steps)
        # Generate placeholders for dropout
        is_training = tf.placeholder(tf.bool, name='is-training')

    LOGITS = models.cnn_2d(train_images, is_training)
    LOSS = models.loss(LOGITS, train_labels)
    TRAIN = models.training(LOSS, Utils.learning_rate)
    
    # Initialize
    with tf.name_scope('Initialize'):
        INIT = tf.group(tf.global_variables_initializer(), tf.local_variables_initializer())

    with tf.Session() as sess:
        # Run the Op to initialize the variables.
        sess.run(INIT)
        # Start input enqueue threads.
        coord = tf.train.Coordinator()
        threads = tf.train.start_queue_runners(sess=sess, coord=coord)

        # Start the training loop.
        for step in xrange(Utils.max_steps):
            start_time = time.time()
            sess.run(TRAIN, feed_dict={is_training: True})

        # When done, ask the threads to stop.
        coord.request_stop()
        # Wait for threads to finish.
        coord.join(threads)

try:
  step = 0
  while not coord.should_stop():
    _, loss_value = sess.run([train_op, loss])
    step += 1
except tf.errors.OutOfRangeError:
  print('Done training for %d epochs, %d steps.' % (FLAGS.num_epochs, step))
finally:
  # When done, ask the threads to stop.
  coord.request_stop()
# Wait for threads to finish.
coord.join(threads)

I tensorflow/stream_executor/dso_loader.cc:126] Couldn't open CUDA library libcupti.so.8.0. LD_LIBRARY_PATH: :/usr/local/cuda/lib64
F tensorflow/core/platform/default/gpu/cupti_wrapper.cc:59] Check failed: ::tensorflow::Status::OK() == (::tensorflow::Env::Default()->GetSymbolFromLibrary( GetDsoHandle(), kName, &f)) (OK vs. Not found: /home/tom/anaconda3/envs/py36/lib/python3.6/site-packages/tensorflow/python/_pywrap_tensorflow.so: undefined symbol: cuptiActivityRegisterCallbacks)could not find cuptiActivityRegisterCallbacksin libcupti DSO Aborted

with tf.name_scope('hidden') as scope:
  a = tf.constant(5, name='alpha')
  W = tf.Variable(tf.random_uniform([1, 2], -1.0, 1.0), name='weights')
  b = tf.Variable(tf.zeros([1]), name='biases')

def variable_summaries(var):
  """Attach a lot of summaries to a Tensor (for TensorBoard visualization)."""
  with tf.name_scope('summaries'):
    mean = tf.reduce_mean(var)
    tf.summary.scalar('mean', mean)
    with tf.name_scope('stddev'):
      stddev = tf.sqrt(tf.reduce_mean(tf.square(var - mean)))
    tf.summary.scalar('stddev', stddev)
    tf.summary.scalar('max', tf.reduce_max(var))
    tf.summary.scalar('min', tf.reduce_min(var))
    tf.summary.histogram('histogram', var)

def nn_layer(input_tensor, input_dim, output_dim, layer_name, act=tf.nn.relu):
  """Reusable code for making a simple neural net layer.

  It does a matrix multiply, bias add, and then uses relu to nonlinearize.
  It also sets up name scoping so that the resultant graph is easy to read,
  and adds a number of summary ops.
  """
  # Adding a name scope ensures logical grouping of the layers in the graph.
  with tf.name_scope(layer_name):
    # This Variable will hold the state of the weights for the layer
    with tf.name_scope('weights'):
      weights = weight_variable([input_dim, output_dim])
      variable_summaries(weights)
    with tf.name_scope('biases'):
      biases = bias_variable([output_dim])
      variable_summaries(biases)
    with tf.name_scope('Wx_plus_b'):
      preactivate = tf.matmul(input_tensor, weights) + biases
      tf.summary.histogram('pre_activations', preactivate)
    activations = act(preactivate, name='activation')
    tf.summary.histogram('activations', activations)
    return activations

hidden1 = nn_layer(x, 784, 500, 'layer1')

with tf.name_scope('dropout'):
  keep_prob = tf.placeholder(tf.float32)
  tf.summary.scalar('dropout_keep_probability', keep_prob)
  dropped = tf.nn.dropout(hidden1, keep_prob)

# Do not apply softmax activation yet, see below.
y = nn_layer(dropped, 500, 10, 'layer2', act=tf.identity)

with tf.name_scope('cross_entropy'):
  # The raw formulation of cross-entropy,
  #
  # So here we use tf.nn.softmax_cross_entropy_with_logits on the
  # raw outputs of the nn_layer above, and then average across
  # the batch.
  diff = tf.nn.softmax_cross_entropy_with_logits(targets=y_, logits=y)
  with tf.name_scope('total'):
    cross_entropy = tf.reduce_mean(diff)
tf.summary.scalar('cross_entropy', cross_entropy)

with tf.name_scope('train'):
  train_step = tf.train.AdamOptimizer(FLAGS.learning_rate).minimize(
      cross_entropy)

with tf.name_scope('accuracy'):
  with tf.name_scope('correct_prediction'):
    correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
  with tf.name_scope('accuracy'):
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
tf.summary.scalar('accuracy', accuracy)

# Merge all the summaries and write them out to /tmp/mnist_logs (by default)
merged = tf.summary.merge_all()
train_writer = tf.summary.FileWriter(FLAGS.summaries_dir + '/train',
                                      sess.graph)
test_writer = tf.summary.FileWriter(FLAGS.summaries_dir + '/test')
tf.global_variables_initializer().run()

summary = tf.Summary(value=[
    tf.Summary.Value(tag="summary_tag", simple_value=0),
    tf.Summary.Value(tag="summary_tag2", simple_value=1),
])
# x代表横轴坐标
summary_writer.add_summary(summary, x)

summary = tf.Summary()
summary.value.add(tag="summary_tag", simple_value=0)
summary.value.add(tag="summary_tag2", simple_value=1)
# x代表横轴坐标
summary_writer.add_summary(summary, x)

# Train the model, and also write summaries.
# Every 10th step, measure test-set accuracy, and write test summaries
# All other steps, run train_step on training data, & add training summaries
for i in range(FLAGS.max_steps):
  if i % 10 == 0:  # Record summaries and test-set accuracy
    summary, acc = sess.run([merged, accuracy], feed_dict=feed_dict(False))
    test_writer.add_summary(summary, i)
    print('Accuracy at step %s: %s' % (i, acc))
  else:  # Record train set summaries, and train
    if i % 100 == 99:  # Record execution stats
      run_options = tf.RunOptions(trace_level=tf.RunOptions.FULL_TRACE)
      run_metadata = tf.RunMetadata()
      summary, _ = sess.run([merged, train_step],
                            feed_dict=feed_dict(True),
                            options=run_options,
                            run_metadata=run_metadata)
      train_writer.add_run_metadata(run_metadata, 'step%d' % i)
      train_writer.add_summary(summary, i)
      print('Adding run metadata for', i)
    else:  # Record a summary
      summary, _ = sess.run([merged, train_step], feed_dict=feed_dict(True))
      train_writer.add_summary(summary, i)