0

如果这是一个幼稚的问题，我很抱歉。这是我第一次尝试使用 tensorflow。作为 Udacity 课程的一部分，我在非 MNIST 数据集上尝试了 numpy 之后，我正在使用它。现在，这是我编写的代码。然而，这给了我 87-88% 的准确率。请建议我应该注意哪些错误以及代码中可能出现的错误：

batch_size = 256
node_dimensions = 1024


graph = tf.Graph()
with graph.as_default():

  tf_train_dataset = tf.placeholder(tf.float32,
                                shape=(batch_size, image_size *image_size))
  tf_train_labels = tf.placeholder(tf.float32, shape=(batch_size,num_labels))
  tf_valid_dataset = tf.constant(valid_dataset)
  tf_test_dataset = tf.constant(test_dataset)

  # Variables.  
  #Layer 1
  w1 = tf.Variable(
    tf.truncated_normal([image_size * image_size, node_dimensions]))
  b1 = tf.Variable(tf.zeros([node_dimensions]))

  #Layer 2
  w2 = tf.Variable(tf.random_uniform([node_dimensions, 
    node_dimensions], -0.01, 0.01))
  b2 = tf.Variable(tf.zeros([node_dimensions]))

  #Layer 3
  w3 = tf.Variable(
    tf.truncated_normal([node_dimensions, num_labels]))
  b3 = tf.Variable(tf.zeros([num_labels]))

  # Training computation.  
  # Layer 1.
  y1 = tf.nn.softmax(tf.matmul(tf_train_dataset, w1) + b1)

 # Layer 2.
  y2 = tf.nn.relu(tf.matmul(y1, w2) + b2)

  # Layer 3.
  logits = tf.matmul(y2, w3) + b3
  loss = tf.reduce_mean(
    tf.nn.softmax_cross_entropy_with_logits(labels=tf_train_labels,logits=logits))


  # Valid computation.  
  # Layer 1.
  y1 = tf.nn.softmax(tf.matmul(tf_valid_dataset, w1) + b1)

  # Layer 2.
  y2 = tf.nn.relu(tf.matmul(y1, w2) + b2)

  # Layer 3.
  logits_valid = tf.matmul(y2, w3) + b3

  # Test computation.  
  # Layer 1.
  y1 = tf.nn.softmax(tf.matmul(tf_test_dataset, w1) + b1)

  # Layer 2.
  y2 = tf.nn.relu(tf.matmul(y1, w2) + b2)

  # Layer 3.
  logits_test = tf.matmul(y2, w3) + b3

  # Optimizer.
  optimizer = tf.train.GradientDescentOptimizer(0.5).minimize(loss)

  # Predictions for the training, validation, and test data.
  train_prediction = tf.nn.softmax(logits)
  valid_prediction = tf.nn.softmax(logits_valid)
  test_prediction = tf.nn.softmax(logits_test)


num_steps = 10001

with tf.Session(graph=graph) as session:
  tf.global_variables_initializer().run()
  print("Initialized")
  for step in range(num_steps):
    offset = (step * batch_size) % (train_labels.shape[0] - batch_size)
    # Generate a minibatch.
    batch_data = train_dataset[offset:(offset + batch_size), :]
    batch_labels = train_labels[offset:(offset + batch_size), :]
    # Prepare a dictionary telling the session where to feed the minibatch.
    # The key of the dictionary is the placeholder node of the graph to be fed,
    # and the value is the numpy array to feed to it.
    feed_dict = {tf_train_dataset : batch_data, tf_train_labels :batch_labels}
    _, l, predictions = session.run(
      [optimizer, loss, train_prediction], feed_dict=feed_dict)
    if (step % 500 == 0):
      print("Minibatch loss at step %d: %f" % (step, l))
      print("Minibatch accuracy: %.1f%%" % accuracy(predictions, batch_labels))
      print("Validation accuracy: %.1f%%" % accuracy(
        valid_prediction.eval(), valid_labels))
  print("Test accuracy: %.1f%%" % accuracy(test_prediction.eval(), 
test_labels))
4

1 回答 1

0

您需要提及您正在使用的数据集。如果这是 Mnist，我同意 88% 是低的。但是在任何其他数据集上都很难说。另外，你为什么设置num_steps = 1000。一般来说，应该这样训练

num_steps = len(train_data) // batch_size
num_epochs = 10
for _ in num_epochs:
    for i in num_steps:
        /* Train Code*/
于 2018-06-07T05:31:51.477 回答