機器學習資料庫是關鍵，自己搜搜吧，規模太小訓練不出來，正樣本和負樣本。

訓練之前要處理訓練檔案，這個我在之前的python影象操作這篇博文裡寫過，並有完整程式碼。

也可以用我處理好的資料，稍後我會上傳

input_data.py

"""Functions for downloading and reading MNIST data."""
from __future__ import print_function
import gzip
import os
import numpy


def extract_images(filename):
  """Extract the images into a 4D uint8 numpy array [index, y, x, depth]."""
  print('Extracting', filename)
  rows = 128
  cols = 64
  data = numpy.fromfile(filename, dtype=numpy.uint8)
  data = data.reshape(-1, rows, cols, 1)
  #print numpy.shape(data)
  return data


def dense_to_one_hot(labels_dense, num_classes=2):
  """Convert class labels from scalars to one-hot vectors."""
  num_labels = labels_dense.shape[0]
  index_offset = numpy.arange(num_labels) * num_classes
  labels_one_hot = numpy.zeros((num_labels, num_classes))
  labels_one_hot.flat[index_offset + labels_dense.ravel()] = 1
  return labels_one_hot


def extract_labels(filename, one_hot=False):
  """Extract the labels into a 1D uint8 numpy array [index]."""
  print('Extracting', filename)
  labels = numpy.fromfile(filename, dtype=numpy.uint8)
  if one_hot:
     return dense_to_one_hot(labels)
  return labels


class DataSet(object):

  def __init__(self, images, labels, fake_data=False):
    if fake_data:
      self._num_examples = 10000
    else:
      assert images.shape[0] == labels.shape[0], (
          "images.shape: %s labels.shape: %s" % (images.shape,
                                                 labels.shape))
      self._num_examples = images.shape[0]

      # Convert shape from [num examples, rows, columns, depth]
      # to [num examples, rows*columns] (assuming depth == 1)
      assert images.shape[3] == 1
      images = images.reshape(images.shape[0],
                              images.shape[1] * images.shape[2])
      # Convert from [0, 255] -> [0.0, 1.0].
      images = images.astype(numpy.float32)
      images = numpy.multiply(images, 1.0 / 255.0)
    self._images = images
    self._labels = labels
    self._epochs_completed = 0
    self._index_in_epoch = 0

  @property
  def images(self):
    return self._images

  @property
  def labels(self):
    return self._labels

  @property
  def num_examples(self):
    return self._num_examples

  @property
  def epochs_completed(self):
    return self._epochs_completed

  def next_batch(self, batch_size, fake_data=False):
    """Return the next `batch_size` examples from this data set."""
    if fake_data:
      fake_image = [1.0 for _ in xrange(784)]
      fake_label = 0
      return [fake_image for _ in xrange(batch_size)], [
          fake_label for _ in xrange(batch_size)]
    start = self._index_in_epoch
    self._index_in_epoch += batch_size
    if self._index_in_epoch > self._num_examples:
      # Finished epoch
      self._epochs_completed += 1
      # Shuffle the data
      perm = numpy.arange(self._num_examples)
      numpy.random.shuffle(perm)
      self._images = self._images[perm]
      self._labels = self._labels[perm]
      # Start next epoch
      start = 0
      self._index_in_epoch = batch_size
      assert batch_size <= self._num_examples
    end = self._index_in_epoch
    return self._images[start:end], self._labels[start:end]


def read_data_sets(train_dir, fake_data=False, one_hot=False):
  class DataSets(object):
    pass
  data_sets = DataSets()

  if fake_data:
    data_sets.train = DataSet([], [], fake_data=True)
    data_sets.validation = DataSet([], [], fake_data=True)
    data_sets.test = DataSet([], [], fake_data=True)
    return data_sets

  TRAIN_IMAGES = 'train_data.bin'
  TRAIN_LABELS = 'train_label.bin'
  TEST_IMAGES = 'test_data.bin'
  TEST_LABELS = 'test_label.bin'
  VALIDATION_SIZE = 500

  local_file =os.path.join(train_dir, TRAIN_IMAGES)
  train_images = extract_images(local_file)
  
  local_file =os.path.join(train_dir, TRAIN_LABELS)
  train_labels = extract_labels(local_file, one_hot=one_hot)

  local_file = os.path.join(train_dir, TEST_IMAGES)
  test_images = extract_images(local_file)
  
  local_file =os.path.join(train_dir, TEST_LABELS)
  test_labels = extract_labels(local_file, one_hot=one_hot)

  validation_images = train_images[:VALIDATION_SIZE]
  validation_labels = train_labels[:VALIDATION_SIZE]
  train_images = train_images[VALIDATION_SIZE:]
  train_labels = train_labels[VALIDATION_SIZE:]

  data_sets.train = DataSet(train_images, train_labels)
  data_sets.validation = DataSet(validation_images, validation_labels)
  data_sets.test = DataSet(test_images, test_labels)

  return data_sets
 

conv_net.py

import input_data
mnist = input_data.read_data_sets('dataset', one_hot=True)
import tensorflow as tf

# Parameters
learning_rate = 0.001
training_iters = 100000
batch_size = 128
display_step = 10

# Network Parameters
n_input = 128*64 #  data input (img shape: 128*64)
n_classes = 2 # total classes (0-1)
dropout = 0.50 # Dropout, probability to keep units

# tf Graph input
x = tf.placeholder(tf.float32, [None, n_input])
y = tf.placeholder(tf.float32, [None, n_classes])
keep_prob = tf.placeholder(tf.float32) #dropout (keep probability)

# Create model
def conv2d(img, w, b):
    return tf.nn.relu(tf.nn.bias_add(tf.nn.conv2d(img, w, strides=[1, 1, 1, 1], padding='SAME'),b))

def max_pool(img, k):
    return tf.nn.max_pool(img, ksize=[1, k, k, 1], strides=[1, k, k, 1], padding='SAME')

def conv_net(_X, _weights, _biases, _dropout):
    # Reshape input picture
    _X = tf.reshape(_X, shape=[-1, 128, 64, 1])

    # Convolution Layer
    conv1 = conv2d(_X, _weights['wc1'], _biases['bc1'])
    # Max Pooling (down-sampling)
    conv1 = max_pool(conv1, k=2)
    # Apply Dropout
    conv1 = tf.nn.dropout(conv1, _dropout)

    # Convolution Layer
    conv2 = conv2d(conv1, _weights['wc2'], _biases['bc2'])
    # Max Pooling (down-sampling)
    conv2 = max_pool(conv2, k=2)
    # Apply Dropout
    conv2 = tf.nn.dropout(conv2, _dropout)

    # Fully connected layer
    dense1 = tf.reshape(conv2, [-1, _weights['wd1'].get_shape().as_list()[0]]) # Reshape conv2 output to fit dense layer input
    dense1 = tf.nn.relu(tf.add(tf.matmul(dense1, _weights['wd1']), _biases['bd1'])) # Relu activation
    dense1 = tf.nn.dropout(dense1, _dropout) # Apply Dropout

    # Output, class prediction
    out = tf.add(tf.matmul(dense1, _weights['out']), _biases['out'])
    return out

# Store layers weight & bias
weights = {
    'wc1': tf.Variable(tf.random_normal([5, 5, 1, 32])), # 5x5 conv, 1 input, 32 outputs
    'wc2': tf.Variable(tf.random_normal([5, 5, 32, 64])), # 5x5 conv, 32 inputs, 64 outputs
    'wd1': tf.Variable(tf.random_normal([32*16*64, 1024])), # fully connected, 7*7*64 inputs, 1024 outputs
    'out': tf.Variable(tf.random_normal([1024, n_classes])) # 1024 inputs, 10 outputs (class prediction)
}

biases = {
    'bc1': tf.Variable(tf.random_normal([32])),
    'bc2': tf.Variable(tf.random_normal([64])),
    'bd1': tf.Variable(tf.random_normal([1024])),
    'out': tf.Variable(tf.random_normal([n_classes]))
}

# Construct model
pred = conv_net(x, weights, biases, keep_prob)

# Define loss and optimizer
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(pred, y))
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)

# Evaluate model
correct_pred = tf.equal(tf.argmax(pred,1), tf.argmax(y,1))
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))

# Initializing the variables
init = tf.initialize_all_variables()

# Launch the graph
with tf.Session() as sess:
    sess.run(init)
    step = 1
    # Keep training until reach max iterations
    while step * batch_size < training_iters:
        batch_xs, batch_ys = mnist.train.next_batch(batch_size)
        # Fit training using batch data
        sess.run(optimizer, feed_dict={x: batch_xs, y: batch_ys, keep_prob: dropout})
        if step % display_step == 0:
            # Calculate batch accuracy
            acc = sess.run(accuracy, feed_dict={x: batch_xs, y: batch_ys, keep_prob: 1.})
            # Calculate batch loss
            loss = sess.run(cost, feed_dict={x: batch_xs, y: batch_ys, keep_prob: 1.})
            print "Iter " + str(step*batch_size) + ", Minibatch Loss= " + "{:.6f}".format(loss) + ", Training Accuracy= " + "{:.5f}".format(acc)
        step += 1
    print "Optimization Finished!"
    # Calculate accuracy for 256 mnist test images
    print "Testing Accuracy:", sess.run(accuracy, feed_dict={x: mnist.test.images[:256], y: mnist.test.labels[:256], keep_prob: 1.})