机器学习数据库是关键,自己搜搜吧,规模太小训练不出来,正样本和负样本。
训练之前要处理训练文件,这个我在之前的python图像操作这篇博文里写过,并有完整代码。
也可以用我处理好的数据,稍后我会上传
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.})
下面是训练结果