Tensorflow, двоичная классификация

Question

Можно ли сделать двоичную классификацию? Специально для обнаружения пешеходов, будь то пешеход или нет. Я не мог найти ничего в API или каких-либо хороших учебниках для этого. Я попытался адаптировать код из глубокого учебника MNIST, который использовался для классификации нескольких классов; Я сделал изображения с пешеходами в них с меткой 1, а отрицательные с 0, и использовал 3 канала (для цветов, не должно быть проблемой?), Но точность просто прыгает повсюду.

Код

import dataset as input_data 
    import tensorflow as tf 


    def weight_variable(shape): 
     initial = tf.truncated_normal(shape, stddev=0.1) 
     return tf.Variable(initial) 


    def bias_variable(shape): 
     initial = tf.constant(0.1, shape=shape) 
     return tf.Variable(initial) 


    def conv2d(x, W): 
     return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME') 


    def max_pool_2x2(x): 
     return tf.nn.max_pool(x, ksize=[1, 3, 3, 1], 
           strides=[1, 2, 2, 1], padding='SAME') 


    data = input_data.read_data_sets() 

    sess = tf.InteractiveSession() 

    x = tf.placeholder("float", shape=[None, input_data.HEIGHT * input_data.WIDTH * 3]) 
    y_ = tf.placeholder("float", shape=[None, 2]) 

    W_conv1 = weight_variable([5, 5, 3, 64]) 
    b_conv1 = bias_variable([64]) 

    x_image = tf.reshape(x, [-1, input_data.WIDTH, input_data.HEIGHT, 3]) 

    h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1) 
    h_pool1 = max_pool_2x2(h_conv1) 
    h_norm1 = tf.nn.lrn(h_pool1, 4, bias=1.0, alpha=0.001/9.0, beta=0.75) 

    W_conv2 = weight_variable([5, 5, 64, 64]) 
    b_conv2 = bias_variable([64]) 

    h_conv2 = tf.nn.relu(conv2d(h_norm1, W_conv2) + b_conv2) 
    h_norm2 = tf.nn.lrn(h_conv2, 4, bias=1.0, alpha=0.001/9.0, beta=0.75) 
    h_pool2 = max_pool_2x2(h_norm2) 

    W_fc1 = weight_variable([input_data.HEIGHT/4 * input_data.WIDTH/4 * 64, 1024]) 
    b_fc1 = bias_variable([1024]) 

    h_pool2_flat = tf.reshape(h_pool2, [-1, input_data.HEIGHT/4 * input_data.WIDTH/4 * 64]) 
    h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1) 

    keep_prob = tf.placeholder("float") 
    h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob) 

    W_fc2 = weight_variable([1024, 2]) 
    b_fc2 = bias_variable([2]) 

    y_conv = tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2) 

    cross_entropy = -tf.reduce_sum(y_ * tf.log(y_conv)) 
    train_step = tf.train.AdamOptimizer(1e-6).minimize(cross_entropy) 
    correct_prediction = tf.equal(tf.argmax(y_conv, 1), tf.argmax(y_, 1)) 
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float")) 
    sess.run(tf.initialize_all_variables()) 
    for i in range(20000): 
     batch = data.train.next_batch(50) 
     if i % 100 == 0: 
      train_accuracy = accuracy.eval(feed_dict={ 
       x: batch[0], y_: batch[1], keep_prob: 1.0}) 
      print "step %d, training accuracy %g" % (i, train_accuracy) 
     train_step.run(feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5}) 

    print "test accuracy %g" % accuracy.eval(feed_dict={ 
     x: data.test.images, y_: data.test.labels, keep_prob: 1.0}) 

Выход

step 0, training accuracy 0.14 
    step 100, training accuracy 0.54 
    step 200, training accuracy 0.28 
    step 300, training accuracy 0.46 
    step 400, training accuracy 0.32 
    step 500, training accuracy 0.52 
    step 600, training accuracy 0.56 
    step 700, training accuracy 0.76 
    step 800, training accuracy 0.66 

Помощь будет apriciated, спасибо.

Answer 1

Вы должны определенно использовать тензограмму, чтобы визуализировать кросс-энтропию, предвзятости и весовые сводки. Я думаю, это даст вам гораздо лучшее представление о том, что происходит.

Попробуйте этот код, а затем запустить tensorboard:

import dataset as input_data 
import tensorflow as tf 


def weight_variable(shape): 
    initial = tf.truncated_normal(shape, stddev=0.1) 
    return tf.Variable(initial) 


def bias_variable(shape): 
    initial = tf.constant(0.1, shape=shape) 
    return tf.Variable(initial) 


def conv2d(x, W): 
    return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME') 


def max_pool_2x2(x): 
    return tf.nn.max_pool(x, ksize=[1, 3, 3, 1], 
          strides=[1, 2, 2, 1], padding='SAME') 


data = input_data.read_data_sets() 

sess = tf.InteractiveSession() 

x = tf.placeholder("float", shape=[None, input_data.HEIGHT * input_data.WIDTH * 3]) 
y_ = tf.placeholder("float", shape=[None, 2]) 

W_conv1 = weight_variable([5, 5, 3, 64]) 
b_conv1 = bias_variable([64]) 

x_image = tf.reshape(x, [-1, input_data.WIDTH, input_data.HEIGHT, 3]) 

h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1) 
h_pool1 = max_pool_2x2(h_conv1) 
h_norm1 = tf.nn.lrn(h_pool1, 4, bias=1.0, alpha=0.001/9.0, beta=0.75) 

W_conv2 = weight_variable([5, 5, 64, 64]) 
b_conv2 = bias_variable([64]) 

h_conv2 = tf.nn.relu(conv2d(h_norm1, W_conv2) + b_conv2) 
h_norm2 = tf.nn.lrn(h_conv2, 4, bias=1.0, alpha=0.001/9.0, beta=0.75) 
h_pool2 = max_pool_2x2(h_norm2) 

W_fc1 = weight_variable([input_data.HEIGHT/4 * input_data.WIDTH/4 * 64, 1024]) 
b_fc1 = bias_variable([1024]) 

h_pool2_flat = tf.reshape(h_pool2, [-1, input_data.HEIGHT/4 * input_data.WIDTH/4 * 64]) 
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1) 

keep_prob = tf.placeholder("float") 
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob) 

W_fc2 = weight_variable([1024, 2]) 
b_fc2 = bias_variable([2]) 

y_conv = tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2) 

# Add summary ops to collect data 
w_fc2_hist = tf.histogram_summary("weights_fc2", W_fc2) 
b_fc2_hist = tf.histogram_summary("bias_fc2", b_fc2) 
w_in_hist = tf.histogram_summary("weights_in", W) 
b_in_hist = tf.histogram_summary("bias_in", b) 
y_hist = tf.histogram_summary("y_conv", y_conv) 

cross_entropy = -tf.reduce_sum(y_ * tf.log(y_conv)) 
ce_summ = tf.scalar_summary("cross entropy", cross_entropy) 
train_step = tf.train.AdamOptimizer(1e-6).minimize(cross_entropy) 
correct_prediction = tf.equal(tf.argmax(y_conv, 1), tf.argmax(y_, 1)) 
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float")) 
accuracy_summary = tf.scalar_summary("train accuracy", accuracy) 
# Merge all the summaries and write them out to /tmp/tf 
merged = tf.merge_all_summaries() 
writer = tf.train.SummaryWriter("/tmp/tf", sess.graph_def) 
sess.run(tf.initialize_all_variables()) 
for i in range(20000): 
    batch = data.train.next_batch(50) 
    feed={x: batch[0], y_: batch[1], keep_prob: 0.5} 
    result = sess.run([merged, accuracy, train_step], feed_dict=feed)   
    if i % 100 == 0: # Record summary data, and the accuracy 
      summary_str = result[0] 
      acc = result[1] 
      writer.add_summary(summary_str, i) 
      print("Accuracy at step {0}/{1}: {2}%".format(i, 20000, int(acc*100))) 

print "test accuracy %g" % accuracy.eval(feed_dict={ 
    x: data.test.images, y_: data.test.labels, keep_prob: 1.0})