tensorflow卷积网络测试

from __future__ import print_functionimport tensorflow as tffrom tensorflow.examples.tutorials.mnist import input_datamnist = input_data.read_data_sets("MNIST_data/", one_hot=True)learning_rate = 0.001training_iters = 200000batch_size = 128display_step = 10n_input = 784 n_classes = 10dropout = 0.75 x = tf.placeholder(tf.float32, [None, n_input])y = tf.placeholder(tf.float32, [None, n_classes])keep_prob = tf.placeholder(tf.float32) def conv2d(x, W, b, strides=1):    x = tf.nn.conv2d(x, W, strides=[1, strides, strides, 1], padding='SAME')    x = tf.nn.bias_add(x, b)    return tf.nn.relu(x)def maxpool2d(x, k=2):    return tf.nn.max_pool(x, ksize=[1, k, k, 1], strides=[1, k, k, 1], padding='SAME')def conv_net(x, weights, biases, dropout):    # 输入-1代表图片数量不定 , 28*28图片，1通道灰色图    x = tf.reshape(x, shape=[-1, 28, 28, 1])    ############# 第一层卷积 #####################    conv1 = conv2d(x, weights['wc1'], biases['bc1'])    conv1 = maxpool2d(conv1, k=2)    ############# 第二层卷积 #####################    conv2 = conv2d(conv1, weights['wc2'], biases['bc2'])    conv2 = maxpool2d(conv2, k=2)    ############# 第三层全连接 ###################    fc1 = tf.reshape(conv2, [-1, weights['wd1'].get_shape().as_list()[0]])    fc1 = tf.add(tf.matmul(fc1, weights['wd1']), biases['bd1'])    fc1 = tf.nn.relu(fc1)    fc1 = tf.nn.dropout(fc1, dropout)    ############# 第四层全连接 ###################    out = tf.add(tf.matmul(fc1, weights['out']), biases['out'])    return outweights = {    # 5x5 conv, 1 input, 32 outputs, 第一层卷积结果14*14*32（32张图）    'wc1': tf.Variable(tf.random_normal([5, 5, 1, 32])),    # 5x5 conv, 32 inputs, 64 outputs, 第二层卷积结果7*7*64（64张图）    'wc2': tf.Variable(tf.random_normal([5, 5, 32, 64])),    # fully connected, 7*7*64 inputs, 1024 outputs    'wd1': tf.Variable(tf.random_normal([7*7*64, 1024])),    # 1024 inputs, 10 outputs (class prediction)    'out': tf.Variable(tf.random_normal([1024, n_classes]))}biases = {    # xx通道输出，对应xx偏置量    '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]))}predict = conv_net(x, weights, biases, keep_prob)############# 回归分类 #############cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=predict, labels=y))optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)############# 预测 #####################correct_pred = tf.equal(tf.argmax(predict, 1), tf.argmax(y, 1))accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))init = tf.global_variables_initializer()with tf.Session() as sess:    sess.run(init)    step = 1    ############# 训练 #####################    while step * batch_size < training_iters:        batch_x, batch_y = mnist.train.next_batch(batch_size)        sess.run(optimizer, feed_dict={x: batch_x, y: batch_y, keep_prob: dropout})        if step % display_step == 0:            loss, acc = sess.run([cost, accuracy],                                  feed_dict={x: batch_x, y: batch_y, keep_prob: 1.})            print("Iter " + str(step*batch_size) + ", Minibatch Loss= " + \                  "{:.6f}".format(loss) + ", Training Accuracy= " + "{:.5f}".format(acc))        step += 1    print("Optimization Finished!")    test_accuracy = sess.run(accuracy, feed_dict={x: mnist.test.images[:256],                                                  y: mnist.test.labels[:256], keep_prob: 1.}）    print("Testing Accuracy:", test_accuracy)

结果：

Iter 1280, Minibatch Loss= 26739.099609, Training Accuracy= 0.25781Iter 2560, Minibatch Loss= 9156.189453, Training Accuracy= 0.57031Iter 3840, Minibatch Loss= 6651.129883, Training Accuracy= 0.67188Iter 5120, Minibatch Loss= 6166.565430, Training Accuracy= 0.78906Iter 6400, Minibatch Loss= 5917.207031, Training Accuracy= 0.76562Iter 7680, Minibatch Loss= 4123.412598, Training Accuracy= 0.80469Iter 8960, Minibatch Loss= 2672.761719, Training Accuracy= 0.87500Iter 10240, Minibatch Loss= 4759.664062, Training Accuracy= 0.82812Iter 11520, Minibatch Loss= 1856.829102, Training Accuracy= 0.89844Iter 12800, Minibatch Loss= 3375.414062, Training Accuracy= 0.87500Iter 14080, Minibatch Loss= 1702.190063, Training Accuracy= 0.88281Iter 15360, Minibatch Loss= 2097.105225, Training Accuracy= 0.89844Iter 16640, Minibatch Loss= 2330.599121, Training Accuracy= 0.92188Iter 17920, Minibatch Loss= 2278.968750, Training Accuracy= 0.89062Iter 19200, Minibatch Loss= 2017.522705, Training Accuracy= 0.86719Iter 20480, Minibatch Loss= 2566.398682, Training Accuracy= 0.87500Iter 21760, Minibatch Loss= 238.359406, Training Accuracy= 0.96875Iter 23040, Minibatch Loss= 1531.023071, Training Accuracy= 0.93750Iter 24320, Minibatch Loss= 2890.682861, Training Accuracy= 0.85938Iter 25600, Minibatch Loss= 835.863403, Training Accuracy= 0.95312Iter 26880, Minibatch Loss= 1700.663086, Training Accuracy= 0.92969Iter 28160, Minibatch Loss= 1126.358643, Training Accuracy= 0.89844Iter 29440, Minibatch Loss= 2107.322021, Training Accuracy= 0.87500Iter 30720, Minibatch Loss= 530.002075, Training Accuracy= 0.93750Iter 32000, Minibatch Loss= 850.515503, Training Accuracy= 0.96094Iter 33280, Minibatch Loss= 1732.267334, Training Accuracy= 0.89844Iter 34560, Minibatch Loss= 1890.741699, Training Accuracy= 0.92188Iter 35840, Minibatch Loss= 1371.276733, Training Accuracy= 0.93750Iter 37120, Minibatch Loss= 370.038940, Training Accuracy= 0.97656Iter 38400, Minibatch Loss= 981.587280, Training Accuracy= 0.92188Iter 39680, Minibatch Loss= 1120.410034, Training Accuracy= 0.92188Iter 40960, Minibatch Loss= 1850.069580, Training Accuracy= 0.90625Iter 42240, Minibatch Loss= 929.379517, Training Accuracy= 0.96094Iter 43520, Minibatch Loss= 1343.690430, Training Accuracy= 0.94531Iter 44800, Minibatch Loss= 965.836792, Training Accuracy= 0.95312Iter 46080, Minibatch Loss= 1384.953125, Training Accuracy= 0.93750Iter 47360, Minibatch Loss= 544.845093, Training Accuracy= 0.97656Iter 48640, Minibatch Loss= 1975.952637, Training Accuracy= 0.91406Iter 49920, Minibatch Loss= 784.620056, Training Accuracy= 0.93750Iter 51200, Minibatch Loss= 921.763916, Training Accuracy= 0.94531Iter 52480, Minibatch Loss= 584.898987, Training Accuracy= 0.96875Iter 53760, Minibatch Loss= 1298.738037, Training Accuracy= 0.93750Iter 55040, Minibatch Loss= 474.747986, Training Accuracy= 0.95312Iter 56320, Minibatch Loss= 1118.239258, Training Accuracy= 0.91406Iter 57600, Minibatch Loss= 500.907440, Training Accuracy= 0.96875Iter 58880, Minibatch Loss= 605.852844, Training Accuracy= 0.96094Iter 60160, Minibatch Loss= 320.352173, Training Accuracy= 0.95312Iter 61440, Minibatch Loss= 90.246094, Training Accuracy= 0.98438Iter 62720, Minibatch Loss= 952.188599, Training Accuracy= 0.94531Iter 64000, Minibatch Loss= 709.913330, Training Accuracy= 0.92969Iter 65280, Minibatch Loss= 1092.906006, Training Accuracy= 0.97656Iter 66560, Minibatch Loss= 1067.758057, Training Accuracy= 0.93750Iter 67840, Minibatch Loss= 482.389526, Training Accuracy= 0.96875Iter 69120, Minibatch Loss= 1065.343384, Training Accuracy= 0.94531Iter 70400, Minibatch Loss= 980.166809, Training Accuracy= 0.96875Iter 71680, Minibatch Loss= 1640.528564, Training Accuracy= 0.93750Iter 72960, Minibatch Loss= 612.411499, Training Accuracy= 0.96875Iter 74240, Minibatch Loss= 432.089081, Training Accuracy= 0.96094Iter 75520, Minibatch Loss= 326.332825, Training Accuracy= 0.95312Iter 76800, Minibatch Loss= 903.289001, Training Accuracy= 0.92969Iter 78080, Minibatch Loss= 440.528931, Training Accuracy= 0.96875Iter 79360, Minibatch Loss= 431.268433, Training Accuracy= 0.96094Iter 80640, Minibatch Loss= 215.546570, Training Accuracy= 0.97656Iter 81920, Minibatch Loss= 476.220642, Training Accuracy= 0.96875Iter 83200, Minibatch Loss= 66.687637, Training Accuracy= 0.99219Iter 84480, Minibatch Loss= 109.571373, Training Accuracy= 0.97656Iter 85760, Minibatch Loss= 780.713013, Training Accuracy= 0.92969Iter 87040, Minibatch Loss= 470.991821, Training Accuracy= 0.93750Iter 88320, Minibatch Loss= 665.605103, Training Accuracy= 0.94531Iter 89600, Minibatch Loss= 486.712555, Training Accuracy= 0.95312Iter 90880, Minibatch Loss= 1212.130615, Training Accuracy= 0.93750Iter 92160, Minibatch Loss= 319.079803, Training Accuracy= 0.97656Iter 93440, Minibatch Loss= 453.148254, Training Accuracy= 0.95312Iter 94720, Minibatch Loss= 569.428711, Training Accuracy= 0.92188Iter 96000, Minibatch Loss= 94.126587, Training Accuracy= 0.97656Iter 97280, Minibatch Loss= 275.076508, Training Accuracy= 0.96094Iter 98560, Minibatch Loss= 758.537231, Training Accuracy= 0.95312Iter 99840, Minibatch Loss= 217.494034, Training Accuracy= 0.97656Iter 101120, Minibatch Loss= 666.817688, Training Accuracy= 0.94531Iter 102400, Minibatch Loss= 387.140015, Training Accuracy= 0.97656Iter 103680, Minibatch Loss= 309.601013, Training Accuracy= 0.97656Iter 104960, Minibatch Loss= 491.488007, Training Accuracy= 0.96875Iter 106240, Minibatch Loss= 559.815063, Training Accuracy= 0.96094Iter 107520, Minibatch Loss= 469.924438, Training Accuracy= 0.95312Iter 108800, Minibatch Loss= 463.599823, Training Accuracy= 0.96875Iter 110080, Minibatch Loss= 652.325684, Training Accuracy= 0.95312Iter 111360, Minibatch Loss= 380.302612, Training Accuracy= 0.94531Iter 112640, Minibatch Loss= 265.474548, Training Accuracy= 0.95312Iter 113920, Minibatch Loss= 145.682693, Training Accuracy= 0.97656Iter 115200, Minibatch Loss= 468.385132, Training Accuracy= 0.96094Iter 116480, Minibatch Loss= 337.575378, Training Accuracy= 0.96875Iter 117760, Minibatch Loss= 137.029846, Training Accuracy= 0.97656Iter 119040, Minibatch Loss= 385.774475, Training Accuracy= 0.96875Iter 120320, Minibatch Loss= 855.515930, Training Accuracy= 0.94531Iter 121600, Minibatch Loss= 826.428955, Training Accuracy= 0.93750Iter 122880, Minibatch Loss= 840.954712, Training Accuracy= 0.95312Iter 124160, Minibatch Loss= 135.299774, Training Accuracy= 0.97656Iter 125440, Minibatch Loss= 596.197998, Training Accuracy= 0.96094Iter 126720, Minibatch Loss= 77.240379, Training Accuracy= 0.97656Iter 128000, Minibatch Loss= 375.658081, Training Accuracy= 0.97656Iter 129280, Minibatch Loss= 262.859131, Training Accuracy= 0.97656Iter 130560, Minibatch Loss= 44.147209, Training Accuracy= 0.97656Iter 131840, Minibatch Loss= 293.386353, Training Accuracy= 0.96875Iter 133120, Minibatch Loss= 126.623993, Training Accuracy= 0.99219Iter 134400, Minibatch Loss= 761.212891, Training Accuracy= 0.97656Iter 135680, Minibatch Loss= 35.652237, Training Accuracy= 0.99219Iter 136960, Minibatch Loss= 136.761017, Training Accuracy= 0.98438Iter 138240, Minibatch Loss= 427.506470, Training Accuracy= 0.97656Iter 139520, Minibatch Loss= 603.883118, Training Accuracy= 0.96094Iter 140800, Minibatch Loss= 532.734253, Training Accuracy= 0.92969Iter 142080, Minibatch Loss= 229.608871, Training Accuracy= 0.95312Iter 143360, Minibatch Loss= 100.882248, Training Accuracy= 0.97656Iter 144640, Minibatch Loss= 256.012390, Training Accuracy= 0.96875Iter 145920, Minibatch Loss= 155.531174, Training Accuracy= 0.98438Iter 147200, Minibatch Loss= 0.000000, Training Accuracy= 1.00000Iter 148480, Minibatch Loss= 505.638275, Training Accuracy= 0.97656Iter 149760, Minibatch Loss= 44.933327, Training Accuracy= 0.99219Iter 151040, Minibatch Loss= 142.327377, Training Accuracy= 0.97656Iter 152320, Minibatch Loss= 461.496185, Training Accuracy= 0.96094Iter 153600, Minibatch Loss= 118.370140, Training Accuracy= 0.97656Iter 154880, Minibatch Loss= 403.881134, Training Accuracy= 0.93750Iter 156160, Minibatch Loss= 27.085678, Training Accuracy= 0.98438Iter 157440, Minibatch Loss= 233.737488, Training Accuracy= 0.98438Iter 158720, Minibatch Loss= 252.954391, Training Accuracy= 0.95312Iter 160000, Minibatch Loss= 78.215767, Training Accuracy= 0.97656Iter 161280, Minibatch Loss= 313.302979, Training Accuracy= 0.96875Iter 162560, Minibatch Loss= 86.086960, Training Accuracy= 0.98438Iter 163840, Minibatch Loss= 159.479080, Training Accuracy= 0.98438Iter 165120, Minibatch Loss= 237.137192, Training Accuracy= 0.96875Iter 166400, Minibatch Loss= 71.959213, Training Accuracy= 0.99219Iter 167680, Minibatch Loss= 79.412460, Training Accuracy= 0.96094Iter 168960, Minibatch Loss= 163.784363, Training Accuracy= 0.97656Iter 170240, Minibatch Loss= 210.554535, Training Accuracy= 0.96875Iter 171520, Minibatch Loss= 62.252472, Training Accuracy= 0.99219Iter 172800, Minibatch Loss= 196.883423, Training Accuracy= 0.97656Iter 174080, Minibatch Loss= 67.746567, Training Accuracy= 0.98438Iter 175360, Minibatch Loss= 250.539902, Training Accuracy= 0.96875Iter 176640, Minibatch Loss= 125.992264, Training Accuracy= 0.99219Iter 177920, Minibatch Loss= 349.852203, Training Accuracy= 0.96875Iter 179200, Minibatch Loss= 149.910400, Training Accuracy= 0.96875Iter 180480, Minibatch Loss= 151.258850, Training Accuracy= 0.97656Iter 181760, Minibatch Loss= 39.953766, Training Accuracy= 0.98438Iter 183040, Minibatch Loss= 115.344940, Training Accuracy= 0.96094Iter 184320, Minibatch Loss= 32.580063, Training Accuracy= 0.99219Iter 185600, Minibatch Loss= 307.355103, Training Accuracy= 0.96875Iter 186880, Minibatch Loss= 211.242493, Training Accuracy= 0.96875Iter 188160, Minibatch Loss= 245.367706, Training Accuracy= 0.97656Iter 189440, Minibatch Loss= 121.856567, Training Accuracy= 0.96875Iter 190720, Minibatch Loss= 297.908020, Training Accuracy= 0.95312Iter 192000, Minibatch Loss= 28.702240, Training Accuracy= 0.99219Iter 193280, Minibatch Loss= 124.350609, Training Accuracy= 0.96094Iter 194560, Minibatch Loss= 223.368149, Training Accuracy= 0.96094Iter 195840, Minibatch Loss= 419.990204, Training Accuracy= 0.96875Iter 197120, Minibatch Loss= 19.725143, Training Accuracy= 0.98438Iter 198400, Minibatch Loss= 359.439301, Training Accuracy= 0.95312Iter 199680, Minibatch Loss= 176.249619, Training Accuracy= 0.97656Optimization Finished!Testing Accuracy: 0.988281