CNN 卷积神经网络 2

建立全连接层

进入全连接层时, 通过tf.reshape()将h_pool2的输出值从一个三维的变为一维的数据

-1表示先不考虑输入图片例子维度, 将上一个输出结果展平.

#[n_samples,7,7,64]->>[n_samples,7*7*64]
h_pool2_flat=tf.reshape(h_pool2,[-1,7*7*64])

W_fc1=weight_variable([7*7*64,1024]) 
b_fc1=bias_variable([1024])

将展平后的h_pool2_flat与本层的W_fc1相乘（注意这个时候不是卷积了）

h_fc1=tf.nn.relu(tf.matmul(h_pool2_flat,W_fc1)+b_fc1)

dropout处理:

h_fc1_drop=tf.nn.dropout(h_fc1,keep_drop)

最后一层的构建:

W_fc2=weight_variable([1024,10]) b_fc2=bias_variable([10])

用softmax分类器（多分类，输出是各个类的概率）,对输出进行分类

prediction=tf.nn.softmax(tf.matmul(h_fc1_dropt,W_fc2),b_fc2)

选优化方法

利用交叉熵损失函数来定义cost function:

cross_entropy=tf.reduce_mean(
    -tf.reduce_sum(ys*tf.log(prediction),
    reduction_indices=[1]))

train_step=tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)

import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
import numpy as np
import matplotlib.pyplot as plt

tf.set_random_seed(1)
np.random.seed(1)

BATCH_SIZE = 50
LR = 0.001              # learning rate

mnist = input_data.read_data_sets('./mnist', one_hot=True)  # they has been normalized to range (0,1)
test_x = mnist.test.images[:2000]
test_y = mnist.test.labels[:2000]

# plot one example
print(mnist.train.images.shape)     # (55000, 28 * 28)
print(mnist.train.labels.shape)   # (55000, 10)
plt.imshow(mnist.train.images[0].reshape((28, 28)), cmap='gray')
plt.title('%i' % np.argmax(mnist.train.labels[0])); plt.show()

tf_x = tf.placeholder(tf.float32, [None, 28*28]) / 255.
image = tf.reshape(tf_x, [-1, 28, 28, 1])              # (batch, height, width, channel)
tf_y = tf.placeholder(tf.int32, [None, 10])            # input y

# CNN
conv1 = tf.layers.conv2d(   # shape (28, 28, 1)
    inputs=image,
    filters=16,
    kernel_size=5,
    strides=1,
    padding='same',
    activation=tf.nn.relu
)           # -> (28, 28, 16)
pool1 = tf.layers.max_pooling2d(
    conv1,
    pool_size=2,
    strides=2,
)           # -> (14, 14, 16)
conv2 = tf.layers.conv2d(pool1, 32, 5, 1, 'same', activation=tf.nn.relu)    # -> (14, 14, 32)
pool2 = tf.layers.max_pooling2d(conv2, 2, 2)    # -> (7, 7, 32)
flat = tf.reshape(pool2, [-1, 7*7*32])          # -> (7*7*32, )
output = tf.layers.dense(flat, 10)              # output layer

loss = tf.losses.softmax_cross_entropy(onehot_labels=tf_y, logits=output)           # compute cost
train_op = tf.train.AdamOptimizer(LR).minimize(loss)

accuracy = tf.metrics.accuracy(          # return (acc, update_op), and create 2 local variables
    labels=tf.argmax(tf_y, axis=1), predictions=tf.argmax(output, axis=1),)[1]

sess = tf.Session()
init_op = tf.group(tf.global_variables_initializer(), tf.local_variables_initializer()) # the local var is for accuracy_op
sess.run(init_op)     # initialize var in graph

# following function (plot_with_labels) is for visualization, can be ignored if not interested
from matplotlib import cm
try: from sklearn.manifold import TSNE; HAS_SK = True
except: HAS_SK = False; print('\nPlease install sklearn for layer visualization\n')
def plot_with_labels(lowDWeights, labels):
    plt.cla(); X, Y = lowDWeights[:, 0], lowDWeights[:, 1]
    for x, y, s in zip(X, Y, labels):
        c = cm.rainbow(int(255 * s / 9)); plt.text(x, y, s, backgroundcolor=c, fontsize=9)
    plt.xlim(X.min(), X.max()); plt.ylim(Y.min(), Y.max()); plt.title('Visualize last layer'); plt.show(); plt.pause(0.01)

plt.ion()
for step in range(600):
    b_x, b_y = mnist.train.next_batch(BATCH_SIZE)
    _, loss_ = sess.run([train_op, loss], {tf_x: b_x, tf_y: b_y})
    if step % 50 == 0:
        accuracy_, flat_representation = sess.run([accuracy, flat], {tf_x: test_x, tf_y: test_y})
        print('Step:', step, '| train loss: %.4f' % loss_, '| test accuracy: %.2f' % accuracy_)

        if HAS_SK:
            # Visualization of trained flatten layer (T-SNE)
            tsne = TSNE(perplexity=30, n_components=2, init='pca', n_iter=5000); plot_only = 500
            low_dim_embs = tsne.fit_transform(flat_representation[:plot_only, :])
            labels = np.argmax(test_y, axis=1)[:plot_only]; plot_with_labels(low_dim_embs, labels)
plt.ioff()

# print 10 predictions from test data
test_output = sess.run(output, {tf_x: test_x[:10]})
pred_y = np.argmax(test_output, 1)
print(pred_y, 'prediction number')
print(np.argmax(test_y[:10], 1), 'real number')