GAN代码实操(github代码实操)

备注：下载github程序并运行，本人是小白一枚。这也是本人第一次运行ＧＡＮ程序。在这里仅仅将自己的代码实操过程分享出来。附件的tf.subtract()和tf.multiply()函数相对于github有所改动，不然版本配不上会出错。这里附上:github源代码链接

#运行run.py文件
run run.py

运行结果，耗时约一小时，CPU Windows7

step 0: loss 21.247
step 10: loss 22.076
step 20: loss 19.516
step 30: loss 6.678
step 40: loss 5.416
step 50: loss 8.300
step 60: loss 5.144
step 70: loss 6.920
step 80: loss 5.351
step 90: loss 6.231
step 100: loss 5.182
step 110: loss 4.267
step 120: loss 7.220
step 130: loss 6.011
step 140: loss 6.295
step 150: loss 4.976

·····

step 99870: loss 0.013
step 99880: loss 0.011
step 99890: loss 0.010
step 99900: loss 0.014
step 99910: loss 0.011
step 99920: loss 0.009
step 99930: loss 0.014
step 99940: loss 0.011
step 99950: loss 0.014
step 99960: loss 0.006
step 99970: loss 0.003
step 99980: loss 0.017
step 99990: loss 0.004

<Figure size 640x480 with 1 Axes>

#显示生成的最后一张图片
visualize.visualize(embed, x_test)

附件

#run.py

""" Siamese implementation using Tensorflow with MNIST example.
This siamese network embeds a 28x28 image (a point in 784D) 
into a point in 2D.

By Youngwook Paul Kwon (young at berkeley.edu)
"""

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

#import system things
from tensorflow.examples.tutorials.mnist import input_data # for data
import tensorflow as tf
import numpy as np
import os

#import helpers
import inference
import visualize

# prepare data and tf.session
mnist = input_data.read_data_sets('MNIST_data', one_hot=False)
sess = tf.InteractiveSession()

# setup siamese network
siamese = inference.siamese();
train_step = tf.train.GradientDescentOptimizer(0.01).minimize(siamese.loss)
saver = tf.train.Saver()
tf.initialize_all_variables().run()

# if you just want to load a previously trainmodel?
new = True
model_ckpt = 'model.ckpt'
if os.path.isfile(model_ckpt):
    input_var = None
    while input_var not in ['yes', 'no']:
        input_var = raw_input("We found model.ckpt file. Do you want to load it [yes/no]?")
    if input_var == 'yes':
        new = False

# start training
if new:
    for step in range(100000):
        batch_x1, batch_y1 = mnist.train.next_batch(128)
        batch_x2, batch_y2 = mnist.train.next_batch(128)
        batch_y = (batch_y1 == batch_y2).astype('float')

        _, loss_v = sess.run([train_step, siamese.loss], feed_dict={
                            siamese.x1: batch_x1, 
                            siamese.x2: batch_x2, 
                            siamese.y_: batch_y})

        if np.isnan(loss_v):
            print('Model diverged with loss = NaN')
            quit()

        if step % 10 == 0:
            print ('step %d: loss %.3f' % (step, loss_v))

        if step % 1000 == 0 and step > 0:
            saver.save(sess, 'model.ckpt')
            embed = siamese.o1.eval({siamese.x1: mnist.test.images})
            embed.tofile('embed.txt')
else:
    saver.restore(sess, 'model.ckpt')

# visualize result
x_test = mnist.test.images.reshape([-1, 28, 28])
visualize.visualize(embed, x_test)

#inference.py
import tensorflow as tf 

class siamese:
    # Create model
    def __init__(self):
        self.x1 = tf.placeholder(tf.float32, [None, 784])
        self.x2 = tf.placeholder(tf.float32, [None, 784])

        with tf.variable_scope("siamese") as scope:
            self.o1 = self.network(self.x1)
            scope.reuse_variables()
            self.o2 = self.network(self.x2)

        # Create loss
        self.y_ = tf.placeholder(tf.float32, [None])
        self.loss = self.loss_with_spring()

    def network(self, x):
        weights = []
        fc1 = self.fc_layer(x, 1024, "fc1")
        ac1 = tf.nn.relu(fc1)
        fc2 = self.fc_layer(ac1, 1024, "fc2")
        ac2 = tf.nn.relu(fc2)
        fc3 = self.fc_layer(ac2, 2, "fc3")
        return fc3

    def fc_layer(self, bottom, n_weight, name):
        assert len(bottom.get_shape()) == 2
        n_prev_weight = bottom.get_shape()[1]
        initer = tf.truncated_normal_initializer(stddev=0.01)
        W = tf.get_variable(name+'W', dtype=tf.float32, shape=[n_prev_weight, n_weight], initializer=initer)
        b = tf.get_variable(name+'b', dtype=tf.float32, initializer=tf.constant(0.01, shape=[n_weight], dtype=tf.float32))
        fc = tf.nn.bias_add(tf.matmul(bottom, W), b)
        return fc

    def loss_with_spring(self):
        margin = 5.0
        labels_t = self.y_
        labels_f = tf.subtract(1.0, self.y_, name="1-yi")          # labels_ = !labels;
        eucd2 = tf.pow(tf.subtract(self.o1, self.o2), 2)
        eucd2 = tf.reduce_sum(eucd2, 1)
        eucd = tf.sqrt(eucd2+1e-6, name="eucd")
        C = tf.constant(margin, name="C")
        # yi*||CNN(p1i)-CNN(p2i)||^2 + (1-yi)*max(0, C-||CNN(p1i)-CNN(p2i)||^2)
        pos = tf.multiply(labels_t, eucd2, name="yi_x_eucd2")
        # neg = tf.mul(labels_f, tf.sub(0.0,eucd2), name="yi_x_eucd2")
        # neg = tf.mul(labels_f, tf.maximum(0.0, tf.sub(C,eucd2)), name="Nyi_x_C-eucd_xx_2")
        neg = tf.multiply(labels_f, tf.pow(tf.maximum(tf.subtract(C, eucd), 0), 2), name="Nyi_x_C-eucd_xx_2")
        losses = tf.add(pos, neg, name="losses")
        loss = tf.reduce_mean(losses, name="loss")
        return loss

    def loss_with_step(self):
        margin = 5.0
        labels_t = self.y_
        labels_f = tf.subtract(1.0, self.y_, name="1-yi")          # labels_ = !labels;
        eucd2 = tf.pow(tf.subtract(self.o1, self.o2), 2)
        eucd2 = tf.reduce_sum(eucd2, 1)
        eucd = tf.sqrt(eucd2+1e-6, name="eucd")
        C = tf.constant(margin, name="C")
        pos = tf.multiply(labels_t, eucd, name="y_x_eucd")
        neg = tf.multiply(labels_f, tf.maximum(0.0, tf.subtract(C, eucd)), name="Ny_C-eucd")
        losses = tf.add(pos, neg, name="losses")
        loss = tf.reduce_mean(losses, name="loss")
        return loss

#visualize.py
from tensorflow.examples.tutorials.mnist import input_data

import numpy as np
import matplotlib.pyplot as plt
from matplotlib import offsetbox


def visualize(embed, x_test):

    # two ways of visualization: scale to fit [0,1] scale
    # feat = embed - np.min(embed, 0)
    # feat /= np.max(feat, 0)

    # two ways of visualization: leave with original scale
    feat = embed
    ax_min = np.min(embed,0)
    ax_max = np.max(embed,0)
    ax_dist_sq = np.sum((ax_max-ax_min)**2)

    plt.figure()
    ax = plt.subplot(111)
    shown_images = np.array([[1., 1.]])
    for i in range(feat.shape[0]):
        dist = np.sum((feat[i] - shown_images)**2, 1)
        if np.min(dist) < 3e-4*ax_dist_sq:   # don't show points that are too close
            continue
        shown_images = np.r_[shown_images, [feat[i]]]
        imagebox = offsetbox.AnnotationBbox(
            offsetbox.OffsetImage(x_test[i], zoom=0.6, cmap=plt.cm.gray_r),
            xy=feat[i], frameon=False
        )
        ax.add_artist(imagebox)

    plt.axis([ax_min[0], ax_max[0], ax_min[1], ax_max[1]])
    # plt.xticks([]), plt.yticks([])
    plt.title('Embedding from the last layer of the network')
    plt.show()

if __name__ == "__main__":

    mnist = input_data.read_data_sets('MNIST_data', one_hot=False)
    x_test = mnist.test.images
    x_test = x_test.reshape([-1, 28, 28])

    embed = np.fromfile('embed.txt', dtype=np.float32)
    embed = embed.reshape([-1, 2])

    visualize(embed, x_test)