本文使用的tensorflow版本：1.4
tensorflow安裝：pip install tensorflow
1、先來目睹一下效果吧
這篇文章講解了如何使用GAN來生成我們的手寫數字，我們首先來看看生成的效果吧：
10輪：
可以看到，在10輪的時候，我們的Generator生成的圖檔非常模糊，幾乎是無法用肉眼來分别數字的，到了第50輪的時候，已經初見雛形了，有一些數字比如1、4、5這些都可以很清楚的分辨出來，不過還并不是十分完美。到了100輪的時候，像數字8和9這些也基本能準确的生成了，而到200輪的時候，除去個别的以外，基本上都能正确的手寫出來了，由于時間的原因，沒有繼續訓練下去，如果大家感興趣，可以訓練更多輪，看看更好的效果。
2、思路解析
設定參數
本文設定的參數是，圖檔的大小是28*28，這是mnist圖檔的标準大小，後面是一些儲存模型的設定。我們總共的訓練輪數是500輪。在我們的Generator和Discriminator中，我們設定的是一個簡單的有兩層隐藏層的全連結神經網絡。對于Generator來說，輸入的的大小是[batch_size,z_size]，第一個隐藏層有150個神經元，第二個隐藏層有300個神經元，輸出的大小就是圖檔的size28*28。而對于Discriminator來說，我們的輸入的大小是[batch_size * 2,img_size]，因為我們要摻雜真實的img和Generator生成的img。第一個隐藏層有300個神經元，第二個隐藏層有150個神經元，輸出層隻有1個數，表示該圖檔為真實圖檔的機率。關于神經網絡的結構我們會在後面詳細講解。
img_height = 28img_width = 28img_size = img_height * img_width
to_train = Trueto_restore = Falseoutput_path = "output"# 總疊代次數500max_epoch = 500h1_size = 150h2_size = 300z_size = 100batch_size = 256
建立Generator
剛才也講到了，對于Generator來說，輸入的的大小是[batch_size,z_size]，第一個隐藏層有150個神經元，第二個隐藏層有300個神經元，輸出的大小就是圖檔的size28*28。總的來說，經過Generator，由[batch_size,z_size] 變為 [batch_size,img_size]
# generate (model 1)def build_generator(z_prior):
w1 = tf.Variable(tf.truncated_normal([z_size, h1_size], stddev=0.1), name="g_w1", dtype=tf.float32)
b1 = tf.Variable(tf.zeros([h1_size]), name="g_b1", dtype=tf.float32)
h1 = tf.nn.relu(tf.matmul(z_prior, w1) + b1)
w2 = tf.Variable(tf.truncated_normal([h1_size, h2_size], stddev=0.1), name="g_w2", dtype=tf.float32)
b2 = tf.Variable(tf.zeros([h2_size]), name="g_b2", dtype=tf.float32)
h2 = tf.nn.relu(tf.matmul(h1, w2) + b2)
w3 = tf.Variable(tf.truncated_normal([h2_size, img_size], stddev=0.1), name="g_w3", dtype=tf.float32)
b3 = tf.Variable(tf.zeros([img_size]), name="g_b3", dtype=tf.float32)
h3 = tf.matmul(h2, w3) + b3
x_generate = tf.nn.tanh(h3)
g_params = [w1, b1, w2, b2, w3, b3] return x_generate, g_params
建立Discrminator
而對于Discriminator來說，我們的輸入的大小是[batch_size * 2,img_size]，因為我們要摻雜真實的img和Generator生成的img。第一個隐藏層有300個神經元，第二個隐藏層有150個神經元，輸出層隻有1個數，表示該圖檔為真實圖檔的機率。要注意，我們的輸入和輸出是嚴格對應的，是以對于輸出成的輸出h3來說，前batch_size個代表着對真實圖檔的判别機率，而後batch_size代表着對Generator生成的圖檔的判别機率。這裡是用了一個tf.slice()函數，之前沒有接觸過，故在這裡做一下記錄：
1，函數原型 tf.slice(inputs,begin,size,name='')
2，用途：從inputs中抽取部分内容
inputs：可以是list,array,tensor
begin：n維清單，begin[i] 表示從inputs中第i維抽取資料時，相對0的起始偏移量，也就是從第i維的begin[i]開始抽取資料
size：n維清單，size[i]表示要抽取的第i維元素的數目
是以可以看到，最終y_data儲存的是真實圖檔的判别機率，這些值要越接近于1越好，而y_generated儲存的是Generator生成的圖檔的判别機率，這些值要越接近于0越好。
def build_discriminator(x_data, x_generated, keep_prob): # tf.concat
x_in = tf.concat([x_data, x_generated], 0)
w1 = tf.Variable(tf.truncated_normal([img_size, h2_size], stddev=0.1), name="d_w1", dtype=tf.float32)
b1 = tf.Variable(tf.zeros([h2_size]), name="d_b1", dtype=tf.float32)
h1 = tf.nn.dropout(tf.nn.relu(tf.matmul(x_in, w1) + b1), keep_prob)
w2 = tf.Variable(tf.truncated_normal([h2_size, h1_size], stddev=0.1), name="d_w2", dtype=tf.float32)
b2 = tf.Variable(tf.zeros([h1_size]), name="d_b2", dtype=tf.float32)
h2 = tf.nn.dropout(tf.nn.relu(tf.matmul(h1, w2) + b2), keep_prob)
w3 = tf.Variable(tf.truncated_normal([h1_size, 1], stddev=0.1), name="d_w3", dtype=tf.float32)
b3 = tf.Variable(tf.zeros([1]), name="d_b3", dtype=tf.float32)
h3 = tf.matmul(h2, w3) + b3
y_data = tf.nn.sigmoid(tf.slice(h3, [0, 0], [batch_size, -1], name=None))
y_generated = tf.nn.sigmoid(tf.slice(h3, [batch_size, 0], [-1, -1], name=None))
d_params = [w1, b1, w2, b2, w3, b3] return y_data, y_generated, d_params
儲存圖檔
關于儲存圖檔的代碼，我們這裡就不講了，這也不是重點，大家有興趣的話可以研究下：
def show_result(batch_res, fname, grid_size=(8, 8), grid_pad=5):
batch_res = 0.5 * batch_res.reshape((batch_res.shape[0], img_height, img_width)) + 0.5
img_h, img_w = batch_res.shape[1], batch_res.shape[2]
grid_h = img_h * grid_size[0] + grid_pad * (grid_size[0] - 1)
grid_w = img_w * grid_size[1] + grid_pad * (grid_size[1] - 1)
img_grid = np.zeros((grid_h, grid_w), dtype=np.uint8) for i, res in enumerate(batch_res): if i >= grid_size[0] * grid_size[1]: break
img = (res) * 255
img = img.astype(np.uint8)
row = (i // grid_size[0]) * (img_h + grid_pad)
col = (i % grid_size[1]) * (img_w + grid_pad)
img_grid[row:row + img_h, col:col + img_w] = img
imsave(fname, img_grid)
設定訓練目标
對于Discriminator來說，他希望能夠使二分類的結果越準确越好，即越能準确判别真實圖檔和Generator生成的圖檔越好，是以我們這裡使用類似于邏輯回歸中的損失函數，而對于Generator來說，它希望的是Discriminator無法分辨它生成的圖檔，是以它希望Discriminator能将它生成的圖檔越多的分類為真實圖檔，是以我們設定的訓練目标如下：
# 損失函數的設定
d_loss = - (tf.log(y_data) + tf.log(1 - y_generated))
g_loss = - tf.log(y_generated)
optimizer = tf.train.AdamOptimizer(0.0001)
# 兩個模型的優化函數
d_trainer = optimizer.minimize(d_loss, var_list=d_params)
g_trainer = optimizer.minimize(g_loss, var_list=g_params)
訓練
訓練其實很簡單，每次得到batch_size大小的樣本，先訓練一次Discriminator，然後再訓練我們的Generator
z_sample_val = np.random.normal(0, 1, size=(batch_size, z_size)).astype(np.float32)
steps = 60000 / batch_size for i in range(sess.run(global_step), max_epoch): for j in np.arange(steps): # for j in range(steps): print("epoch:%s, iter:%s" % (i, j)) # 每一步疊代，我們都會加載256個訓練樣本，然後執行一次train_step
x_value, _ = mnist.train.next_batch(batch_size)
x_value = 2 * x_value.astype(np.float32) - 1
z_value = np.random.normal(0, 1, size=(batch_size, z_size)).astype(np.float32) # 執行生成
sess.run(d_trainer,
feed_dict={x_data: x_value, z_prior: z_value, keep_prob: np.sum(0.7).astype(np.float32)}) # 執行判别 if j % 1 == 0:
sess.run(g_trainer,
feed_dict={x_data: x_value, z_prior: z_value, keep_prob: np.sum(0.7).astype(np.float32)})
3、完整代碼
本文涉及到的完整代碼如下：
import tensorflow as tffrom tensorflow.examples.tutorials.mnist import input_dataimport numpy as npfrom skimage.io import imsaveimport osimport shutil
img_height = 28img_width = 28img_size = img_height * img_width
to_train = Trueto_restore = Falseoutput_path = "output"# 總疊代次數500max_epoch = 500h1_size = 150h2_size = 300z_size = 100batch_size = 256# generate (model 1)def build_generator(z_prior):
w1 = tf.Variable(tf.truncated_normal([z_size, h1_size], stddev=0.1), name="g_w1", dtype=tf.float32)
b1 = tf.Variable(tf.zeros([h1_size]), name="g_b1", dtype=tf.float32)
h1 = tf.nn.relu(tf.matmul(z_prior, w1) + b1)
w2 = tf.Variable(tf.truncated_normal([h1_size, h2_size], stddev=0.1), name="g_w2", dtype=tf.float32)
b2 = tf.Variable(tf.zeros([h2_size]), name="g_b2", dtype=tf.float32)
h2 = tf.nn.relu(tf.matmul(h1, w2) + b2)
w3 = tf.Variable(tf.truncated_normal([h2_size, img_size], stddev=0.1), name="g_w3", dtype=tf.float32)
b3 = tf.Variable(tf.zeros([img_size]), name="g_b3", dtype=tf.float32)
h3 = tf.matmul(h2, w3) + b3
x_generate = tf.nn.tanh(h3)
g_params = [w1, b1, w2, b2, w3, b3] return x_generate, g_params# discriminator (model 2)def build_discriminator(x_data, x_generated, keep_prob): # tf.concat
x_in = tf.concat([x_data, x_generated], 0)
w1 = tf.Variable(tf.truncated_normal([img_size, h2_size], stddev=0.1), name="d_w1", dtype=tf.float32)
b1 = tf.Variable(tf.zeros([h2_size]), name="d_b1", dtype=tf.float32)
h1 = tf.nn.dropout(tf.nn.relu(tf.matmul(x_in, w1) + b1), keep_prob)
w2 = tf.Variable(tf.truncated_normal([h2_size, h1_size], stddev=0.1), name="d_w2", dtype=tf.float32)
b2 = tf.Variable(tf.zeros([h1_size]), name="d_b2", dtype=tf.float32)
h2 = tf.nn.dropout(tf.nn.relu(tf.matmul(h1, w2) + b2), keep_prob)
w3 = tf.Variable(tf.truncated_normal([h1_size, 1], stddev=0.1), name="d_w3", dtype=tf.float32)
b3 = tf.Variable(tf.zeros([1]), name="d_b3", dtype=tf.float32)
h3 = tf.matmul(h2, w3) + b3
y_data = tf.nn.sigmoid(tf.slice(h3, [0, 0], [batch_size, -1], name=None))
y_generated = tf.nn.sigmoid(tf.slice(h3, [batch_size, 0], [-1, -1], name=None))
d_params = [w1, b1, w2, b2, w3, b3] return y_data, y_generated, d_params#def show_result(batch_res, fname, grid_size=(8, 8), grid_pad=5):
batch_res = 0.5 * batch_res.reshape((batch_res.shape[0], img_height, img_width)) + 0.5
img_h, img_w = batch_res.shape[1], batch_res.shape[2]
grid_h = img_h * grid_size[0] + grid_pad * (grid_size[0] - 1)
grid_w = img_w * grid_size[1] + grid_pad * (grid_size[1] - 1)
img_grid = np.zeros((grid_h, grid_w), dtype=np.uint8) for i, res in enumerate(batch_res): if i >= grid_size[0] * grid_size[1]: break
img = (res) * 255
img = img.astype(np.uint8)
row = (i // grid_size[0]) * (img_h + grid_pad)
col = (i % grid_size[1]) * (img_w + grid_pad)
img_grid[row:row + img_h, col:col + img_w] = img
imsave(fname, img_grid)def train(): # load data（mnist手寫資料集）
mnist = input_data.read_data_sets('MNIST_data', one_hot=True)
x_data = tf.placeholder(tf.float32, [batch_size, img_size], name="x_data")
z_prior = tf.placeholder(tf.float32, [batch_size, z_size], name="z_prior")
keep_prob = tf.placeholder(tf.float32, name="keep_prob")
global_step = tf.Variable(0, name="global_step", trainable=False) # 建立生成模型
x_generated, g_params = build_generator(z_prior) # 建立判别模型
y_data, y_generated, d_params = build_discriminator(x_data, x_generated, keep_prob) # 損失函數的設定
d_loss = - (tf.log(y_data) + tf.log(1 - y_generated))
g_loss = - tf.log(y_generated)
optimizer = tf.train.AdamOptimizer(0.0001) # 兩個模型的優化函數
d_trainer = optimizer.minimize(d_loss, var_list=d_params)
g_trainer = optimizer.minimize(g_loss, var_list=g_params)
saver = tf.train.Saver() # 啟動預設圖
init = tf.global_variables_initializer()
sess = tf.Session() # 初始化
sess.run(init) if to_restore:
chkpt_fname = tf.train.latest_checkpoint(output_path)
saver.restore(sess, chkpt_fname) else: if os.path.exists(output_path):
shutil.rmtree(output_path)
z_sample_val = np.random.normal(0, 1, size=(batch_size, z_size)).astype(np.float32)
os.mkdir(output_path)
steps = 60000 / batch_size for i in range(sess.run(global_step), max_epoch): for j in np.arange(steps): # for j in range(steps):
print("epoch:%s, iter:%s" % (i, j)) # 每一步疊代，我們都會加載256個訓練樣本，然後執行一次train_step
x_value, _ = mnist.train.next_batch(batch_size)
x_value = 2 * x_value.astype(np.float32) - 1
z_value = np.random.normal(0, 1, size=(batch_size, z_size)).astype(np.float32) # 執行生成
sess.run(d_trainer,
feed_dict={x_data: x_value, z_prior: z_value, keep_prob: np.sum(0.7).astype(np.float32)}) # 執行判别 if j % 1 == 0:
sess.run(g_trainer,
feed_dict={x_data: x_value, z_prior: z_value, keep_prob: np.sum(0.7).astype(np.float32)})
x_gen_val = sess.run(x_generated, feed_dict={z_prior: z_sample_val})
show_result(x_gen_val, "output/sample{0}.jpg".format(i))
z_random_sample_val = np.random.normal(0, 1, size=(batch_size, z_size)).astype(np.float32)
x_gen_val = sess.run(x_generated, feed_dict={z_prior: z_random_sample_val})
show_result(x_gen_val, "output/random_sample{0}.jpg".format(i))
sess.run(tf.assign(global_step, i + 1))
saver.save(sess, os.path.join(output_path, "model"), global_step=global_step)if __name__ == '__main__':
train()
原文釋出時間為：2018-08-23
本文作者：文文
本文來自雲栖社群合作夥伴“
Python愛好者社群”，了解相關資訊可以關注“
”。