喜欢猫吗?用这个开源工具撸一只吧!
【导读】我们身边总是不乏各种各样的撸猫人士,面对朋友圈一波又一波晒猫的浪潮,作为学生狗和工作狗的我们只有羡慕的份,更流传有 “吸猫穷三代,撸猫毁一生?” 的名言,今天小编就为广大爱猫人士发放一份福利,看看如何用 AI 来生成猫的图片?
用 DCGAN 生成的猫图片示例
领军研究员 Yann Lecun 称生成式对抗网络( Generative Adverserial Networks, GAN )是 “过去 20 年里机器学习中最棒的想法”。因为这种网络结构的出现,我们才能在今天搭建一个可以生成栩栩如生的猫图片的 AI 系统。这是不是很令人振奋?
DCGAN 的训练过程
完整代码(Github):
https://gist.github.com/simoninithomas/c7d1e80810ef838330d7dab068d6b26f#file-training-py
如果你使用过 Python、Tensorflow,学习过深度学习、CNNs(卷积神经网络),将对理解代码大有裨益。
▌什么是 DCGAN?
深度卷积生成对抗网络(Deep Convolutional Generative Adverserial Networks,DCGAN)是一种深度学习架构,它会生成和训练集中数据相似的结果。
这一模型用卷积层代替了生成对抗网络(GAN)模型中的全连接层。
为了解释 DCGAN 是如何运行的,我们用艺术专家和冒牌专家来做比喻。
冒牌专家( 即 “生成器” )企图模仿梵高的画作生成图片并把它当做真实的梵高作品。
而另一边,艺术专家( 即 “分类器” )试图利用它们对梵高画作的了解来识别出赝品( 即生成图片 )。
随着时间推移,艺术专家鉴别赝品的技术不断长进,冒牌专家仿作的能力也不断提高。
如我们所见,DCGANs 由两个互相对抗的深度神经网络组成。
- 生成器是一个仿造者,生成和真实数据相似的结果。它本身不知道真实数据是什么样,但会从另一个模型的反馈信息中学习和调整。
- 分类器是一个检测者,通过与真实数据比较来确定伪造数据(即模型生成的图片),但尽力不对真实数据报错。这一部分会为生成器的反向传播服务。
DCGAN 工作流程示例
- 生成器会加入随机噪声向量,生成图片;
- 这张图片被输入给分类器,和训练集进行比较;
- 最后分类器返回一个 0(伪造图像)和 1(真实图像)之间的数字。
▌让我们来创建 DCGAN 吧!
现在,我们可以准备创建 AI 了。
在这部分,我们将关注模型的主要元素。若你想看所有代码,请点这里的 notebook(https://github.com/simoninithomas/CatDCGAN/blob/master/Cat%20DCGAN.ipynb)。
输入部分
先创建输入占位符:分类器:inputs_real,生成器:inputs_z。
注意,我们用两个学习率,一个是生成器的学习率,一个是分类器的学习率。
DCGANs 对超参数特别敏感,所以精确调参尤其重要。
def model_inputs(real_dim, z_dim):
""" Create the model inputs
:param real_dim: tuple containing width, height and channels
:param z_dim: The dimension of Z
:return: Tuple of (tensor of real input images, tensor of z data, learning rate G, learning rate D)
""" # inputs_real for Discriminator
inputs_real = tf.placeholder(tf.float32, (None, *real_dim), name='inputs_real')
# inputs_z for Generator
inputs_z = tf.placeholder(tf.float32, (None, z_dim), name="input_z")
# Two different learning rate : one for the generator, one for the discriminator
learning_rate_G = tf.placeholder(tf.float32, name="learning_rate_G")
learning_rate_D = tf.placeholder(tf.float32, name="learning_rate_D")
return inputs_real, inputs_z, learning_rate_G, learning_rate_D
分类器和生成器
我们用函数 tf.variable_scope 的原因有两个:
- 第一,我们想要保证所有变量名称都以 generator 或 discriminator 开头,这将为我们之后训练两个网络提供帮助。
- 第二,我们要用不同的输入重复训练网络:对于生成器,既要训练它,也要在训练后从生成图像中采样;对于分类器,我们需要在生成图像和真实图像间共用变量。
我们先来创建分类器。记住,要用真实或生成图像作为输入,然后输出分数。
需要注意的技术点:
- 关键点是在每个卷积层加倍过滤器的尺寸;
- 不建议进行下采样,我们只用一定步长的卷积层;
- 每层都使用 batch 标准化(输入层除外),因为它会减小协方差转变。想了解更多信息的话请看这篇文章(https://medium.com/@ageitgey/machine-learning-is-fun-80ea3ec3c471)。
- 我们用 Leaky ReLU 作为激活函数,因为它能帮助避免梯度消失问题。
def discriminator(x, is_reuse=False, alpha = 0.2):
''' Build the discriminator network.
Arguments
---------
x : Input tensor for the discriminator
n_units: Number of units in hidden layer
reuse : Reuse the variables with tf.variable_scope
alpha : leak parameter for leaky ReLU
Returns
-------
out, logits:
'''
with tf.variable_scope("discriminator", reuse = is_reuse):
# Input layer 128*128*3 --> 64x64x64
# Conv --> BatchNorm --> LeakyReLU
conv1 = tf.layers.conv2d(inputs = x,
filters = 64,
kernel_size = [5,5],
strides = [2,2],
padding = "SAME",
kernel_initializer=tf.truncated_normal_initializer(stddev=0.02),
name='conv1')
batch_norm1 = tf.layers.batch_normalization(conv1,
training = True,
epsilon = 1e-5,
name = 'batch_norm1')
conv1_out = tf.nn.leaky_relu(batch_norm1, alpha=alpha, name="conv1_out")
# 64x64x64--> 32x32x128
# Conv --> BatchNorm --> LeakyReLU
conv2 = tf.layers.conv2d(inputs = conv1_out,
filters = 128,
kernel_size = [5, 5],
strides = [2, 2],
padding = "SAME",
kernel_initializer=tf.truncated_normal_initializer(stddev=0.02),
name='conv2')
batch_norm2 = tf.layers.batch_normalization(conv2,
training = True,
epsilon = 1e-5,
name = 'batch_norm2')
conv2_out = tf.nn.leaky_relu(batch_norm2, alpha=alpha, name="conv2_out")
# 32x32x128 --> 16x16x256
# Conv --> BatchNorm --> LeakyReLU
conv3 = tf.layers.conv2d(inputs = conv2_out,
filters = 256,
kernel_size = [5, 5],
strides = [2, 2],
padding = "SAME",
kernel_initializer=tf.truncated_normal_initializer(stddev=0.02),
name='conv3')
batch_norm3 = tf.layers.batch_normalization(conv3,
training = True,
epsilon = 1e-5,
name = 'batch_norm3')
conv3_out = tf.nn.leaky_relu(batch_norm3, alpha=alpha, name="conv3_out")
# 16x16x256 --> 16x16x512
# Conv --> BatchNorm --> LeakyReLU
conv4 = tf.layers.conv2d(inputs = conv3_out,
filters = 512,
kernel_size = [5, 5],
strides = [1, 1],
padding = "SAME",
kernel_initializer=tf.truncated_normal_initializer(stddev=0.02),
name='conv4')
batch_norm4 = tf.layers.batch_normalization(conv4,
training = True,
epsilon = 1e-5,
name = 'batch_norm4')
conv4_out = tf.nn.leaky_relu(batch_norm4, alpha=alpha, name="conv4_out")
# 16x16x512 --> 8x8x1024
# Conv --> BatchNorm --> LeakyReLU
conv5 = tf.layers.conv2d(inputs = conv4_out,
filters = 1024,
kernel_size = [5, 5],
strides = [2, 2],
padding = "SAME",
kernel_initializer=tf.truncated_normal_initializer(stddev=0.02),
name='conv5')
batch_norm5 = tf.layers.batch_normalization(conv5,
training = True,
epsilon = 1e-5,
name = 'batch_norm5')
conv5_out = tf.nn.leaky_relu(batch_norm5, alpha=alpha, name="conv5_out")
# Flatten it
flatten = tf.reshape(conv5_out, (-1, 8*8*1024))
# Logits
logits = tf.layers.dense(inputs = flatten,
units = 1,
activation = None)
out = tf.sigmoid(logits)
return out, logits
再来创建生成器。记住,用随机噪声向量(z)作为输入,根据转置的卷积层输出生成图像。
其主要思想是在每层将过滤器尺寸减半,而将图片尺寸加倍。研究已经发现,用 tanh 作为输出层的激活函数时,生成器的表现最好。
def generator(z, output_channel_dim, is_train=True):
''' Build the generator network.
Arguments
---------
z : Input tensor for the generator
output_channel_dim : Shape of the generator output
n_units : Number of units in hidden layer
reuse : Reuse the variables with tf.variable_scope
alpha : leak parameter for leaky ReLU
Returns
-------
out:
'''
with tf.variable_scope("generator", reuse= not is_train):
# First FC layer --> 8x8x1024
fc1 = tf.layers.dense(z, 8*8*1024)
# Reshape it
fc1 = tf.reshape(fc1, (-1, 8, 8, 1024))
# Leaky ReLU
fc1 = tf.nn.leaky_relu(fc1, alpha=alpha)
# Transposed conv 1 --> BatchNorm --> LeakyReLU
# 8x8x1024 --> 16x16x512
trans_conv1 = tf.layers.conv2d_transpose(inputs = fc1,
filters = 512,
kernel_size = [5,5],
strides = [2,2],
padding = "SAME",
kernel_initializer=tf.truncated_normal_initializer(stddev=0.02),
name="trans_conv1")
# Transposed conv 1 --> BatchNorm --> LeakyReLU
# 8x8x1024 --> 16x16x512
trans_conv1 = tf.layers.conv2d_transpose(inputs = fc1,
filters = 512,
kernel_size = [5,5],
strides = [2,2],
padding = "SAME",
kernel_initializer=tf.truncated_normal_initializer(stddev=0.02),
name="trans_conv1")
batch_trans_conv1 = tf.layers.batch_normalization(inputs = trans_conv1, training=is_train, epsilon=1e-5, name="batch_trans_conv1")
trans_conv1_out = tf.nn.leaky_relu(batch_trans_conv1, alpha=alpha, name="trans_conv1_out")
# Transposed conv 2 --> BatchNorm --> LeakyReLU
# 16x16x512 --> 32x32x256
trans_conv2 = tf.layers.conv2d_transpose(inputs = trans_conv1_out,
filters = 256,
kernel_size = [5,5],
strides = [2,2],
padding = "SAME",
kernel_initializer=tf.truncated_normal_initializer(stddev=0.02),
name="trans_conv2")
batch_trans_conv2 = tf.layers.batch_normalization(inputs = trans_conv2, training=is_train, epsilon=1e-5, name="batch_trans_conv2")
trans_conv2_out = tf.nn.leaky_relu(batch_trans_conv2, alpha=alpha, name="trans_conv2_out")
# Transposed conv 3 --> BatchNorm --> LeakyReLU
# 32x32x256 --> 64x64x128
trans_conv3 = tf.layers.conv2d_transpose(inputs = trans_conv2_out,
filters = 128,
kernel_size = [5,5],
strides = [2,2],
padding = "SAME",
kernel_initializer=tf.truncated_normal_initializer(stddev=0.02),
name="trans_conv3")
batch_trans_conv3 = tf.layers.batch_normalization(inputs = trans_conv3, training=is_train, epsilon=1e-5, name="batch_trans_conv3")
trans_conv3_out = tf.nn.leaky_relu(batch_trans_conv3, alpha=alpha, name="trans_conv3_out")
# Transposed conv 4 --> BatchNorm --> LeakyReLU
# 64x64x128 --> 128x128x64
trans_conv4 = tf.layers.conv2d_transpose(inputs = trans_conv3_out,
filters = 64,
kernel_size = [5,5],
strides = [2,2],
padding = "SAME",
kernel_initializer=tf.truncated_normal_initializer(stddev=0.02),
name="trans_conv4")
batch_trans_conv4 = tf.layers.batch_normalization(inputs = trans_conv4, training=is_train, epsilon=1e-5, name="batch_trans_conv4")
trans_conv4_out = tf.nn.leaky_relu(batch_trans_conv4, alpha=alpha, name="trans_conv4_out")
# Transposed conv 5 --> tanh
# 128x128x64 --> 128x128x3
logits = tf.layers.conv2d_transpose(inputs = trans_conv4_out,
filters = 3,
kernel_size = [5,5],
strides = [1,1],
padding = "SAME",
kernel_initializer=tf.truncated_normal_initializer(stddev=0.02),
name="logits")
out = tf.tanh(logits, name="out")
return out
▌分类器和生成器的损失
因为我们是同时训练分类器和生成器,因此,两个网络的损失都需要计算。
我们的目标是使分类器认为图片为真实图片时输出 “1”,认为图片是生成图片时输出 “ 0 ”。因此,我们需要设计能够反映这一特点的损失函数。
分类器的损失是真实和生成图片的损失之和:
d_loss = d_loss_real + d_loss_fake
d_loss_real 是分类器将真实图片错误地预测为生成图片时的损失。它的计算如下:
- 用 d_logits_real ,所有标签均为 1(因为所有数据都是真实的);
- labels = tf.ones_like (tensor) * (1 - smooth) ,使用标签平滑:也就是略微减小标签,例如从 1.0 变为 0.9 ,从而使分类器泛化地更好。
- d_loss_fake 是分类器预测一张图片为真实图片、但实际是生成图片时的损失。
- 用 d_logits_fake ,所有标签都为 0.
生成器的损失仍使用分类器中的 d_logits_fake ,但标签均为 1,因为生成器要迷惑分类器。
def model_loss(input_real, input_z, output_channel_dim, alpha):
"""
Get the loss for the discriminator and generator
:param input_real: Images from the real dataset
:param input_z: Z input
:param out_channel_dim: The number of channels in the output image
:return: A tuple of (discriminator loss, generator loss)
"""
# Generator network here g_model = generator(input_z, output_channel_dim)
# g_model is the generator output
# Discriminator network here d_model_real, d_logits_real = discriminator(input_real, alpha=alpha) d_model_fake, d_logits_fake = discriminator(g_model,is_reuse=True, alpha=alpha)
# Calculate losses d_loss_real = tf.reduce_mean(
tf.nn.sigmoid_cross_entropy_with_logits(logits=d_logits_real, labels=tf.ones_like(d_model_real))) d_loss_fake = tf.reduce_mean(
tf.nn.sigmoid_cross_entropy_with_logits(logits=d_logits_fake, labels=tf.zeros_like(d_model_fake))) d_loss = d_loss_real + d_loss_fake
g_loss = tf.reduce_mean(
tf.nn.sigmoid_cross_entropy_with_logits(logits=d_logits_fake, labels=tf.ones_like(d_model_fake)))
return d_loss, g_loss
▌优化器
计算损失后,我们需要分别更新生成器和分类器。
要更新生成器和分类器,我们需要在每部分用 tf.trainable_variables () 获取变量,这样便创建了一个包含已在图中定义好的所有变量的列表。
def model_optimizers(d_loss, g_loss, lr_D, lr_G, beta1):
"""
Get optimization operations
:param d_loss: Discriminator loss Tensor
:param g_loss: Generator loss Tensor
:param learning_rate: Learning Rate Placeholder
:param beta1: The exponential decay rate for the 1st moment in the optimizer
:return: A tuple of (discriminator training operation, generator training operation)
"""
# Get the trainable_variables, split into G and D parts t_vars = tf.trainable_variables()
g_vars = [var for var in t_vars if var.name.startswith("generator")]
d_vars = [var for var in t_vars if var.name.startswith("discriminator")]
update_ops = tf.get_collection(tf.GraphKeys.UPDATE_OPS)
# Generator update gen_updates = [op for op in update_ops if op.name.startswith('generator')]
# Optimizers with tf.control_dependencies(gen_updates):
d_train_opt = tf.train.AdamOptimizer(learning_rate=lr_D, beta1=beta1).minimize(d_loss, var_list=d_vars) g_train_opt = tf.train.AdamOptimizer(learning_rate=lr_G, beta1=beta1).minimize(g_loss, var_list=g_vars)
return d_train_opt, g_train_opt
▌训练
现在,我们来执行训练函数。
想法很简单:
- 每迭代 5 次保存一次模型;
- 每训练 10 个 batch 的图片就保存一张;
- 每迭代 15 次将 g_loss , d_loss 和生成图片可视化一次。这样做的原因很简单:显示太多图片的话,Jupyter Notebook 可能会出错。
- 或者,我们也可以直接通过加载保存的模型来查看图片(这样会节省 20h 的训练时间)。
def train(epoch_count, batch_size, z_dim, learning_rate_D, learning_rate_G, beta1, get_batches, data_shape, data_image_mode, alpha):
"""
Train the GAN
:param epoch_count: Number of epochs
:param batch_size: Batch Size
:param z_dim: Z dimension
:param learning_rate: Learning Rate
:param beta1: The exponential decay rate for the 1st moment in the optimizer
:param get_batches: Function to get batches
:param data_shape: Shape of the data
:param data_image_mode: The image mode to use for images ("RGB" or "L")
"""
# Create our input placeholders
input_images, input_z, lr_G, lr_D = model_inputs(data_shape[1:], z_dim)
# Losses
d_loss, g_loss = model_loss(input_images, input_z, data_shape[3], alpha)
# Optimizers
d_opt, g_opt = model_optimizers(d_loss, g_loss, lr_D, lr_G, beta1)
i = 0
version = "firstTrain"
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
# Saver
saver = tf.train.Saver()
num_epoch = 0
if from_checkpoint == True:
saver.restore(sess, "./models/model.ckpt")
show_generator_output(sess, 4, input_z, data_shape[3], data_image_mode, image_path, True, False)
else:
for epoch_i in range(epoch_count):
num_epoch += 1
if num_epoch % 5 == 0:
# Save model every 5 epochs
#if not os.path.exists("models/" + version):
# os.makedirs("models/" + version)
save_path = saver.save(sess, "./models/model.ckpt")
print("Model saved")
for batch_images in get_batches(batch_size):
# Random noise
batch_z = np.random.uniform(-1, 1, size=(batch_size, z_dim))
i += 1
# Run optimizers
_ = sess.run(d_opt, feed_dict={input_images: batch_images, input_z: batch_z, lr_D: learning_rate_D})
_ = sess.run(g_opt, feed_dict={input_images: batch_images, input_z: batch_z, lr_G: learning_rate_G})
if i % 10 == 0:
train_loss_d = d_loss.eval({input_z: batch_z, input_images: batch_images})
train_loss_g = g_loss.eval({input_z: batch_z})
# Save it
image_name = str(i) + ".jpg"
image_path = "./images/" + image_name
show_generator_output(sess, 4, input_z, data_shape[3], data_image_mode, image_path, True, False)
return losses, samples
▌怎样运行模型
你不能在自己的笔记本上运行这个模型 —— 除非你有自己的 GPU,或者准备好等个十来年。
因此,你最好用在线 GPU 服务,如 AWS 或者 FloydHub 。我个人训练这个 DCGAN 模型花了 20 个小时,用的是 Microsoft Azure 和他们的深度学习虚拟机。
Deep Learning Virtual Machine:
https://medium.com/@ageitgey/machine-learning-is-fun-80ea3ec3c471
作者 | Thomas Simonini
原文链接
https://medium.freecodecamp.org/how-ai-can-learn-to-generate-pictures-of-cats-ba692cb6eae4