【Tensorflow+keras】Keras API两种训练GAN网络的方式
2023-09-14 09:12:40 时间
1 第一种 train_on_batch
(1)简介
github:https://github.com/eriklindernoren/Keras-GAN/tree/master/cgan
运行一批样品的单次梯度更新。该方法搭配keras的sequential API使用。
其他网络结构参考Keras API三种搭建神经网络的方式及以mnist举例实现
(2)举例实现
from __future__ import print_function, division
from tensorflow.keras.datasets import mnist
from tensorflow.keras.layers import Input, Dense, Reshape, Flatten, Dropout, multiply
from tensorflow.keras.layers import BatchNormalization, Activation, Embedding, ZeroPadding2D
from tensorflow.keras.layers import LeakyReLU
from tensorflow.keras.layers import UpSampling2D, Conv2D
from tensorflow.keras.models import Sequential, Model
from tensorflow.keras.optimizers import Adam
import matplotlib.pyplot as plt
import numpy as np
class CGAN():
def __init__(self):
# Input shape
self.img_rows = 28
self.img_cols = 28
self.channels = 1
self.img_shape = (self.img_rows, self.img_cols, self.channels)
self.num_classes = 10
self.latent_dim = 100
optimizer = Adam(0.0002, 0.5)
# Build and compile the discriminator
self.discriminator = self.build_discriminator()
self.discriminator.compile(loss=['binary_crossentropy'],
optimizer=optimizer,
metrics=['accuracy'])
# Build the generator
self.generator = self.build_generator()
# The generator takes noise and the target label as input
# and generates the corresponding digit of that label
noise = Input(shape=(self.latent_dim,))
label = Input(shape=(1,))
img = self.generator([noise, label])
# For the combined model we will only train the generator
self.discriminator.trainable = False
# The discriminator takes generated image as input and determines validity
# and the label of that image
valid = self.discriminator([img, label])
# The combined model (stacked generator and discriminator)
# Trains generator to fool discriminator
self.combined = Model([noise, label], valid)
self.combined.compile(loss=['binary_crossentropy'],
optimizer=optimizer)
def build_generator(self):
model = Sequential()
model.add(Dense(256, input_dim=self.latent_dim))
model.add(LeakyReLU(alpha=0.2))
model.add(BatchNormalization(momentum=0.8))
model.add(Dense(512))
model.add(LeakyReLU(alpha=0.2))
model.add(BatchNormalization(momentum=0.8))
model.add(Dense(1024))
model.add(LeakyReLU(alpha=0.2))
model.add(BatchNormalization(momentum=0.8))
model.add(Dense(np.prod(self.img_shape), activation='tanh'))
model.add(Reshape(self.img_shape))
model.summary()
noise = Input(shape=(self.latent_dim,))
label = Input(shape=(1,), dtype='int32')
label_embedding = Flatten()(Embedding(self.num_classes, self.latent_dim)(label))
model_input = multiply([noise, label_embedding])
img = model(model_input)
return Model([noise, label], img)
def build_discriminator(self):
model = Sequential()
model.add(Dense(512, input_dim=np.prod(self.img_shape)))
model.add(LeakyReLU(alpha=0.2))
model.add(Dense(512))
model.add(LeakyReLU(alpha=0.2))
model.add(Dropout(0.4))
model.add(Dense(512))
model.add(LeakyReLU(alpha=0.2))
model.add(Dropout(0.4))
model.add(Dense(1, activation='sigmoid'))
model.summary()
img = Input(shape=self.img_shape)
label = Input(shape=(1,), dtype='int32')
label_embedding = Flatten()(Embedding(self.num_classes, np.prod(self.img_shape))(label))
flat_img = Flatten()(img)
model_input = multiply([flat_img, label_embedding])
validity = model(model_input)
return Model([img, label], validity)
def train(self, epochs, batch_size=128, sample_interval=50):
# Load the dataset
(X_train, y_train), (_, _) = mnist.load_data()
# Configure input
X_train = (X_train.astype(np.float32) - 127.5) / 127.5
X_train = np.expand_dims(X_train, axis=3)
y_train = y_train.reshape(-1, 1)
# Adversarial ground truths
valid = np.ones((batch_size, 1))
fake = np.zeros((batch_size, 1))
for epoch in range(epochs):
# ---------------------
# Train Discriminator
# ---------------------
# Select a random half batch of images
idx = np.random.randint(0, X_train.shape[0], batch_size)
imgs, labels = X_train[idx], y_train[idx]
# Sample noise as generator input
noise = np.random.normal(0, 1, (batch_size, 100))
# Generate a half batch of new images
gen_imgs = self.generator.predict([noise, labels])
# Train the discriminator
d_loss_real = self.discriminator.train_on_batch([imgs, labels], valid)
#train_on_batch返回值 为长度为2的列表, d_loss_real[0]为loss, d_loss_real[1]为accuracy
d_loss_fake = self.discriminator.train_on_batch([gen_imgs, labels], fake)
d_loss = 0.5 * np.add(d_loss_real, d_loss_fake)
# ---------------------
# Train Generator
# ---------------------
# Condition on labels
sampled_labels = np.random.randint(0, 10, batch_size).reshape(-1, 1)
# Train the generator
g_loss = self.combined.train_on_batch([noise, sampled_labels], valid)
# Plot the progress
print ("%d [D loss: %f, acc.: %.2f%%] [G loss: %f]" % (epoch, d_loss[0], 100*d_loss[1], g_loss))
# If at save interval => save generated image samples
if epoch % sample_interval == 0:
self.sample_images(epoch)
def sample_images(self, epoch):
r, c = 2, 5
noise = np.random.normal(0, 1, (r * c, 100))
sampled_labels = np.arange(0, 10).reshape(-1, 1)
gen_imgs = self.generator.predict([noise, sampled_labels])
# Rescale images 0 - 1
gen_imgs = 0.5 * gen_imgs + 0.5
fig, axs = plt.subplots(r, c)
cnt = 0
for i in range(r):
for j in range(c):
axs[i,j].imshow(gen_imgs[cnt,:,:,0], cmap='gray')
axs[i,j].set_title("Digit: %d" % sampled_labels[cnt])
axs[i,j].axis('off')
cnt += 1
fig.savefig("images/%d.png" % epoch)
plt.close()
if __name__ == '__main__':
cgan = CGAN()
cgan.train(epochs=1000, batch_size=32, sample_interval=200)
2 第二种 tf.GradientTape()
参考:https://www.tensorflow.org/guide/keras/customizing_what_happens_in_fit
(1)搭建网络
from tensorflow.keras import layers
# Create the discriminator
discriminator = keras.Sequential(
[
keras.Input(shape=(28, 28, 1)),
layers.Conv2D(64, (3, 3), strides=(2, 2), padding="same"),
layers.LeakyReLU(alpha=0.2),
layers.Conv2D(128, (3, 3), strides=(2, 2), padding="same"),
layers.LeakyReLU(alpha=0.2),
layers.GlobalMaxPooling2D(),
layers.Dense(1),
],
name="discriminator",
)
# Create the generator
latent_dim = 128
generator = keras.Sequential(
[
keras.Input(shape=(latent_dim,)),
# We want to generate 128 coefficients to reshape into a 7x7x128 map
layers.Dense(7 * 7 * 128),
layers.LeakyReLU(alpha=0.2),
layers.Reshape((7, 7, 128)),
layers.Conv2DTranspose(128, (4, 4), strides=(2, 2), padding="same"),
layers.LeakyReLU(alpha=0.2),
layers.Conv2DTranspose(128, (4, 4), strides=(2, 2), padding="same"),
layers.LeakyReLU(alpha=0.2),
layers.Conv2D(1, (7, 7), padding="same", activation="sigmoid"),
],
name="generator",
)
#训练网络
class GAN(keras.Model):
def __init__(self, discriminator, generator, latent_dim):
super(GAN, self).__init__()
self.discriminator = discriminator
self.generator = generator
self.latent_dim = latent_dim
def compile(self, d_optimizer, g_optimizer, loss_fn):
super(GAN, self).compile()
self.d_optimizer = d_optimizer
self.g_optimizer = g_optimizer
self.loss_fn = loss_fn
def train_step(self, real_images):
if isinstance(real_images, tuple):
real_images = real_images[0]
# Sample random points in the latent space
batch_size = tf.shape(real_images)[0]
random_latent_vectors = tf.random.normal(shape=(batch_size, self.latent_dim))
# Decode them to fake images
generated_images = self.generator(random_latent_vectors)
# Combine them with real images
combined_images = tf.concat([generated_images, real_images], axis=0)
# Assemble labels discriminating real from fake images
labels = tf.concat(
[tf.ones((batch_size, 1)), tf.zeros((batch_size, 1))], axis=0
)
# Add random noise to the labels - important trick!
labels += 0.05 * tf.random.uniform(tf.shape(labels))
# Train the discriminator
with tf.GradientTape() as tape:
predictions = self.discriminator(combined_images)
d_loss = self.loss_fn(labels, predictions)
grads = tape.gradient(d_loss, self.discriminator.trainable_weights)
self.d_optimizer.apply_gradients(
zip(grads, self.discriminator.trainable_weights)
)
# Sample random points in the latent space
random_latent_vectors = tf.random.normal(shape=(batch_size, self.latent_dim))
# Assemble labels that say "all real images"
misleading_labels = tf.zeros((batch_size, 1))
# Train the generator (note that we should *not* update the weights
# of the discriminator)!
with tf.GradientTape() as tape:
predictions = self.discriminator(self.generator(random_latent_vectors))
g_loss = self.loss_fn(misleading_labels, predictions)
grads = tape.gradient(g_loss, self.generator.trainable_weights)
self.g_optimizer.apply_gradients(zip(grads, self.generator.trainable_weights))
return {"d_loss": d_loss, "g_loss": g_loss}
#测试网络
batch_size = 64
(x_train, _), (x_test, _) = keras.datasets.mnist.load_data()
all_digits = np.concatenate([x_train, x_test])
all_digits = all_digits.astype("float32") / 255.0
all_digits = np.reshape(all_digits, (-1, 28, 28, 1))
dataset = tf.data.Dataset.from_tensor_slices(all_digits)
dataset = dataset.shuffle(buffer_size=1024).batch(batch_size)
gan = GAN(discriminator=discriminator, generator=generator, latent_dim=latent_dim)
gan.compile(
d_optimizer=keras.optimizers.Adam(learning_rate=0.0003),
g_optimizer=keras.optimizers.Adam(learning_rate=0.0003),
loss_fn=keras.losses.BinaryCrossentropy(from_logits=True),
)
相关文章
- keras2.2.4使用resnet101网络和预训练模型
- 5300亿NLP模型“威震天-图灵”发布,由4480块A100训练,微软英伟达联合出品
- 2023年!自然语言处理(NLP)10 大预训练模型
- Play.ht训练出播客乔布斯/用嘴做视频?Meta出品/我国牵头发布首个自动驾驶测试场景领域国际标准
- Diffusion预训练成本降低6.5倍,微调硬件成本降低7倍!Colossal-AI完整开源方案低成本加速AIGC产业落地
- 原创 | 利用BERT 训练推特上COVID-19数据
- NeurIPS 2022 | 四分钟内就能训练目标检测器,商汤基模型团队是怎么做到的?
- Patterns | 自监督图预训练模型整合大规模分子网络以探寻疾病相关基因的内在互作机制
- 提升网络训练的准确率
- 特定领域知识图谱融合方案:文本匹配算法之预训练Simbert、ERNIE-Gram单塔模型等诸多模型【三】
- 第十四届蓝桥杯集训——练习解题阶段(无序阶段)-ALGO-5 算法训练 最短路
- 络训练Linux520网络技能大赛:学习、提高、胜出(linux520网)