使用 CelebA Progressive GAN 模型生成人脸

在 TensorFlow.org 上查看

在 Google Colab 中运行

在 GitHub 上查看

下载笔记本

查看 TF Hub 模型

此 Colab 演示了基于生成对抗网络 (GAN) 的 TF Hub 模块的使用。该模块将来自称为潜在空间的 N 维向量映射到 RGB 图像。

提供了两个示例

• 映射来自潜在空间到图像，以及
• 给定目标图像，使用梯度下降找到生成与目标图像相似的图像的潜在向量。

可选先决条件

• 熟悉 低级 Tensorflow 概念。
• 生成对抗网络 在维基百科上。
• 关于 Progressive GAN 的论文：Progressive Growing of GANs for Improved Quality, Stability, and Variation。

更多模型

这里您可以找到目前托管在 tfhub.dev 上的所有可以生成图像的模型。

设置

# Install imageio for creating animations.
pip -q install imageio
pip -q install scikit-image
pip install git+https://github.com/tensorflow/docs

导入和函数定义

from absl import logging

import imageio
import PIL.Image
import matplotlib.pyplot as plt
import numpy as np

import tensorflow as tf
tf.random.set_seed(0)

import tensorflow_hub as hub
from tensorflow_docs.vis import embed
import time

try:
  from google.colab import files
except ImportError:
  pass

from IPython import display
from skimage import transform

# We could retrieve this value from module.get_input_shapes() if we didn't know
# beforehand which module we will be using.
latent_dim = 512


# Interpolates between two vectors that are non-zero and don't both lie on a
# line going through origin. First normalizes v2 to have the same norm as v1. 
# Then interpolates between the two vectors on the hypersphere.
def interpolate_hypersphere(v1, v2, num_steps):
  v1_norm = tf.norm(v1)
  v2_norm = tf.norm(v2)
  v2_normalized = v2 * (v1_norm / v2_norm)

  vectors = []
  for step in range(num_steps):
    interpolated = v1 + (v2_normalized - v1) * step / (num_steps - 1)
    interpolated_norm = tf.norm(interpolated)
    interpolated_normalized = interpolated * (v1_norm / interpolated_norm)
    vectors.append(interpolated_normalized)
  return tf.stack(vectors)

# Simple way to display an image.
def display_image(image):
  image = tf.constant(image)
  image = tf.image.convert_image_dtype(image, tf.uint8)
  return PIL.Image.fromarray(image.numpy())

# Given a set of images, show an animation.
def animate(images):
  images = np.array(images)
  converted_images = np.clip(images * 255, 0, 255).astype(np.uint8)
  imageio.mimsave('./animation.gif', converted_images)
  return embed.embed_file('./animation.gif')

logging.set_verbosity(logging.ERROR)

潜在空间插值

随机向量

两个随机初始化向量之间的潜在空间插值。我们将使用 TF Hub 模块 progan-128，其中包含一个预训练的 Progressive GAN。

progan = hub.load("https://tfhub.dev/google/progan-128/1").signatures['default']

2024-03-09 13:17:20.450855: E external/local_xla/xla/stream_executor/cuda/cuda_driver.cc:282] failed call to cuInit: CUDA_ERROR_NO_DEVICE: no CUDA-capable device is detected

def interpolate_between_vectors():
  v1 = tf.random.normal([latent_dim])
  v2 = tf.random.normal([latent_dim])

  # Creates a tensor with 25 steps of interpolation between v1 and v2.
  vectors = interpolate_hypersphere(v1, v2, 50)

  # Uses module to generate images from the latent space.
  interpolated_images = progan(vectors)['default']

  return interpolated_images

interpolated_images = interpolate_between_vectors()
animate(interpolated_images)

在潜在空间中查找最接近的向量

修复目标图像。例如，使用从模块生成的图像或上传您自己的图像。

image_from_module_space = True  # @param { isTemplate:true, type:"boolean" }

def get_module_space_image():
  vector = tf.random.normal([1, latent_dim])
  images = progan(vector)['default'][0]
  return images

def upload_image():
  uploaded = files.upload()
  image = imageio.imread(uploaded[list(uploaded.keys())[0]])
  return transform.resize(image, [128, 128])

if image_from_module_space:
  target_image = get_module_space_image()
else:
  target_image = upload_image()

display_image(target_image)

在定义目标图像和由潜在空间变量生成的图像之间的损失函数后，我们可以使用梯度下降来查找最小化损失的变量值。

tf.random.set_seed(42)
initial_vector = tf.random.normal([1, latent_dim])

display_image(progan(initial_vector)['default'][0])

def find_closest_latent_vector(initial_vector, num_optimization_steps,
                               steps_per_image):
  images = []
  losses = []

  vector = tf.Variable(initial_vector)  
  optimizer = tf.optimizers.Adam(learning_rate=0.01)
  loss_fn = tf.losses.MeanAbsoluteError(reduction="sum")

  for step in range(num_optimization_steps):
    if (step % 100)==0:
      print()
    print('.', end='')
    with tf.GradientTape() as tape:
      image = progan(vector.read_value())['default'][0]
      if (step % steps_per_image) == 0:
        images.append(image.numpy())
      target_image_difference = loss_fn(image, target_image[:,:,:3])
      # The latent vectors were sampled from a normal distribution. We can get
      # more realistic images if we regularize the length of the latent vector to 
      # the average length of vector from this distribution.
      regularizer = tf.abs(tf.norm(vector) - np.sqrt(latent_dim))

      loss = target_image_difference + regularizer
      losses.append(loss.numpy())
    grads = tape.gradient(loss, [vector])
    optimizer.apply_gradients(zip(grads, [vector]))

  return images, losses


num_optimization_steps=200
steps_per_image=5
images, loss = find_closest_latent_vector(initial_vector, num_optimization_steps, steps_per_image)

....................................................................................................
....................................................................................................

plt.plot(loss)
plt.ylim([0,max(plt.ylim())])

(0.0, 6696.3041717529295)

animate(np.stack(images))

将结果与目标进行比较

display_image(np.concatenate([images[-1], target_image], axis=1))

使用上述示例

如果图像来自模块空间，则下降速度很快，并收敛到一个合理的样本。尝试下降到不是来自模块空间的图像。只有当图像与训练图像空间相当接近时，下降才会收敛。

如何使其下降更快并得到更逼真的图像？您可以尝试

• 使用图像差异上的不同损失，例如二次损失，
• 在潜在向量上使用不同的正则化器，
• 在多次运行中从随机向量初始化，
• 等等。