cs20_8-1

Posted 2021-02-09 ls1314

1. VAE

1. lecture link: https://docs.google.com/presentation/d/1VSNlkGcR-b39tMcuREjzZdhYOPvoZudpcbuNlf5hOIM/edit#slide=id.g334db163d4_0_41
2. todo, 我打印了个pdf, tutorial to VAE

2. tensorflow distribution(并不是分布式！而是概率分布)

1. PPL(probabilities program language)
   • https://www.zhihu.com/question/59442141
   • http://webppl.org/ (体验下PPL)
2. tensorflow distribution
   • https://zhuanlan.zhihu.com/p/36032114
   • https://zhuanlan.zhihu.com/p/35782672
   • The TensorFlow Distributions library has moved to TensorFlow Probability

3. VAE in Tensorflow

1. 如下面测试代码

   import os
   
   os.environ["CUDA_VISIBLE_DEVICES"] = "0"
   #
   import tensorflow as tf
   import numpy as np
   import scipy.misc
   
   def make_prior(code_size=2):
     mean, stddev = tf.zeros([code_size]), tf.ones([code_size])
     return tfd.MultivariateNormalDiag(mean, stddev)
   
   def make_encoder(images, code_size=2):
     images = tf.layers.flatten(images)
     hidden = tf.layers.dense(images, 100, tf.nn.relu)
     mean = tf.layers.dense(hidden, code_size)
     stddev = tf.layers.dense(hidden, code_size, tf.nn.softplus)
     return tfd.MultivariateNormalDiag(mean, stddev)
   
   def make_decoder(code, data_shape=[28, 28]):
     hidden = tf.layers.dense(code, 100, tf.nn.relu)
     logit = tf.layers.dense(hidden, np.prod(data_shape))
     logit = tf.reshape(logit, [-1] + data_shape)
     return tfd.Independent(tfd.Bernoulli(logit), len(data_shape))
   
   tfd = tf.contrib.distributions
   images = tf.placeholder(tf.float32, [None, 28, 28])
   prior = make_prior()
   posterior = make_encoder(images)
   dist = make_decoder(posterior.sample())
   elbo = dist.log_prob(images) - tfd.kl_divergence(posterior, prior)
   optimize = tf.train.AdamOptimizer().minimize(-elbo)
   samples = make_decoder(prior.sample(10)).mean()  # For visualization
   print("samples-shape: ", tf.shape(samples))
   print("samples: : ", samples)
   # 转换shape 为 28x28xC //现在是 10x28x28，我要换成 28x28x10，利用 tf.transpose
   samples = tf.transpose(samples, [1,2,0])
   samples = samples[:][:][0] # 同理，使用 for 可以找出其他剩余9张图片
   print("samples-1: : ", samples)
   
   with tf.Session() as sess:
       sess.run(tf.initialize_all_variables())
       sess.run(tf.global_variables_initializer())
       img_numpy = samples.eval(session=sess) # tensor to numpy_arr
       print(type(img_numpy))
   scipy.misc.imsave('VAE_TF.png', img_numpy) # numpy_arr to image
   
   
   # The tfd.Independent(dist, 2) tells TensorFlow to treat the two innermost dimensions as
   #  data dimensions rather than batch dimensions
   # This means dist.log_prob(images) returns
   #  a number per images rather than per pixel
   # As the name tfd.Independent() says,
   # it's just summing the pixel log probabilities

4. BNN in Tensorflow

1. 如下示例代码：

   import os
   
   os.environ["CUDA_VISIBLE_DEVICES"] = "0"
   #
   import tensorflow as tf
   import numpy as np
   
   # Byase NN
   
   def define_network(images, num_classes=10):
     mean = tf.get_variable('mean', [28 * 28, num_classes])
     stddev = tf.get_variable('stddev', [28 * 28, num_classes])
     prior = tfd.MultivariateNormalDiag(
         tf.zeros_like(mean), tf.ones_like(stddev))
     posterior = tfd.MultivariateNormalDiag(mean, tf.nn.softplus(stddev))
     bias = tf.get_variable('bias', [num_classes])  # Or Bayesian, too
     logit = tf.nn.relu(tf.matmul(posterior.sample(), images) + bias)
     return tfd.Categorical(logit), posterior, prior
   
   tfd = tf.contrib.distributions
   images = None # to do
   label = None # to do
   
   dist, posterior, prior = define_network(images)
   elbo = (tf.reduce_mean(dist.log_prob(label)) -
           tf.reduce_mean(tfd.kl_divergence(posterior, prior)))