1. VAE

lecture link: https://docs.google.com/presentation/d/1VSNlkGcR-b39tMcuREjzZdhYOPvoZudpcbuNlf5hOIM/edit#slide=id.g334db163d4_0_41

todo, 我打印了個pdf, tutorial to VAE

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

PPL(probabilities program language)

• https://www.zhihu.com/question/59442141
• http://webppl.org/ (體驗下PPL)

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

如下面測試代碼

import osos.environ["CUDA_VISIBLE_DEVICES"] = "0" # import tensorflow as tf import numpy as np import scipy.miscdef 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) # 轉(zhuǎn)換shape 為 28x28xC //現(xiàn)在是 10x28x28，我要換成 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張圖片 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_arrprint(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

如下示例代碼：

import osos.environ["CUDA_VISIBLE_DEVICES"] = "0" # import tensorflow as tf import numpy as np# Byase NNdef 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, toologit = tf.nn.relu(tf.matmul(posterior.sample(), images) + bias)return tfd.Categorical(logit), posterior, priortfd = tf.contrib.distributions images = None # to do label = None # to dodist, posterior, prior = define_network(images) elbo = (tf.reduce_mean(dist.log_prob(label)) -tf.reduce_mean(tfd.kl_divergence(posterior, prior)))

轉(zhuǎn)載于:https://www.cnblogs.com/LS1314/p/10371229.html

總結(jié)

以上是生活随笔為你收集整理的cs20_8-1的全部內(nèi)容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網(wǎng)站內(nèi)容還不錯，歡迎將生活随笔推薦給好友。