Neekity的博客

from __future__ import print_functionimport tensorflow as tfhello = tf.constant('hello, tensorflow')sess = tf.Session()print(sess.run(hello))

Word2vec 之 Skip-Gram 模型from __future__ import division, print_function, absolute_importimport collectionsimport osimport randomimport urllib.requestimport zipfileimport numpy as npimport ten...

import numpy as npimport tensorflow as tfimport gymenv=gym.make('CartPole-v0')xs,ys,drs=[],[],[]reward_sum=0episode_number=1total_episodes=10000H=50batch_size=25learning_rate=0.1D=4gamma=...

DBNs（Deep Belief Networks）由多个限制玻尔兹曼机（Restricted Boltzmann Machines）层组成。先用自编码器的方法进行无监督的预训练，提取特征并初始化权重，然后使用标注信息进行监督式的训练。当然自编码器的作用不仅局限于给监督训练做预训练，直接使用自编码器进行特征提取和分析也是可以的。import numpy as npimport sklearn...

tf.nn.dropout(x, keep_prob)x：指输入keep_prob: 设置神经元被选中的概率import numpy as npimport sklearn.preprocessing as prepimport tensorflow as tffrom tensorflow.examples.tutorials.mnist import input_datamni...

卷积神经网络需要创建很多的权重和偏置，所以定义函数来重复调用。tf.nn.conv2d(x,w,strides=[1,1,1,1],padding=‘SAME’)x是输入，w是卷积的参数。w=[5,5,1,32]，5*5是卷积核的尺寸，1代表通道数（灰度是1，彩色RGB是3），32代表有32个卷积核数量。strides,表示移动步长，1为不遗漏图上的每一个点。padding='SAME’表示卷...

from tensorflow.examples.tutorials.mnist import input_datamnist = input_data.read_data_sets("MNIST_data/", one_hot=True)import tensorflow as tflearning_rate=0.001batch_size=100display_step=1mod...

加载模型时要先定义tensorflow计算图上的所有运算from tensorflow.examples.tutorials.mnist import input_datamnist = input_data.read_data_sets("MNIST_data/", one_hot=True)import tensorflow as tflearning_rate=0.001batch...

异或问题训练出来的值都是nan# -*- coding: utf-8 -*-import tensorflow as tfimport numpy as npimport matplotlib.pyplot as plttf.set_random_seed(55)np.random.seed(55)input_data = [[0., 0.], [0., 1.], [1., 0...

cifar10.maybe_download_and_extract() 默认在E:/tmp/中import syspath = r'E:\learn\pc_code\tensorflow\example\models-master\tutorials\image\cifar10'sys.path.append(path)import cifar10, cifar10_inputimp...

看了很多tensorflow 的KNN代码，基本就是下面原版代码的变种。很多人认为Xtr, Ytr = mnist.train.next_batch(5000) #5000 for training (nn candidates)这行代码就是超参数K=5000. 但我仍有疑问以下是我的见解，不正之处请指出。不知道是不是该这样理解。它这里选了5000个训练样本，200个测试样本。然后遍历200个测...

import pandas as pdimport numpy as npimport tensorflow as tf from sklearn import preprocessingfrom tensorflow.contrib.tensor_forest.python import tensor_forestfrom tensorflow.python.ops import re...

from __future__ import absolute_import, division, print_functionimport numpy as npimport tensorflow as tfimport tensorflow.contrib.eager as tfetfe.enable_eager_execution()a = tf.constant(2)pr...

from __function__ import print_function import tensorflow as tf a=tf.constant(2)b=tf.constant(3)with tf.Session() as sess: print('sess run ... a+b result: %i' % sess.run(a+b)) print('sess run .....

tf.reset_default_graph() 注意要重新设置一下图from __future__ import print_functionimport tensorflow as tffrom tensorflow.contrib.tensor_forest.python import tensor_forestfrom tensorflow.python.ops import r...

kaggle上泰坦尼克的年龄使用随机森林分类为什么准确率只有0.47import pandas as pdimport numpy as npimport tensorflow as tf from tensorflow.contrib.tensor_forest.python import tensor_forestfrom tensorflow.python.ops import ...

from __future__ import print_functionimport numpy as npimport tensorflow as tffrom tensorflow.examples.tutorials.mnist import input_datamnist=input_data.read_data_sets("/tmp/data/",one_hot=True)...

from __future__ import print_functionimport tensorflow as tfimport numpy as npimport matplotlib.pyplot as pltnr=np.randomlearning_rate = 0.01training_epochs=1000display_step=50train_X = np.a...

tf.cast 是转换类型from __future__ import print_functionimport tensorflow as tfimport numpy as npimport matplotlib.pyplot as pltfrom tensorflow.examples.tutorials.mnist import input_datamnist=input_da...

tf.nn.embedding_lookup：tf.nn.embedding_lookup()就是根据input_ids中的id，寻找embeddings中的第id行。比如input_ids=[1,3,5]，则找出embeddings中第1，3，5行，组成一个tensor返回。num_steps=500batch_size=1024k=25num_classes=10num_featu...

tensorboard --logdir=绝对路径import tensorflow as tffrom tensorflow.examples.tutorials.mnist import input_datamnist = input_data.read_data_sets("MNIST_data/", one_hot=True)import oslearning_rate = 0....

cross_entry的设置tensorflow 权重更新为nan的问题当用cifar10时，cross_entry=tf.reduce_mean(-tf.reduce_sum(y*tf.log(ylog),reduction_indices=1))无法更新权重，cross_entry=tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(...