0
推荐
1291
阅读
tensorflow 基础模型应用4 —— 卷积神经网络 【转】
v1.convolutional_networkfrom __future__ import print_function
import tensorflow as tf
# Import MNIST data
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("/tmp/data/", one_hot=True)
# Parameters
learning_rate = 0.001
training_iters = 200000
batch_si...
0
推荐
984
阅读
tensorflow 基础模型应用3 —— k-means 【转】
1.create样本import tensorflow as tf
import numpy as np
def create_samples(n_clusters, n_samples_per_cluster, n_features, embiggen_factor, seed):
np.random.seed(seed)
slices = []
centroids = []
# Create samples for each cluster
for i in range(n_clusters):
samples = tf...
0
推荐
907
阅读
tensorflow 基础模型应用2 —神经网络 【转自github+整理】
1.神经网络import tensorflow as tf
import numpy as np
import input_data
def init_weights(shape):
return tf.Variable(tf.random_normal(shape, stddev=0.01))
def model(X, w_h, w_o):
h = tf.nn.sigmoid(tf.matmul(X, w_h)) # this is a basic mlp, think 2 stacked logistic regressions
return ...
0
推荐
2740
阅读
tensorflow 基础模型应用1 ——回归 【转自github+整理】
1.一元线性回归import tensorflow as tf
import numpy as np
trx = np.linspace(-1,1,101) #np.linspace(2.0, 3.0, num=5) array([ 2. , 2.25, 2.5 , 2.75, 3. ])
try = 2*trx + np.random.randn(*trx.shape)*0.33 ## 构建y，近似线性但又有很多噪音
X = tf.placeholder("float")
Y = tf.placeholder("fl...
1
推荐
1452
阅读
tensorflow 基础操作 [转自github]
1.导入库import tensorflow as tf2.基础操作# The value returned by the constructor represents the output
# of the Constant op.a=tf.constant(2)
b=tf.constant(3)3.launch the default graphwith tf.Session() as sess:
print "a=2, b=3"
print "Addition with constants: %i" % sess.run(a+b)
print ...