基本信息
源码名称:Python实现的TensorFlow入门案例
源码大小:0.77KB
文件格式:.py
开发语言:Python
更新时间:2019-09-07
友情提示:(无需注册或充值,赞助后即可获取资源下载链接)
嘿,亲!知识可是无价之宝呢,但咱这精心整理的资料也耗费了不少心血呀。小小地破费一下,绝对物超所值哦!如有下载和支付问题,请联系我们QQ(微信同号):813200300
本次赞助数额为: 2 元×
微信扫码支付:2 元
×
请留下您的邮箱,我们将在2小时内将文件发到您的邮箱
源码介绍
本例介绍了TensorFlow的基本框架模型,用于入门再好不过!
# 1 collect data
x_data = np.float32(np.random.rand(200,2));
y_data = np.matmul(x_data,[[5.2],[9.6]]) 3.4;
# 2 Ceate model
W = tf.Variable(tf.random_uniform([2,1],-1,1));
b = tf.Variable(tf.zeros([1]));
y_ = tf.matmul(x_data,W) b;
# 3 loss function
loss = tf.reduce_mean(tf.square(y_-y_data));
optimizer = tf.train.GradientDescentOptimizer(0.5);
train = optimizer.minimize(loss);
# 4 Initialzer
init = tf.initialize_all_variables();
sess = tf.Session(config = tf.ConfigProto(allow_soft_placement=True,log_device_placement=True));
sess.run(init);
# 5 Train
for step in range(0,201):
sess.run(train);
if step%10 == 0:
print(step,np.transpose(sess.run(W)),sess.run(b));
# 6 Output
sess.close();
本例介绍了TensorFlow的基本框架模型,用于入门再好不过!
import tensorflow as tf
import numpy as np# 1 collect data
x_data = np.float32(np.random.rand(200,2));
y_data = np.matmul(x_data,[[5.2],[9.6]]) 3.4;
# 2 Ceate model
W = tf.Variable(tf.random_uniform([2,1],-1,1));
b = tf.Variable(tf.zeros([1]));
y_ = tf.matmul(x_data,W) b;
# 3 loss function
loss = tf.reduce_mean(tf.square(y_-y_data));
optimizer = tf.train.GradientDescentOptimizer(0.5);
train = optimizer.minimize(loss);
# 4 Initialzer
init = tf.initialize_all_variables();
sess = tf.Session(config = tf.ConfigProto(allow_soft_placement=True,log_device_placement=True));
sess.run(init);
# 5 Train
for step in range(0,201):
sess.run(train);
if step%10 == 0:
print(step,np.transpose(sess.run(W)),sess.run(b));
# 6 Output
sess.close();