seo优化网站教程百度,泰州企业做网站,昆山市建设局招投标网站,wordpress主题防修改文章目录 使用TensorFlow完成逻辑回归1. 环境设定2. 数据读取3. 准备好placeholder4. 准备好参数/权重5. 计算多分类softmax的loss function6. 准备好optimizer7. 在session里执行graph里定义的运算 附#xff1a;系列文章 使用TensorFlow完成逻辑回归
TensorFlow是一种开源的… 文章目录 使用TensorFlow完成逻辑回归1. 环境设定2. 数据读取3. 准备好placeholder4. 准备好参数/权重5. 计算多分类softmax的loss function6. 准备好optimizer7. 在session里执行graph里定义的运算 附系列文章 使用TensorFlow完成逻辑回归
TensorFlow是一种开源的机器学习框架由Google Brain团队于2015年开发。它被广泛应用于图像和语音识别、自然语言处理、推荐系统等领域。
TensorFlow的核心是用于计算的数据流图。在数据流图中节点表示数学操作边表示张量多维数组。将操作和数据组合在一起的数据流图可以使 TensorFlow 对复杂的数学模型进行优化同时支持分布式计算。
TensorFlow提供了PythonCJavaGo等多种编程语言的接口让开发者可以更便捷地使用TensorFlow构建和训练深度学习模型。此外TensorFlow还具有丰富的工具和库包括TensorBoard可视化工具、TensorFlow Serving用于生产环境的模型服务、Keras高层封装API等。
TensorFlow已经发展出了许多优秀的模型如卷积神经网络、循环神经网络、生成对抗网络等。这些模型已经在许多领域取得了优秀的成果如图像识别、语音识别、自然语言处理等。
除了开源的TensorFlowGoogle还推出了基于TensorFlow的云端机器学习平台Google Cloud ML为用户提供了更便捷的训练和部署机器学习模型的服务。
解决分类问题里最普遍的baseline model就是逻辑回归简单同时可解释性好使得它大受欢迎我们来用tensorflow完成这个模型的搭建。
1. 环境设定
import os
os.environ[TF_CPP_MIN_LOG_LEVEL]2import warnings
warnings.filterwarnings(ignore)import numpy as np
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
import time2. 数据读取
#使用tensorflow自带的工具加载MNIST手写数字集合
mnist input_data.read_data_sets(./data/mnist, one_hotTrue) Extracting ./data/mnist/train-images-idx3-ubyte.gz
Extracting ./data/mnist/train-labels-idx1-ubyte.gz
Extracting ./data/mnist/t10k-images-idx3-ubyte.gz
Extracting ./data/mnist/t10k-labels-idx1-ubyte.gz#查看一下数据维度
mnist.train.images.shape(55000, 784)#查看target维度
mnist.train.labels.shape(55000, 10)3. 准备好placeholder
batch_size 128
X tf.placeholder(tf.float32, [batch_size, 784], nameX_placeholder)
Y tf.placeholder(tf.int32, [batch_size, 10], nameY_placeholder)4. 准备好参数/权重
w tf.Variable(tf.random_normal(shape[784, 10], stddev0.01), nameweights)
b tf.Variable(tf.zeros([1, 10]), namebias)logits tf.matmul(X, w) b 5. 计算多分类softmax的loss function
# 求交叉熵损失
entropy tf.nn.softmax_cross_entropy_with_logits(logitslogits, labelsY, nameloss)
# 求平均
loss tf.reduce_mean(entropy)6. 准备好optimizer
这里的最优化用的是随机梯度下降我们可以选择AdamOptimizer这样的优化器
learning_rate 0.01
optimizer tf.train.AdamOptimizer(learning_rate).minimize(loss)7. 在session里执行graph里定义的运算
#迭代总轮次
n_epochs 30with tf.Session() as sess:# 在Tensorboard里可以看到图的结构writer tf.summary.FileWriter(../graphs/logistic_reg, sess.graph)start_time time.time()sess.run(tf.global_variables_initializer()) n_batches int(mnist.train.num_examples/batch_size)for i in range(n_epochs): # 迭代这么多轮total_loss 0for _ in range(n_batches):X_batch, Y_batch mnist.train.next_batch(batch_size)_, loss_batch sess.run([optimizer, loss], feed_dict{X: X_batch, Y:Y_batch}) total_loss loss_batchprint(Average loss epoch {0}: {1}.format(i, total_loss/n_batches))print(Total time: {0} seconds.format(time.time() - start_time))print(Optimization Finished!)# 测试模型preds tf.nn.softmax(logits)correct_preds tf.equal(tf.argmax(preds, 1), tf.argmax(Y, 1))accuracy tf.reduce_sum(tf.cast(correct_preds, tf.float32))n_batches int(mnist.test.num_examples/batch_size)total_correct_preds 0for i in range(n_batches):X_batch, Y_batch mnist.test.next_batch(batch_size)accuracy_batch sess.run([accuracy], feed_dict{X: X_batch, Y:Y_batch}) total_correct_preds accuracy_batch[0]print(Accuracy {0}.format(total_correct_preds/mnist.test.num_examples))writer.close()Average loss epoch 0: 0.36748782022571785 Average loss epoch 1: 0.2978815356126198 Average loss epoch 2: 0.27840628396797845 Average loss epoch 3: 0.2783186247437706 Average loss epoch 4: 0.2783641471138923 Average loss epoch 5: 0.2750668214473413 Average loss epoch 6: 0.2687560408126502 Average loss epoch 7: 0.2713795114126239 Average loss epoch 8: 0.2657588795522154 Average loss epoch 9: 0.26322007090686916 Average loss epoch 10: 0.26289192279735646 Average loss epoch 11: 0.26248606019989873 Average loss epoch 12: 0.2604622903056356 Average loss epoch 13: 0.26015280702939403 Average loss epoch 14: 0.2581879366319496 Average loss epoch 15: 0.2590309207117085 Average loss epoch 16: 0.2630510463581219 Average loss epoch 17: 0.25501730025578767 Average loss epoch 18: 0.2547102673000945 Average loss epoch 19: 0.258298404375851 Average loss epoch 20: 0.2549241428330784 Average loss epoch 21: 0.2546788509283866 Average loss epoch 22: 0.259556887067837 Average loss epoch 23: 0.25428259843365575 Average loss epoch 24: 0.25442713139565676 Average loss epoch 25: 0.2553852511383159 Average loss epoch 26: 0.2503043229415978 Average loss epoch 27: 0.25468004046828596 Average loss epoch 28: 0.2552785321479633 Average loss epoch 29: 0.2506257003663859 Total time: 28.603315353393555 seconds Optimization Finished! Accuracy 0.9187附系列文章
序号文章目录直达链接1波士顿房价预测https://want595.blog.csdn.net/article/details/1321819502鸢尾花数据集分析https://want595.blog.csdn.net/article/details/1321820573特征处理https://want595.blog.csdn.net/article/details/1321821654交叉验证https://want595.blog.csdn.net/article/details/1321822385构造神经网络示例https://want595.blog.csdn.net/article/details/1321823416使用TensorFlow完成线性回归https://want595.blog.csdn.net/article/details/1321824177使用TensorFlow完成逻辑回归https://want595.blog.csdn.net/article/details/1321824968TensorBoard案例https://want595.blog.csdn.net/article/details/1321825849使用Keras完成线性回归https://want595.blog.csdn.net/article/details/13218272310使用Keras完成逻辑回归https://want595.blog.csdn.net/article/details/13218279511使用Keras预训练模型完成猫狗识别https://want595.blog.csdn.net/article/details/13224392812使用PyTorch训练模型https://want595.blog.csdn.net/article/details/13224398913使用Dropout抑制过拟合https://want595.blog.csdn.net/article/details/13224411114使用CNN完成MNIST手写体识别(TensorFlow)https://want595.blog.csdn.net/article/details/13224449915使用CNN完成MNIST手写体识别(Keras)https://want595.blog.csdn.net/article/details/13224455216使用CNN完成MNIST手写体识别(PyTorch)https://want595.blog.csdn.net/article/details/13224464117使用GAN生成手写数字样本https://want595.blog.csdn.net/article/details/13224476418自然语言处理https://want595.blog.csdn.net/article/details/132276591
