华为云AI-深度学习糖尿病预测

Posted 2021-01-24

#!/usr/bin/env python2
# -*- coding: utf-8 -*-
"""
Created on Sat Sep 15 10:54:53 2018
@author: myhaspl
@email:[email protected]
糖尿病预测（多层）
csv格式：怀孕次数、葡萄糖、血压、皮肤厚度，胰岛素,bmi,糖尿病血统函数,年龄,结果
"""

import tensorflow as tf
import os

trainCount=10000
inputNodeCount=8
validateCount=50
sampleCount=200
testCount=10
outputNodeCount=1

g=tf.Graph()
with g.as_default():

    def getWeights(shape,wname):
        weights=tf.Variable(tf.truncated_normal(shape,stddev=0.1),name=wname)
        return weights

    def getBias(shape,bname):
        biases=tf.Variable(tf.constant(0.1,shape=shape),name=bname)
        return biases

    def inferenceInput(x):
        layer1=tf.nn.relu(tf.add(tf.matmul(x,w1),b1))    
        result=tf.add(tf.matmul(layer1,w2),b2)
        return result

    def inference(x):
        yp=inferenceInput(x)
        return tf.sigmoid(yp)

    def loss():
        yp=inferenceInput(x)
        return tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(labels=y,logits=yp))

    def train(learningRate,trainLoss,trainStep):
        trainOp=tf.train.AdamOptimizer(learningRate).minimize(trainLoss,global_step=trainStep)
        return trainOp

    def evaluate(x):
        return tf.cast(inference(x)>0.5,tf.float32)

    def accuracy(x,y,count):
        yp=evaluate(x)
        return tf.reduce_mean(tf.cast(tf.equal(yp,y),tf.float32))

    def inputFromFile(fileName,skipLines=1):
        #生成文件名队列
        fileNameQueue=tf.train.string_input_producer([fileName])
        #生成记录键值对
        reader=tf.TextLineReader(skip_header_lines=skipLines)
        key,value=reader.read(fileNameQueue)
        return value

    def getTestData(fileName,skipLines=1,n=10):
        #生成文件名队列
        testFileNameQueue=tf.train.string_input_producer([fileName])
        #生成记录键值对
        testReader=tf.TextLineReader(skip_header_lines=skipLines)
        testKey,testValue=testReader.read(testFileNameQueue)
        testRecordDefaults=[[1.],[1.],[1.],[1.],[1.],[1.],[1.],[1.],[1.]]
        testDecoded=tf.decode_csv(testValue,record_defaults=testRecordDefaults)
        pregnancies,glucose,bloodPressure,skinThickness,insulin,bmi,diabetespedigreefunction,age,outcome=tf.train.shuffle_batch(testDecoded,batch_size=n,capacity=1000,min_after_dequeue=1)    
        testFeatures=tf.transpose(tf.stack([pregnancies,glucose,bloodPressure,skinThickness,insulin,bmi,diabetespedigreefunction,age]))
        testY=tf.transpose([outcome])
        return (testFeatures,testY)

    def getNextBatch(n,values):
        recordDefaults=[[1.],[1.],[1.],[1.],[1.],[1.],[1.],[1.],[1.]]
        decoded=tf.decode_csv(values,record_defaults=recordDefaults)
        pregnancies,glucose,bloodPressure,skinThickness,insulin,bmi,diabetespedigreefunction,age,outcome=tf.train.shuffle_batch(decoded,batch_size=n,capacity=1000,min_after_dequeue=1)    
        features=tf.transpose(tf.stack([pregnancies,glucose,bloodPressure,skinThickness,insulin,bmi,diabetespedigreefunction,age]))
        y=tf.transpose([outcome])
        return (features,y) 

    with tf.name_scope("inputSample"): 
        samples=inputFromFile("s3://myhaspl/tf_learn/diabetes.csv",1)
        inputDs=getNextBatch(sampleCount,samples)  
        with tf.name_scope("validateSamples"):
            validateInputs=getNextBatch(validateCount,samples)

    with tf.name_scope("testSamples"):  
        testInputs=getTestData("s3://myhaspl/tf_learn/diabetes_test.csv")

    with tf.name_scope("inputDatas"):
        x=tf.placeholder(dtype=tf.float32,shape=[None,inputNodeCount],name="input_x")
        y=tf.placeholder(dtype=tf.float32,shape=[None,outputNodeCount],name="input_y")

    with tf.name_scope("Variable"):
        w1=getWeights([inputNodeCount,12],"w1")
        b1=getBias((),"b1")       
        w2=getWeights([12,outputNodeCount],"w2")
        b2=getBias((),"b2")       
        trainStep=tf.Variable(0,dtype=tf.int32,name="tcount",trainable=False)      

    with tf.name_scope("train"):
        trainLoss=loss()    
        trainOp=train(0.005,trainLoss,trainStep)
        init=tf.global_variables_initializer()         

with tf.Session(graph=g) as sess:    
    sess.run(init)

    coord = tf.train.Coordinator()
    threads = tf.train.start_queue_runners(coord=coord)

    while trainStep.eval()<trainCount: 

        sampleX,sampleY=sess.run(inputDs)
        sess.run(trainOp,feed_dict={x:sampleX,y:sampleY})
        nowStep=sess.run(trainStep)
        if nowStep%500==0:
            validate_acc=sess.run(accuracy(sampleX,sampleY,sampleCount))
            print "%d次后=>正确率%g"%(nowStep,validate_acc)
        if nowStep>trainCount:
            break

    testInputX,testInputY=sess.run(testInputs)
    print "测试样本正确率%g"%sess.run(accuracy(testInputX,testInputY,testCount))
    print testInputX,testInputY
    print sess.run(evaluate(testInputX))

    coord.request_stop()
    coord.join(threads) 

500次后=>正确率0.67
1000次后=>正确率0.75
1500次后=>正确率0.81
2000次后=>正确率0.75
2500次后=>正确率0.775
3000次后=>正确率0.765
3500次后=>正确率0.84
4000次后=>正确率0.85
4500次后=>正确率0.77
5000次后=>正确率0.78
5500次后=>正确率0.775
6000次后=>正确率0.835
6500次后=>正确率0.84
7000次后=>正确率0.785
7500次后=>正确率0.805
8000次后=>正确率0.765
8500次后=>正确率0.83
9000次后=>正确率0.835
9500次后=>正确率0.78
10000次后=>正确率0.775
测试样本正确率0.7
[[1.00e+01 1.01e+02 7.60e+01 4.80e+01 1.80e+02 3.29e+01 1.71e-01 6.30e+01]
 [3.00e+00 7.80e+01 5.00e+01 3.20e+01 8.80e+01 3.10e+01 2.48e-01 2.60e+01]
 [2.00e+00 1.22e+02 7.00e+01 2.70e+01 0.00e+00 3.68e+01 3.40e-01 2.70e+01]
 [2.00e+00 8.80e+01 5.80e+01 2.60e+01 1.60e+01 2.84e+01 7.66e-01 2.20e+01]
 [1.00e+01 1.01e+02 7.60e+01 4.80e+01 1.80e+02 3.29e+01 1.71e-01 6.30e+01]
 [2.00e+00 1.22e+02 7.00e+01 2.70e+01 0.00e+00 3.68e+01 3.40e-01 2.70e+01]
 [1.00e+00 8.90e+01 6.60e+01 2.30e+01 9.40e+01 2.81e+01 1.67e-01 2.10e+01]
 [6.00e+00 1.48e+02 7.20e+01 3.50e+01 0.00e+00 3.36e+01 6.27e-01 5.00e+01]
 [1.00e+00 9.30e+01 7.00e+01 3.10e+01 0.00e+00 3.04e+01 3.15e-01 2.30e+01]
 [2.00e+00 1.22e+02 7.00e+01 2.70e+01 0.00e+00 3.68e+01 3.40e-01 2.70e+01]] [[0.]
 [1.]
 [0.]
 [0.]
 [0.]
 [0.]
 [0.]
 [1.]
 [0.]
 [0.]]
[[1.]
 [0.]
 [0.]
 [0.]
 [1.]
 [0.]
 [0.]
 [1.]
 [0.]
 [0.]]

感觉华为云中提供的深度学习服务，就是给你提供一个强大的服务器，然后，你自己编写代码。可能还提供了一些更多的功能

另外，提供了一个训练用户自定义数据的代码
补充一个概念：
MoXing是华为云深度学习服务提供的网络模型开发API。相对于TensorFlow和MXNet等原生API而言，MoXing API让模型的代码编写更加简单，而且能够自动获取高性能的分布式执行能力。

MoXing允许用户只需要关心数据输入(input_fn)和模型构建(model_fn)的代码，就可以实现任意模型在多GPU和分布式下的高性能运行。MoXing-TensorFlow支持原生TensorFlow、Keras、slim等API，帮助构建图像分类、物体检测、生成对抗、自然语言处理和OCR等多种模型。

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

import tensorflow as tf
import moxing.tensorflow as mox
slim = tf.contrib.slim

# 用TensorFlow原生的方式定义超参
tf.flags.DEFINE_string(‘data_url‘, None, ‘‘)
tf.flags.DEFINE_string(‘train_dir‘, None, ‘‘)

flags = tf.flags.FLAGS

def train_my_model():

  def input_fn(run_mode, **kwargs):
    # 从TFRecord中获取输入数据集
    keys_to_features = {
      ‘image/encoded‘: tf.FixedLenFeature((), tf.string, default_value=‘‘),
      ‘image/format‘: tf.FixedLenFeature((), tf.string, default_value=‘raw‘),
      ‘image/class/label‘: tf.FixedLenFeature(
        [1], tf.int64, default_value=tf.zeros([1], dtype=tf.int64)),
    }

    items_to_handlers = {
      ‘image‘: slim.tfexample_decoder.Image(shape=[28, 28, 1], channels=1),
      ‘label‘: slim.tfexample_decoder.Tensor(‘image/class/label‘, shape=[]),
    }
    # 数据集中包含60000张训练集图像（数据文件名为mnist_train.tfrecord）
    # 以及10000张验证集图像（数据文件名为mnist_test.tfrecord）
    dataset = mox.get_tfrecord(dataset_dir=flags.data_url,
                               file_pattern=‘mnist_train.tfrecord‘ if run_mode == mox.ModeKeys.TRAIN else ‘mnist_test.tfrecord‘,
                               num_samples=60000 if run_mode == mox.ModeKeys.TRAIN else 10000,
                               keys_to_features=keys_to_features,
                               items_to_handlers=items_to_handlers,
                               capacity=1000)

    image, label = dataset.get([‘image‘, ‘label‘])
    # 将图像像素值转换为float并统一大小
    image = tf.to_float(image)
    image = tf.image.resize_image_with_crop_or_pad(image, 28, 28)
    return image, label

  def model_fn(inputs, run_mode, **kwargs):
    # 获取一批输入数据
    images, labels = inputs
    # 将输入图像进行归一化
    images = tf.subtract(images, 128.0)
    images = tf.div(images, 128.0)
    # 定义函数参数作用域：
    # 1. 所有的卷积和全链接L2正则项系数为0
    # 2. 所有的卷积和全链接使用截断正态分布初始化待训练变量
    # 3. 所有的卷积和全链接的激活层采用ReLU
    with slim.arg_scope(
        [slim.conv2d, slim.fully_connected],
        weights_regularizer=slim.l2_regularizer(scale=0.0),
        weights_initializer=tf.truncated_normal_initializer(stddev=0.1),
        activation_fn=tf.nn.relu):
      # 定义网络
      net = slim.conv2d(images, 32, [5, 5])
      net = slim.max_pool2d(net, [2, 2], 2)
      net = slim.conv2d(net, 64, [5, 5])
      net = slim.max_pool2d(net, [2, 2], 2)
      net = slim.flatten(net)
      net = slim.fully_connected(net, 1024)
      net = slim.dropout(net, 0.5, is_training=True)
      logits = slim.fully_connected(net, 10, activation_fn=None)
    labels_one_hot = slim.one_hot_encoding(labels, 10)
    # 定义交叉熵损失值
    loss = tf.losses.softmax_cross_entropy(
      logits=logits, onehot_labels=labels_one_hot,
      label_smoothing=0.0, weights=1.0)
    # 由于函数参数作用域定义了所有L2正则项系数为0，所以这里将不会获取到任何L2正则项
    regularization_losses = mox.get_collection(tf.GraphKeys.REGULARIZATION_LOSSES)

    if len(regularization_losses) > 0:
      regularization_loss = tf.add_n(regularization_losses)
      loss += regularization_loss
    # 定义评价指标
    accuracy_top_1 = tf.reduce_mean(tf.cast(tf.nn.in_top_k(logits, labels, 1), tf.float32))
    accuracy_top_5 = tf.reduce_mean(tf.cast(tf.nn.in_top_k(logits, labels, 5), tf.float32))
    # 必须返回mox.ModelSpec
    return mox.ModelSpec(loss=loss,
                         log_info={‘loss‘: loss, ‘top1‘: accuracy_top_1, ‘top5‘: accuracy_top_5})

  # 获取一个内置的Optimizer
  optimizer_fn = mox.get_optimizer_fn(‘sgd‘, learning_rate=0.01)

  # 启动训练
  mox.run(input_fn=input_fn,
          model_fn=model_fn,
          optimizer_fn=optimizer_fn,
          run_mode=mox.ModeKeys.TRAIN,
          batch_size=50,
          log_dir=flags.train_dir,
          max_number_of_steps=2000,
          log_every_n_steps=10,
          save_summary_steps=50,
          save_model_secs=60)

if __name__ == ‘__main__‘:
  train_my_model()