【百度飞浆AI Studio】2、感性快速体验深度学习的线性归回预测房价

旧街凉风 提交于 2020-04-15 16:15:39

【推荐阅读】微服务还能火多久?>>>

百度学习原文地址: https://www.paddlepaddle.org.cn/documentation/docs/zh/1.5/beginners_guide/basics/fit_a_line/README.cn.html

import paddle
import paddle.fluid as fluid
import numpy
import math
import sys
from __future__ import print_function
BATCH_SIZE = 20

train_reader = paddle.batch(
    paddle.reader.shuffle(
        paddle.dataset.uci_housing.train(), buf_size=500),
        batch_size=BATCH_SIZE)

test_reader = paddle.batch(
    paddle.reader.shuffle(
        paddle.dataset.uci_housing.test(), buf_size=500),
        batch_size=BATCH_SIZE)
x = fluid.layers.data(name='x', shape=[13], dtype='float32') # 定义输入的形状和数据类型
y = fluid.layers.data(name='y', shape=[1], dtype='float32') # 定义输出的形状和数据类型
y_predict = fluid.layers.fc(input=x, size=1, act=None) # 连接输入和输出的全连接层

main_program = fluid.default_main_program() # 获取默认/全局主函数
startup_program = fluid.default_startup_program() # 获取默认/全局启动程序

cost = fluid.layers.square_error_cost(input=y_predict, label=y) # 利用标签数据和输出的预测数据估计方差
avg_loss = fluid.layers.mean(cost) # 对方差求均值,得到平均损失

sgd_optimizer = fluid.optimizer.SGD(learning_rate=0.001)
sgd_optimizer.minimize(avg_loss)

#克隆main_program得到test_program
#有些operator在训练和测试之间的操作是不同的,例如batch_norm,使用参数for_test来区分该程序是用来训练还是用来测试
#该api不会删除任何操作符,请在backward和optimization之前使用
test_program = main_program.clone(for_test=True)

use_cuda = False
place = fluid.CUDAPlace(0) if use_cuda else fluid.CPUPlace() # 指明executor的执行场所

###executor可以接受传入的program,并根据feed map(输入映射表)和fetch list(结果获取表)向program中添加数据输入算子和结果获取算子。使用close()关闭该executor,调用run(...)执行program。
exe = fluid.Executor(place)


num_epochs = 100

def train_test(executor, program, reader, feeder, fetch_list):
    accumulated = 1 * [0]
    count = 0
    for data_test in reader():
        outs = executor.run(program=program,
                            feed=feeder.feed(data_test),
                            fetch_list=fetch_list)
        accumulated = [x_c[0] + x_c[1][0] for x_c in zip(accumulated, outs)] # 累加测试过程中的损失值
        count += 1 # 累加测试集中的样本数量
    return [x_d / count for x_d in accumulated] # 计算平均损失
%matplotlib inline
params_dirname = "fit_a_line.inference.model"
feeder = fluid.DataFeeder(place=place, feed_list=[x, y])
exe.run(startup_program)
train_prompt = "train cost"
test_prompt = "test cost"
from paddle.utils.plot import Ploter
plot_prompt = Ploter(train_prompt, test_prompt)
step = 0

exe_test = fluid.Executor(place)   


for pass_id in range(num_epochs):
    for data_train in train_reader():
        avg_loss_value, = exe.run(main_program,
                                  feed=feeder.feed(data_train),
                                  fetch_list=[avg_loss])
        if step % 10 == 0: # 每10个批次记录并输出一下训练损失
            plot_prompt.append(train_prompt, step, avg_loss_value[0])
            plot_prompt.plot()
            print("%s, Step %d, Cost %f" %
                      (train_prompt, step, avg_loss_value[0]))
        if step % 100 == 0:  # 每100批次记录并输出一下测试损失
            test_metics = train_test(executor=exe_test,
                                     program=test_program,
                                     reader=test_reader,
                                     fetch_list=[avg_loss.name],
                                     feeder=feeder)
            plot_prompt.append(test_prompt, step, test_metics[0])
            plot_prompt.plot()
            print("%s, Step %d, Cost %f" %
                      (test_prompt, step, test_metics[0]))
            if test_metics[0] < 10.0: # 如果准确率达到要求,则停止训练
                break

        step += 1

        if math.isnan(float(avg_loss_value[0])):
            sys.exit("got NaN loss, training failed.")

        #保存训练参数到之前给定的路径中
        if params_dirname is not None:
            fluid.io.save_inference_model(params_dirname, ['x'], [y_predict], exe)
infer_exe = fluid.Executor(place)
inference_scope = fluid.core.Scope()


def save_result(points1, points2):
    import matplotlib
    matplotlib.use('Agg')
    import matplotlib.pyplot as plt
    x1 = [idx for idx in range(len(points1))]
    y1 = points1
    y2 = points2
    l1 = plt.plot(x1, y1, 'r--', label='predictions')
    l2 = plt.plot(x1, y2, 'g--', label='GT')
    plt.plot(x1, y1, 'ro-', x1, y2, 'g+-')
    plt.title('predictions VS GT')
    plt.legend()
    plt.savefig('./image/prediction_gt.png')
    
with fluid.scope_guard(inference_scope):
    [inference_program, feed_target_names,
     fetch_targets] = fluid.io.load_inference_model(params_dirname, infer_exe) # 载入预训练模型
    batch_size = 10

    infer_reader = paddle.batch(
        paddle.dataset.uci_housing.test(), batch_size=batch_size) # 准备测试集

    infer_data = next(infer_reader())
    infer_feat = numpy.array(
        [data[0] for data in infer_data]).astype("float32") # 提取测试集中的数据
    infer_label = numpy.array(
        [data[1] for data in infer_data]).astype("float32") # 提取测试集中的标签

    assert feed_target_names[0] == 'x'
    results = infer_exe.run(inference_program,
                            feed={feed_target_names[0]: numpy.array(infer_feat)},
                            fetch_list=fetch_targets) # 进行预测
    #打印预测结果和标签并可视化结果
    print("infer results: (House Price)")
    for idx, val in enumerate(results[0]):
        print("%d: %.2f" % (idx, val)) # 打印预测结果

    print("\nground truth:")
    for idx, val in enumerate(infer_label):
        print("%d: %.2f" % (idx, val)) # 打印标签值

    save_result(results[0], infer_label) # 保存图片
    
    
    

把代码复制进去

点击运行查看效果:

易学教程内所有资源均来自网络或用户发布的内容,如有违反法律规定的内容欢迎反馈
该文章没有解决你所遇到的问题?点击提问,说说你的问题,让更多的人一起探讨吧!