使用IRIS数据集训练第一个深度神经网络

最新推荐文章于 2024-07-10 21:30:00 发布

TravisZeng

最新推荐文章于 2024-07-10 21:30:00 发布

阅读量1.2w

点赞数 3

分类专栏：机器学习 TensorFlow 文章标签：神经网络 python 数据

本文链接：https://blog.csdn.net/qq_34841823/article/details/78493377

版权

本文通过IRIS数据集详细介绍如何使用TensorFlow构建和训练一个深度神经网络（DNN）分类器。从数据加载、模型构建到训练和评估，逐步解析每个步骤，最终实现约97%的测试集准确率。

摘要由CSDN通过智能技术生成

本文主要以Iris数据集为例子讲解如何训练一个简单的Deep Neural Network。

环境配置

python 3.5.4

TensorFlow 1.4

完整源码

import os
import urllib

import numpy as np
import tensorflow as tf

# Data sets
IRIS_TRAINING = "iris_training.csv"
IRIS_TRAINING_URL = "http://download.tensorflow.org/data/iris_training.csv"

IRIS_TEST = "iris_test.csv"
IRIS_TEST_URL = "http://download.tensorflow.org/data/iris_test.csv"

def main():
    # If the training and test sets aren't stored locally, download them.
    if not os.path.exists(IRIS_TRAINING):
         raw = urllib.request.urlopen(IRIS_TRAINING_URL).read().decode()
    with open(IRIS_TRAINING, "w") as f:
        f.write(raw)
    if not os.path.exists(IRIS_TEST):
        raw = urllib.request.urlopen(IRIS_TEST_URL).read().decode()
    with open(IRIS_TEST, "w") as f:
        f.write(raw)
    # Load datasets.
    training_set = tf.contrib.learn.datasets.base.load_csv_with_header(
        filename=IRIS_TRAINING,
        target_dtype=np.int,
        features_dtype=np.float32)
    test_set = tf.contrib.learn.datasets.base.load_csv_with_header(
        filename=IRIS_TEST,
        target_dtype=np.int,
        features_dtype=np.float32)
    # Specify that all features have real-value data
    feature_columns = [tf.contrib.layers.real_valued_column("", dimension=4)]
    # Build 3 layer DNN with 10, 20, 10 units respectively.