机器学习3：基本图像分类

开始

1.数据集准备

同样，由于被墙的原因，需要手动下载教程中使用的Fashion mnist数据集

https://github.com/zalandoresearch/fashion-mnist/tree/master/data/fashion

把这个目录的4个压缩包下载下来

放入本地目录中，比如“~/tensorflow-data/fashion”

2.官网教程

基本分类：对服装图像进行分类  |  TensorFlow Core

3.修改fashion mansit数据集的加载方式

修改之前 fashion_mnist.py 加载fashion mansit数据集的方式如下（加载远程数据集）：

    base = "https://storage.googleapis.com/tensorflow/tf-keras-datasets/"
    files = [
        "train-labels-idx1-ubyte.gz",
        "train-images-idx3-ubyte.gz",
        "t10k-labels-idx1-ubyte.gz",
        "t10k-images-idx3-ubyte.gz",
    ]

    paths = []
    for fname in files:
        paths.append(get_file(fname, origin=base + fname, cache_subdir=dirname))

修改之后 fashion_mnist.py 加载fashion mansit数据集的方式如下（加载本地数据集）：

    # 修改为加载本地fashion数据集
    #base = "https://storage.googleapis.com/tensorflow/tf-keras-datasets/"
    base = "/Users/oulongping/tensorflow_data/fashion/"
    files = [
        "train-labels-idx1-ubyte.gz",
        "train-images-idx3-ubyte.gz",
        "t10k-labels-idx1-ubyte.gz",
        "t10k-images-idx3-ubyte.gz",
    ]

    paths = []
    for fname in files:
        #修改为加载本地fashion数据集
        #paths.append(get_file(fname, origin=base + fname, cache_subdir=dirname))
        paths.append(base + fname)