参考文件链接
https://docs.python.org/3.5/library/filesys.html
https://docs.python.org/3.5/library/os.path.html
https://docs.python.org/3.5/library/urllib.request.html?highlight=url#urllib.request.pathname2url
https://docs.python.org/3.5/library/pathlib.html?highlight=iterdir#pathlib.Path.iterdir
import os
import urllib
from pathlib import Path
fpath=os.path.abspath(file)#模块中__file__代表本模块文件
print(‘filepath’,fpath)
filepath D:\Julie1\keras\pathteset.py
pathname =os.path.dirname(fpath)
print(‘path.dirname’,pathname)
path.dirname D:\Julie1\keras
print(‘path.cwd:’,Path.cwd())
print(‘os.getcwd():’,os.getcwd())
path.cwd: D:\Julie1\keras
os.getcwd(): D:\Julie1\keras
下载文件时
from tensorflow.python.keras.utils import get_file
使用了
https://tensorflow.google.cn/api_docs/python/tf/keras/utils
get_file(…): Downloads a file from a URL if it not already in the cache.
因此，必须使用地址格式转换
urllib.request.pathname2url(pathname)
url =urllib.request.pathname2url(pathname)
#pathname = urllib.url2pathname(url)
print('path url: ',url)
path url: ///D:/Julie1/keras
学习tensorflow的官方教程时，第一个例子用keras进行Fashion-MNIST分类。首先读取文件
https://tensorflow.google.cn/tutorials/keras/basic_classification
fashion_mnist = keras.datasets.fashion_mnist
(train_images, train_labels), (test_images, test_labels) = fashion_mnist.load_data()
如果下载成功，文件会存储在
C:\Users\username(windows用户名).keras\datasets
例如：
from tensorflow import keras
imdb = keras.datasets.imdb
(train_data, train_labels), (test_data, test_labels)=imdb.load_data(num_words=10000)
Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/imdb.npz
17465344/17464789 [==============================] - 7s 0us/step
但此处
Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/t10k-labels-idx1-ubyte.gz
下载失败，因此自己改编一下文件的读写
在https://github.com/zalandoresearch/fashion-mnist/tree/master/data中，下载数据文件
编写load模块load_data.py
from tensorflow.python.keras.utils import get_file
import gzip
import numpy as np
import os
import urllib
def load_data():
fpath=os.path.abspath(file)
pathname =os.path.dirname(fpath)
url =urllib.request.pathname2url(pathname)
base =“file:”+url+"/fashionMNIST_data/"
#“file:///D:/fashionMNIST_data/”
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))
with gzip.open(paths[0], ‘rb’) as lbpath:
y_train = np.frombuffer(lbpath.read(), np.uint8, offset=8)
with gzip.open(paths[1], ‘rb’) as imgpath:
x_train = np.frombuffer(
imgpath.read(), np.uint8, offset=16).reshape(len(y_train), 28, 28)
with gzip.open(paths[2], ‘rb’) as lbpath:
y_test = np.frombuffer(lbpath.read(), np.uint8, offset=8)
with gzip.open(paths[3], ‘rb’) as imgpath:
x_test = np.frombuffer(
imgpath.read(), np.uint8, offset=16).reshape(len(y_test), 28, 28)
return (x_train, y_train), (x_test, y_test)