Dataset之MNIST：自定義函數mnist.load_mnist根據網址下載mnist數據集(四個ubyte.gz格式數據集文件)

?

?

目錄

下載結果

運行代碼

---

?

?

下載結果

?

?

運行代碼

mnist.py文件

# coding: utf-8 try:import urllib.request except ImportError:raise ImportError('You should use Python 3.x') import os.path import gzip import pickle import os import numpy as npurl_base = 'http://yann.lecun.com/exdb/mnist/' key_file = {'train_img':'train-images-idx3-ubyte.gz','train_label':'train-labels-idx1-ubyte.gz','test_img':'t10k-images-idx3-ubyte.gz','test_label':'t10k-labels-idx1-ubyte.gz' }dataset_dir = os.path.dirname(os.path.abspath(__file__)) save_file = dataset_dir + "/mnist.pkl"train_num = 60000 test_num = 10000 img_dim = (1, 28, 28) img_size = 784def _download(file_name):file_path = dataset_dir + "/" + file_nameif os.path.exists(file_path):returnprint("Downloading " + file_name + " ... ")urllib.request.urlretrieve(url_base + file_name, file_path)print("Done")def download_mnist():for v in key_file.values():_download(v)def _load_label(file_name):file_path = dataset_dir + "/" + file_nameprint("Converting " + file_name + " to NumPy Array ...")with gzip.open(file_path, 'rb') as f:labels = np.frombuffer(f.read(), np.uint8, offset=8)print("Done")return labelsdef _load_img(file_name):file_path = dataset_dir + "/" + file_nameprint("Converting " + file_name + " to NumPy Array ...") with gzip.open(file_path, 'rb') as f:data = np.frombuffer(f.read(), np.uint8, offset=16)data = data.reshape(-1, img_size)print("Done")return datadef _convert_numpy():dataset = {}dataset['train_img'] = _load_img(key_file['train_img'])dataset['train_label'] = _load_label(key_file['train_label']) dataset['test_img'] = _load_img(key_file['test_img'])dataset['test_label'] = _load_label(key_file['test_label'])return datasetdef init_mnist():download_mnist()dataset = _convert_numpy()print("Creating pickle file ...")with open(save_file, 'wb') as f:pickle.dump(dataset, f, -1)print("Done!")def _change_one_hot_label(X):T = np.zeros((X.size, 10))for idx, row in enumerate(T):row[X[idx]] = 1return Tdef load_mnist(normalize=True, flatten=True, one_hot_label=False):"""讀入MNIST數據集Parameters----------normalize : 將圖像的像素值正規化為0.0~1.0one_hot_label : one_hot_label為True的情況下，標簽作為one-hot數組返回one-hot數組是指[0,0,1,0,0,0,0,0,0,0]這樣的數組flatten : 是否將圖像展開為一維數組Returns-------(訓練圖像, 訓練標簽), (測試圖像, 測試標簽)"""if not os.path.exists(save_file):init_mnist()with open(save_file, 'rb') as f:dataset = pickle.load(f)if normalize:for key in ('train_img', 'test_img'):dataset[key] = dataset[key].astype(np.float32)dataset[key] /= 255.0if one_hot_label:dataset['train_label'] = _change_one_hot_label(dataset['train_label'])dataset['test_label'] = _change_one_hot_label(dataset['test_label'])if not flatten:for key in ('train_img', 'test_img'):dataset[key] = dataset[key].reshape(-1, 1, 28, 28)return (dataset['train_img'], dataset['train_label']), (dataset['test_img'], dataset['test_label']) if __name__ == '__main__':init_mnist()

?

?

總結

以上是生活随笔為你收集整理的Dataset之MNIST：自定义函数mnist.load_mnist根据网址下载mnist数据集(四个ubyte.gz格式数据集文件)的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。