データのダウンロード：
<![CDATA[>>> import tensorflow as tf
>>> TRAIN_DATA_URL = \
'https://storage.googleapis.com/download.tensorflow.org/example_images/flower_photos.tgz'
>>> data_root_orig = \
tf.keras.utils.get_file(origin=TRAIN_DATA_URL, fname='flower_photos', untar=True)
Downloading data from https://storage.googleapis.com/download.tensorflow.org/example_images/flower_photos.tgz
228818944/228813984 [==============================] - 261s 1us/step]]>
ダウンロードしたデータは，つぎのファイル配置になる：
<![CDATA[.keras ─ datasets ┬ flower_photos.tar.gz
└ flower_photos
├ daisy
├ dandelion
├ roses
├ sunflowers
├ tulips
└ LICENSE.txt]]>
このファイル配置は，つぎのコマンドによっても知られる：
<![CDATA[>>> import pathlib
>>> data_root = pathlib.Path(data_root_orig)
>>> print(data_root)
/home/[user name]/.keras/datasets/flower_photos
>>> for item in data_root.iterdir():
... print(item)
...
/home/[user name]/.keras/datasets/flower_photos/roses
/home/[user name]/.keras/datasets/flower_photos/daisy
/home/[user name]/.keras/datasets/flower_photos/dandelion
/home/[user name]/.keras/datasets/flower_photos/tulips
/home/[user name]/.keras/datasets/flower_photos/LICENSE.txt
/home/[user name]/.keras/datasets/flower_photos/sunflowers
>>> ]]>
|