neural_network.input_data¶
Functions for downloading and reading MNIST data (deprecated).
This module and all its submodules are deprecated.
Attributes¶
Classes¶
Container class for a _DataSet (deprecated). |
|
Functions¶
|
Convert class labels from scalars to one-hot vectors. |
Extract the images into a 4D uint8 numpy array [index, y, x, depth]. |
|
|
Extract the labels into a 1D uint8 numpy array [index]. |
|
Download the data from source url, unless it's already here. |
|
|
|
Module Contents¶
- class neural_network.input_data._DataSet(images, labels, fake_data=False, one_hot=False, dtype=dtypes.float32, reshape=True, seed=None)¶
Container class for a _DataSet (deprecated).
THIS CLASS IS DEPRECATED.
- next_batch(batch_size, fake_data=False, shuffle=True)¶
Return the next batch_size examples from this data set.
- _epochs_completed = 0¶
- _images¶
- _index_in_epoch = 0¶
- _labels¶
- _rng¶
- property epochs_completed¶
- property images¶
- property labels¶
- property num_examples¶
- class neural_network.input_data._Datasets¶
Bases:
NamedTuple
- neural_network.input_data._dense_to_one_hot(labels_dense, num_classes)¶
Convert class labels from scalars to one-hot vectors.
- neural_network.input_data._extract_images(f)¶
Extract the images into a 4D uint8 numpy array [index, y, x, depth].
- Args:
f: A file object that can be passed into a gzip reader.
- Returns:
data: A 4D uint8 numpy array [index, y, x, depth].
- Raises:
ValueError: If the bytestream does not start with 2051.
- neural_network.input_data._extract_labels(f, one_hot=False, num_classes=10)¶
Extract the labels into a 1D uint8 numpy array [index].
- Args:
f: A file object that can be passed into a gzip reader. one_hot: Does one hot encoding for the result. num_classes: Number of classes for the one hot encoding.
- Returns:
labels: a 1D uint8 numpy array.
- Raises:
ValueError: If the bystream doesn’t start with 2049.
- neural_network.input_data._maybe_download(filename, work_directory, source_url)¶
Download the data from source url, unless it’s already here.
- Args:
filename: string, name of the file in the directory. work_directory: string, path to working directory. source_url: url to download from if file doesn’t exist.
- Returns:
Path to resulting file.
- neural_network.input_data._read32(bytestream)¶
- neural_network.input_data.read_data_sets(train_dir, fake_data=False, one_hot=False, dtype=dtypes.float32, reshape=True, validation_size=5000, seed=None, source_url=DEFAULT_SOURCE_URL)¶
- neural_network.input_data.DEFAULT_SOURCE_URL = 'https://storage.googleapis.com/cvdf-datasets/mnist/'¶