Python keras.datasets.cifar100.load_data() Examples

The following are 30 code examples of keras.datasets.cifar100.load_data(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module keras.datasets.cifar100 , or try the search function .
Example #1
Source File: utils.py    From ResNet-Tensorflow with MIT License 7 votes vote down vote up 
def load_cifar100() :
    (train_data, train_labels), (test_data, test_labels) = cifar100.load_data()
    # train_data = train_data / 255.0
    # test_data = test_data / 255.0
    train_data, test_data = normalize(train_data, test_data)

    train_labels = to_categorical(train_labels, 100)
    test_labels = to_categorical(test_labels, 100)

    seed = 777
    np.random.seed(seed)
    np.random.shuffle(train_data)
    np.random.seed(seed)
    np.random.shuffle(train_labels)


    return train_data, train_labels, test_data, test_labels
Example #2
Source File: test_datasets.py    From CAPTCHA-breaking with MIT License 6 votes vote down vote up 
def test_cifar(self):
        print('cifar10')
        (X_train, y_train), (X_test, y_test) = cifar10.load_data()
        print(X_train.shape)
        print(X_test.shape)
        print(y_train.shape)
        print(y_test.shape)

        print('cifar100 fine')
        (X_train, y_train), (X_test, y_test) = cifar100.load_data('fine')
        print(X_train.shape)
        print(X_test.shape)
        print(y_train.shape)
        print(y_test.shape)

        print('cifar100 coarse')
        (X_train, y_train), (X_test, y_test) = cifar100.load_data('coarse')
        print(X_train.shape)
        print(X_test.shape)
        print(y_train.shape)
        print(y_test.shape)
Example #3
Source File: test_datasets.py    From CAPTCHA-breaking with MIT License 6 votes vote down vote up 
def test_imdb(self):
        print('imdb')
        (X_train, y_train), (X_test, y_test) = imdb.load_data()
Example #4
Source File: utils.py    From ResNet-Tensorflow with MIT License 6 votes vote down vote up 
def load_mnist() :
    (train_data, train_labels), (test_data, test_labels) = mnist.load_data()
    train_data = np.expand_dims(train_data, axis=-1)
    test_data = np.expand_dims(test_data, axis=-1)

    train_data, test_data = normalize(train_data, test_data)

    train_labels = to_categorical(train_labels, 10)
    test_labels = to_categorical(test_labels, 10)

    seed = 777
    np.random.seed(seed)
    np.random.shuffle(train_data)
    np.random.seed(seed)
    np.random.shuffle(train_labels)


    return train_data, train_labels, test_data, test_labels
Example #5
Source File: convert.py    From MobileNetV2 with MIT License 6 votes vote down vote up 
def convert():
    train = 'train//'
    val = 'validation//'

    (X_train, y_train), (X_test, y_test) = cifar100.load_data(label_mode='fine')

    for i in range(len(X_train)):
        x = X_train[i]
        y = y_train[i]
        path = train + str(y[0])
        x = cv2.resize(x, (224, 224), interpolation=cv2.INTER_CUBIC)
        if not os.path.exists(path):
            os.makedirs(path)
        cv2.imwrite(path + '//' + str(i) + '.jpg', x)

    for i in range(len(X_test)):
        x = X_test[i]
        y = y_test[i]
        path = val + str(y[0])
        x = cv2.resize(x, (224, 224), interpolation=cv2.INTER_CUBIC)
        if not os.path.exists(path):
            os.makedirs(path)
        cv2.imwrite(path + '//' + str(i) + '.jpg', x)
Example #6
Source File: utils.py    From ResNet-Tensorflow with MIT License 6 votes vote down vote up 
def load_fashion() :
    (train_data, train_labels), (test_data, test_labels) = fashion_mnist.load_data()
    train_data = np.expand_dims(train_data, axis=-1)
    test_data = np.expand_dims(test_data, axis=-1)

    train_data, test_data = normalize(train_data, test_data)

    train_labels = to_categorical(train_labels, 10)
    test_labels = to_categorical(test_labels, 10)

    seed = 777
    np.random.seed(seed)
    np.random.shuffle(train_data)
    np.random.seed(seed)
    np.random.shuffle(train_labels)


    return train_data, train_labels, test_data, test_labels
Example #7
Source File: utils.py    From ResNet-Tensorflow with MIT License 6 votes vote down vote up 
def load_cifar10() :
    (train_data, train_labels), (test_data, test_labels) = cifar10.load_data()
    # train_data = train_data / 255.0
    # test_data = test_data / 255.0

    train_data, test_data = normalize(train_data, test_data)

    train_labels = to_categorical(train_labels, 10)
    test_labels = to_categorical(test_labels, 10)

    seed = 777
    np.random.seed(seed)
    np.random.shuffle(train_data)
    np.random.seed(seed)
    np.random.shuffle(train_labels)


    return train_data, train_labels, test_data, test_labels
Example #8
Source File: utils.py    From AnomalyDetectionTransformations with MIT License 5 votes vote down vote up 
def load_fashion_mnist():
    (X_train, y_train), (X_test, y_test) = fashion_mnist.load_data()
    X_train = normalize_minus1_1(cast_to_floatx(np.pad(X_train, ((0, 0), (2, 2), (2, 2)), 'constant')))
    X_train = np.expand_dims(X_train, axis=get_channels_axis())
    X_test = normalize_minus1_1(cast_to_floatx(np.pad(X_test, ((0, 0), (2, 2), (2, 2)), 'constant')))
    X_test = np.expand_dims(X_test, axis=get_channels_axis())
    return (X_train, y_train), (X_test, y_test)
Example #9
Source File: test_datasets.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def test_reuters():
    # only run data download tests 20% of the time
    # to speed up frequent testing
    random.seed(time.time())
    if random.random() > 0.8:
        (x_train, y_train), (x_test, y_test) = reuters.load_data()
        assert len(x_train) == len(y_train)
        assert len(x_test) == len(y_test)
        assert len(x_train) + len(x_test) == 11228
        (x_train, y_train), (x_test, y_test) = reuters.load_data(maxlen=10)
        assert len(x_train) == len(y_train)
        assert len(x_test) == len(y_test)
        word_index = reuters.get_word_index()
        assert isinstance(word_index, dict)
Example #10
Source File: load_datasets.py    From deepcaps with MIT License 5 votes vote down vote up 
def load_cifar10():
    from keras.datasets import cifar10
    (x_train, y_train), (x_test, y_test) = cifar10.load_data()

    x_train = x_train.reshape(-1, 32, 32, 3).astype('float32') / 255.
    x_test = x_test.reshape(-1, 32, 32, 3).astype('float32') / 255.
    # mean = np.mean(x_train, axis=(0,1,2))
    # x_train -= mean
    # x_test -= mean
    
    y_train = to_categorical(y_train.astype('float32'))
    y_test = to_categorical(y_test.astype('float32'))
    
#     return (x_train[0:100], y_train[0:100]), (x_test[0:100], y_test[0:100])
    return (x_train, y_train), (x_test, y_test)
Example #11
Source File: load_datasets.py    From deepcaps with MIT License 5 votes vote down vote up 
def load_cifar100():
    from keras.datasets import cifar100
    (x_train, y_train), (x_test, y_test) = cifar100.load_data()

    x_train = x_train.reshape(-1, 32, 32, 3).astype('float32') / 255.
    x_test = x_test.reshape(-1, 32, 32, 3).astype('float32') / 255.
    y_train = to_categorical(y_train.astype('float32'))
    y_test = to_categorical(y_test.astype('float32'))

    return (x_train, y_train), (x_test, y_test)
Example #12
Source File: load_datasets.py    From deepcaps with MIT License 5 votes vote down vote up 
def load_mnist():
    # the data, shuffled and split between train and test sets
    from keras.datasets import mnist
    (x_train, y_train), (x_test, y_test) = mnist.load_data()

    x_train = x_train.reshape(-1, 28, 28, 1).astype('float32') / 255.
    x_test = x_test.reshape(-1, 28, 28, 1).astype('float32') / 255.
    y_train = to_categorical(y_train.astype('float32'))
    y_test = to_categorical(y_test.astype('float32'))
    return (x_train, y_train), (x_test, y_test)
Example #13
Source File: load_datasets.py    From deepcaps with MIT License 5 votes vote down vote up 
def load_fmnist():
    # the data, shuffled and split between train and test sets
    from keras.datasets import fashion_mnist
    (x_train, y_train), (x_test, y_test) = fashion_mnist.load_data()

    x_train = x_train.reshape(-1, 28, 28, 1).astype('float32') / 255.
    x_test = x_test.reshape(-1, 28, 28, 1).astype('float32') / 255.
    y_train = to_categorical(y_train.astype('float32'))
    y_test = to_categorical(y_test.astype('float32'))
    return (x_train, y_train), (x_test, y_test)
Example #14
Source File: create_data.py    From active-learning with Apache License 2.0 5 votes vote down vote up 
def get_keras_data(dataname):
  """Get datasets using keras API and return as a Dataset object."""
  if dataname == 'cifar10_keras':
    train, test = cifar10.load_data()
  elif dataname == 'cifar100_coarse_keras':
    train, test = cifar100.load_data('coarse')
  elif dataname == 'cifar100_keras':
    train, test = cifar100.load_data()
  elif dataname == 'mnist_keras':
    train, test = mnist.load_data()
  else:
    raise NotImplementedError('dataset not supported')

  X = np.concatenate((train[0], test[0]))
  y = np.concatenate((train[1], test[1]))

  if dataname == 'mnist_keras':
    # Add extra dimension for channel
    num_rows = X.shape[1]
    num_cols = X.shape[2]
    X = X.reshape(X.shape[0], 1, num_rows, num_cols)
    if K.image_data_format() == 'channels_last':
      X = X.transpose(0, 2, 3, 1)

  y = y.flatten()
  data = Dataset(X, y)
  return data


# TODO(lishal): remove regular cifar10 dataset and only use dataset downloaded
# from keras to maintain image dims to create tensor for tf models
# Requires adding handling in run_experiment.py for handling of different
# training methods that require either 2d or tensor data.
Example #15
Source File: utils.py    From AnomalyDetectionTransformations with MIT License 5 votes vote down vote up 
def load_mnist():
    (X_train, y_train), (X_test, y_test) = mnist.load_data()
    X_train = normalize_minus1_1(cast_to_floatx(np.pad(X_train, ((0, 0), (2, 2), (2, 2)), 'constant')))
    X_train = np.expand_dims(X_train, axis=get_channels_axis())
    X_test = normalize_minus1_1(cast_to_floatx(np.pad(X_test, ((0, 0), (2, 2), (2, 2)), 'constant')))
    X_test = np.expand_dims(X_test, axis=get_channels_axis())
    return (X_train, y_train), (X_test, y_test)
Example #16
Source File: utils.py    From Matrix-Capsules-EM-Tensorflow with Apache License 2.0 5 votes vote down vote up 
def load_cifar100(is_training):
    # https://keras.io/datasets/
    # https://www.cs.toronto.edu/~kriz/cifar.html:
    # "Each image comes with a 'fine' label (the class to which it belongs)
    # and a 'coarse' label (the superclass to which it belongs)."
    assert(K.image_data_format() == 'channels_last')
    if is_training:
        return cifar100.load_data(label_mode='fine')[0]
    else:
        return cifar100.load_data(label_mode='fine')[1]
Example #17
Source File: test_datasets.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def test_mnist():
    # only run data download tests 20% of the time
    # to speed up frequent testing
    random.seed(time.time())
    if random.random() > 0.8:
        (x_train, y_train), (x_test, y_test) = mnist.load_data()
        assert len(x_train) == len(y_train) == 60000
        assert len(x_test) == len(y_test) == 10000
Example #18
Source File: utils.py    From AnomalyDetectionTransformations with MIT License 5 votes vote down vote up 
def load_cifar100(label_mode='coarse'):
    (X_train, y_train), (X_test, y_test) = cifar100.load_data(label_mode=label_mode)
    X_train = normalize_minus1_1(cast_to_floatx(X_train))
    X_test = normalize_minus1_1(cast_to_floatx(X_test))
    return (X_train, y_train), (X_test, y_test)
Example #19
Source File: test_datasets.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def test_reuters():
    # only run data download tests 20% of the time
    # to speed up frequent testing
    random.seed(time.time())
    if random.random() > 0.8:
        (x_train, y_train), (x_test, y_test) = reuters.load_data()
        assert len(x_train) == len(y_train)
        assert len(x_test) == len(y_test)
        assert len(x_train) + len(x_test) == 11228
        (x_train, y_train), (x_test, y_test) = reuters.load_data(maxlen=10)
        assert len(x_train) == len(y_train)
        assert len(x_test) == len(y_test)
        word_index = reuters.get_word_index()
        assert isinstance(word_index, dict)
Example #20
Source File: test_datasets.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def test_cifar():
    # only run data download tests 20% of the time
    # to speed up frequent testing
    random.seed(time.time())
    if random.random() > 0.8:
        (x_train, y_train), (x_test, y_test) = cifar10.load_data()
        assert len(x_train) == len(y_train) == 50000
        assert len(x_test) == len(y_test) == 10000
        (x_train, y_train), (x_test, y_test) = cifar100.load_data('fine')
        assert len(x_train) == len(y_train) == 50000
        assert len(x_test) == len(y_test) == 10000
        (x_train, y_train), (x_test, y_test) = cifar100.load_data('coarse')
        assert len(x_train) == len(y_train) == 50000
        assert len(x_test) == len(y_test) == 10000
Example #21
Source File: test_datasets.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def test_boston_housing():
    # only run data download tests 20% of the time
    # to speed up frequent testing
    random.seed(time.time())
    if random.random() > 0.8:
        (x_train, y_train), (x_test, y_test) = boston_housing.load_data()
        assert len(x_train) == len(y_train)
        assert len(x_test) == len(y_test)
Example #22
Source File: test_datasets.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def test_imdb():
    # only run data download tests 20% of the time
    # to speed up frequent testing
    random.seed(time.time())
    if random.random() > 0.8:
        (x_train, y_train), (x_test, y_test) = imdb.load_data()
        (x_train, y_train), (x_test, y_test) = imdb.load_data(maxlen=40)
        assert len(x_train) == len(y_train)
        assert len(x_test) == len(y_test)
        word_index = imdb.get_word_index()
        assert isinstance(word_index, dict)
Example #23
Source File: test_datasets.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def test_mnist():
    # only run data download tests 20% of the time
    # to speed up frequent testing
    random.seed(time.time())
    if random.random() > 0.8:
        (x_train, y_train), (x_test, y_test) = mnist.load_data()
        assert len(x_train) == len(y_train) == 60000
        assert len(x_test) == len(y_test) == 10000
Example #24
Source File: test_datasets.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def test_reuters():
    # only run data download tests 20% of the time
    # to speed up frequent testing
    random.seed(time.time())
    if random.random() > 0.8:
        (x_train, y_train), (x_test, y_test) = reuters.load_data()
        assert len(x_train) == len(y_train)
        assert len(x_test) == len(y_test)
        assert len(x_train) + len(x_test) == 11228
        (x_train, y_train), (x_test, y_test) = reuters.load_data(maxlen=10)
        assert len(x_train) == len(y_train)
        assert len(x_test) == len(y_test)
        word_index = reuters.get_word_index()
        assert isinstance(word_index, dict)
Example #25
Source File: test_datasets.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def test_cifar():
    # only run data download tests 20% of the time
    # to speed up frequent testing
    random.seed(time.time())
    if random.random() > 0.8:
        (x_train, y_train), (x_test, y_test) = cifar10.load_data()
        assert len(x_train) == len(y_train) == 50000
        assert len(x_test) == len(y_test) == 10000
        (x_train, y_train), (x_test, y_test) = cifar100.load_data('fine')
        assert len(x_train) == len(y_train) == 50000
        assert len(x_test) == len(y_test) == 10000
        (x_train, y_train), (x_test, y_test) = cifar100.load_data('coarse')
        assert len(x_train) == len(y_train) == 50000
        assert len(x_test) == len(y_test) == 10000
Example #26
Source File: test_datasets.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def test_boston_housing():
    # only run data download tests 20% of the time
    # to speed up frequent testing
    random.seed(time.time())
    if random.random() > 0.8:
        (x_train, y_train), (x_test, y_test) = boston_housing.load_data()
        assert len(x_train) == len(y_train)
        assert len(x_test) == len(y_test)
Example #27
Source File: test_datasets.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def test_imdb():
    # only run data download tests 20% of the time
    # to speed up frequent testing
    random.seed(time.time())
    if random.random() > 0.8:
        (x_train, y_train), (x_test, y_test) = imdb.load_data()
        (x_train, y_train), (x_test, y_test) = imdb.load_data(maxlen=40)
        assert len(x_train) == len(y_train)
        assert len(x_test) == len(y_test)
        word_index = imdb.get_word_index()
        assert isinstance(word_index, dict)
Example #28
Source File: test_datasets.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def test_mnist():
    # only run data download tests 20% of the time
    # to speed up frequent testing
    random.seed(time.time())
    if random.random() > 0.8:
        (x_train, y_train), (x_test, y_test) = mnist.load_data()
        assert len(x_train) == len(y_train) == 60000
        assert len(x_test) == len(y_test) == 10000
Example #29
Source File: load_cifar.py    From Model-Compression-Keras with MIT License 5 votes vote down vote up 
def load_data(data='c10'):
    if data == 'c10':
        print('Loading CIFAR-10 dataset')
        nb_classes = 10
        (x_train, y_train), (x_test, y_test) = cifar10.load_data()
        x_train = x_train.astype(np.float32)
        x_test = x_test.astype(np.float32)
        mean = np.array([125.3, 123.0, 113.9])
        std = np.array([63.0, 62.1, 66.7])
        x_train -= mean
        x_train /= std
        x_test -= mean
        x_test /= std
    else:
        print('Loading CIFAR-100 dataset')
        nb_classes = 100
        (x_train, y_train), (x_test, y_test) = cifar100.load_data()
        x_train = x_train.astype(np.float32)
        x_test = x_test.astype(np.float32)
        mean = np.array([129.3, 124.1, 112.4])
        std = np.array([68.2, 65.4, 70.4])
        x_train -= mean
        x_train /= std
        x_test -= mean
        x_test /= std

    return x_train, y_train, x_test, y_test, nb_classes
Example #30
Source File: test_datasets.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def test_boston_housing():
    # only run data download tests 20% of the time
    # to speed up frequent testing
    random.seed(time.time())
    if random.random() > 0.8:
        (x_train, y_train), (x_test, y_test) = boston_housing.load_data()
        assert len(x_train) == len(y_train)
        assert len(x_test) == len(y_test)