Ejemplos de realtime_augmented_data_gen en Python

Ejemplo n.º 1

Archivo: try_convnet_keras_modulated.py Proyecto: andrubor/keras-galaxies

def create_data_gen():
    augmented_data_gen = ra.realtime_augmented_data_gen(
        num_chunks=N_TRAIN / BATCH_SIZE * (EPOCHS + 1),
        chunk_size=BATCH_SIZE,
        augmentation_params=augmentation_params,
        ds_transforms=ds_transforms,
        target_sizes=input_sizes)

    post_augmented_data_gen = ra.post_augment_brightness_gen(
        augmented_data_gen, std=0.5)

    train_gen = load_data.buffered_gen_mp(post_augmented_data_gen,
                                          buffer_size=GEN_BUFFER_SIZE)

    input_gen = input_generator(train_gen)

    return input_gen

Ejemplo n.º 2

def dataLoader(data_indices, batch_size=100, shuffle=True):
    data_indices = np.array(data_indices)
    if shuffle:
        np.random.shuffle(data_indices)

    augmented_data_gen = ra.realtime_augmented_data_gen(
        data_indices=data_indices,
        batch_size=batch_size,
        augmentation_params=augmentation_params,
        ds_transforms=ds_transforms,
        target_sizes=input_sizes)

    post_augmented_data_gen = ra.post_augment_brightness_gen(
        augmented_data_gen, std=0.5)

    viewpoints_gen = create_viewpoints(post_augmented_data_gen,
                                       part_size=viewpoint_size)

    data_gen = load_data.buffered_gen_mp(viewpoints_gen,
                                         buffer_size=GEN_BUFFER_SIZE)

    return data_gen

Ejemplo n.º 3

Archivo: try_convnet_cc_multirotflip_3x69r45_maxout2048.py Proyecto: zhangyang5511/kaggle-galaxies

    ra.build_augmentation_transform(rotation=45)
]

num_input_representations = len(ds_transforms)

augmentation_params = {
    'zoom_range': (1.0 / 1.3, 1.3),
    'rotation_range': (0, 360),
    'shear_range': (0, 0),
    'translation_range': (-4, 4),
    'do_flip': True,
}

augmented_data_gen = ra.realtime_augmented_data_gen(
    num_chunks=NUM_CHUNKS,
    chunk_size=CHUNK_SIZE,
    augmentation_params=augmentation_params,
    ds_transforms=ds_transforms,
    target_sizes=input_sizes)

post_augmented_data_gen = ra.post_augment_brightness_gen(augmented_data_gen,
                                                         std=0.5)

train_gen = load_data.buffered_gen_mp(post_augmented_data_gen,
                                      buffer_size=GEN_BUFFER_SIZE)

y_train = np.load("data/solutions_train.npy")
train_ids = load_data.train_ids
test_ids = load_data.test_ids

# split training data into training + a small validation set
num_train = len(train_ids)

Ejemplo n.º 4

Archivo: try_convnet_cc_multirotflip_3x69r45_maxout2048_extradense_dup3.py Proyecto: ANB2/kaggle-galaxies

    ra.build_ds_transform(3.0, target_size=input_sizes[0]),
    ra.build_ds_transform(3.0, target_size=input_sizes[1]) + ra.build_augmentation_transform(rotation=45)
    ]

num_input_representations = len(ds_transforms)

augmentation_params = {
    'zoom_range': (1.0 / 1.3, 1.3),
    'rotation_range': (0, 360),
    'shear_range': (0, 0),
    'translation_range': (-4, 4),
    'do_flip': True,
}

augmented_data_gen = ra.realtime_augmented_data_gen(num_chunks=NUM_CHUNKS, chunk_size=CHUNK_SIZE,
                                                    augmentation_params=augmentation_params, ds_transforms=ds_transforms,
                                                    target_sizes=input_sizes)

post_augmented_data_gen = ra.post_augment_brightness_gen(augmented_data_gen, std=0.5)

train_gen = load_data.buffered_gen_mp(post_augmented_data_gen, buffer_size=GEN_BUFFER_SIZE)


y_train = np.load("data/solutions_train.npy")
train_ids = load_data.train_ids
test_ids = load_data.test_ids

# split training data into training + a small validation set
num_train = len(train_ids)
num_test = len(test_ids)

Ejemplo n.º 5

Archivo: try_convnet_cc_multirotflip_3x69r45_maxout2048_extradense_pysexgen1_dup2.py Proyecto: GregAtHeron/kaggle-galaxies

]

num_input_representations = len(ds_transforms)

augmentation_params = {
    "zoom_range": (1.0 / 1.3, 1.3),
    "rotation_range": (0, 360),
    "shear_range": (0, 0),
    "translation_range": (-4, 4),
    "do_flip": True,
}

augmented_data_gen = ra.realtime_augmented_data_gen(
    num_chunks=NUM_CHUNKS,
    chunk_size=CHUNK_SIZE,
    augmentation_params=augmentation_params,
    ds_transforms=ds_transforms,
    target_sizes=input_sizes,
    processor_class=ra.LoadAndProcessPysexGen1CenteringRescaling,
)

post_augmented_data_gen = ra.post_augment_brightness_gen(augmented_data_gen, std=0.5)

train_gen = load_data.buffered_gen_mp(post_augmented_data_gen, buffer_size=GEN_BUFFER_SIZE)


y_train = np.load("data/solutions_train.npy")
train_ids = load_data.train_ids
test_ids = load_data.test_ids

# split training data into training + a small validation set
num_train = len(train_ids)

Ejemplo n.º 6

Archivo: try_convnet_cc_multirotflip_3x69r45_maxout2048_extradense_pysexgen1_dup.py Proyecto: zhangyang5511/kaggle-galaxies

]

num_input_representations = len(ds_transforms)

augmentation_params = {
    'zoom_range': (1.0 / 1.3, 1.3),
    'rotation_range': (0, 360),
    'shear_range': (0, 0),
    'translation_range': (-4, 4),
    'do_flip': True,
}

augmented_data_gen = ra.realtime_augmented_data_gen(
    num_chunks=NUM_CHUNKS,
    chunk_size=CHUNK_SIZE,
    augmentation_params=augmentation_params,
    ds_transforms=ds_transforms,
    target_sizes=input_sizes,
    processor_class=ra.LoadAndProcessPysexGen1CenteringRescaling)

post_augmented_data_gen = ra.post_augment_brightness_gen(augmented_data_gen,
                                                         std=0.5)

train_gen = load_data.buffered_gen_mp(post_augmented_data_gen,
                                      buffer_size=GEN_BUFFER_SIZE)

y_train = np.load("data/solutions_train.npy")
train_ids = load_data.train_ids
test_ids = load_data.test_ids

# split training data into training + a small validation set

Ejemplo n.º 7

Archivo: keras_modulated_re-init_weight_test.py Proyecto: andrubor/keras-galaxies

    ra.build_augmentation_transform(rotation=45)
]

num_input_representations = len(ds_transforms)

augmentation_params = {
    'zoom_range': (1.0 / 1.3, 1.3),
    'rotation_range': (0, 360),
    'shear_range': (0, 0),
    'translation_range': (-4, 4),
    'do_flip': True,
}

augmented_data_gen = ra.realtime_augmented_data_gen(
    num_chunks=N_TRAIN / BATCH_SIZE * (EPOCHS + 1),
    chunk_size=BATCH_SIZE,
    augmentation_params=augmentation_params,
    ds_transforms=ds_transforms,
    target_sizes=input_sizes)

post_augmented_data_gen = ra.post_augment_brightness_gen(augmented_data_gen,
                                                         std=0.5)

train_gen = load_data.buffered_gen_mp(post_augmented_data_gen,
                                      buffer_size=GEN_BUFFER_SIZE)

input_gen = input_generator(train_gen)


def create_valid_gen():
    data_gen_valid = ra.realtime_fixed_augmented_data_gen(
        valid_indices,

Ejemplo n.º 8

Archivo: try_dense_only_keras_try_fullFit_maxout.py Proyecto: andrubor/keras-galaxies

    ra.build_augmentation_transform(rotation=45)
]

num_input_representations = len(ds_transforms)

augmentation_params = {
    'zoom_range': (1.0 / 1.3, 1.3),
    'rotation_range': (0, 360),
    'shear_range': (0, 0),
    'translation_range': (-4, 4),
    'do_flip': True,
}

augmented_data_gen = ra.realtime_augmented_data_gen(
    num_chunks=EPOCHS,
    chunk_size=N_TRAIN,
    augmentation_params=augmentation_params,
    ds_transforms=ds_transforms,
    target_sizes=input_sizes)

post_augmented_data_gen = ra.post_augment_brightness_gen(augmented_data_gen,
                                                         std=0.5)

train_gen = post_augmented_data_gen
#train_gen = load_data.buffered_gen_mp(post_augmented_data_gen, buffer_size=GEN_BUFFER_SIZE)    augmentation buffering will not work with the keras .fit
'''
def create_train_gen():
    """
    this generates the training data in order, for postprocessing. Do not use this for actual training.
    """
    data_gen_train = ra.realtime_fixed_augmented_data_gen(train_indices, 'train',
        ds_transforms=ds_transforms, chunk_size=N_TRAIN, target_sizes=input_sizes)