def add_feature_data(feature, dataset_df, data, metadata,
preprocessing_parameters):
set_default_value(feature['preprocessing'], 'in_memory',
preprocessing_parameters['in_memory'])
csv_path = None
if hasattr(dataset_df, 'csv'):
csv_path = os.path.dirname(os.path.abspath(dataset_df.csv))
num_images = len(dataset_df)
if num_images == 0:
raise ValueError('There are no images in the dataset provided.')
height = 0
width = 0
should_resize = False
if ('height' in preprocessing_parameters
or 'width' in preprocessing_parameters):
should_resize = True
try:
height = int(preprocessing_parameters[HEIGHT])
width = int(preprocessing_parameters[WIDTH])
except ValueError as e:
raise ValueError('Image height and width must be set and have '
'positive integer values: ' + str(e))
if height <= 0 or width <= 0:
raise ValueError(
'Image height and width must be positive integers')
# here if a width and height have not been specified
# we assume that all images have the same width and height
# thus the width and height of the first one are the same
# of all the other ones
if (csv_path is None
and not os.path.isabs(dataset_df[feature['name']][0])):
raise ValueError('Image file paths must be absolute')
first_image = imread(
get_abs_path(csv_path, dataset_df[feature['name']][0]))
first_img_height = first_image.shape[0]
first_img_width = first_image.shape[1]
first_img_num_channels = num_channels_in_image(first_image)
if height == 0 or width == 0:
# User hasn't specified height and width
height = first_img_height
width = first_img_width
# User specified num_channels in the model/feature definition
user_specified_num_channels = False
num_channels = first_img_num_channels
if NUM_CHANNELS in preprocessing_parameters:
user_specified_num_channels = True
num_channels = preprocessing_parameters[NUM_CHANNELS]
assert isinstance(
num_channels,
int), ValueError('Number of image channels needs to be an integer')
metadata[feature['name']]['preprocessing']['height'] = height
metadata[feature['name']]['preprocessing']['width'] = width
metadata[
feature['name']]['preprocessing']['num_channels'] = num_channels
if feature['preprocessing']['in_memory']:
data[feature['name']] = np.empty(
(num_images, height, width, num_channels), dtype=np.int8)
for i in range(len(dataset_df)):
filepath = get_abs_path(csv_path,
dataset_df[feature['name']][i])
img = ImageBaseFeature._read_image_and_resize(
filepath, width, height, should_resize, num_channels,
preprocessing_parameters['resize_method'],
user_specified_num_channels)
data[feature['name']][i, :, :, :] = img
else:
data_fp = os.path.splitext(dataset_df.csv)[0] + '.hdf5'
mode = 'w'
if os.path.isfile(data_fp):
mode = 'r+'
with h5py.File(data_fp, mode) as h5_file:
image_dataset = h5_file.create_dataset(
feature['name'] + '_data',
(num_images, height, width, num_channels),
dtype=np.uint8)
for i in range(len(dataset_df)):
filepath = get_abs_path(csv_path,
dataset_df[feature['name']][i])
img = ImageBaseFeature._read_image_and_resize(
filepath, width, height, should_resize, num_channels,
preprocessing_parameters['resize_method'],
user_specified_num_channels)
image_dataset[i, :height, :width, :] = img
data[feature['name']] = np.arange(num_images)
def add_feature_data(
feature,
dataset_df,
data,
metadata,
preprocessing_parameters
):
set_default_value(
feature['preprocessing'],
'in_memory',
preprocessing_parameters['in_memory']
)
if ('height' in preprocessing_parameters or
'width' in preprocessing_parameters):
should_resize = True
try:
provided_height = int(preprocessing_parameters[HEIGHT])
provided_width = int(preprocessing_parameters[WIDTH])
except ValueError as e:
raise ValueError(
'Image height and width must be set and have '
'positive integer values: ' + str(e)
)
if (provided_height <= 0 or provided_width <= 0):
raise ValueError(
'Image height and width must be positive integers'
)
else:
should_resize = False
csv_path = None
if hasattr(dataset_df, 'csv'):
csv_path = os.path.dirname(os.path.abspath(dataset_df.csv))
num_images = len(dataset_df)
height = 0
width = 0
num_channels = 1
if num_images > 0:
# here if a width and height have not been specified
# we assume that all images have the same wifth and im_height
# thus the width and height of the first one are the same
# of all the other ones
if (csv_path is None and
not os.path.isabs(dataset_df[feature['name']][0])):
raise ValueError(
'Image file paths must be absolute'
)
first_image = imread(
get_abs_path(
csv_path,
dataset_df[feature['name']][0]
)
)
height = first_image.shape[0]
width = first_image.shape[1]
if first_image.ndim == 2:
num_channels = 1
else:
num_channels = first_image.shape[2]
if should_resize:
height = provided_height
width = provided_width
metadata[feature['name']]['preprocessing']['height'] = height
metadata[feature['name']]['preprocessing']['width'] = width
metadata[feature['name']]['preprocessing'][
'num_channels'] = num_channels
if feature['preprocessing']['in_memory']:
data[feature['name']] = np.empty(
(num_images, height, width, num_channels),
dtype=np.int8
)
for i in range(len(dataset_df)):
img = imread(
get_abs_path(
csv_path,
dataset_df[feature['name']][i]
)
)
if img.ndim == 2:
img = img.reshape((img.shape[0], img.shape[1], 1))
if should_resize:
img = resize_image(
img,
(height, width),
preprocessing_parameters['resize_method']
)
# todo: temporary workaround for images with alpha channel, replace
if img.ndim == 3 and img.shape[2] != num_channels:
img = img[:, :, :num_channels]
data[feature['name']][i, :, :, :] = img
else:
data_fp = os.path.splitext(dataset_df.csv)[0] + '.hdf5'
mode = 'w'
if os.path.isfile(data_fp):
mode = 'r+'
with h5py.File(data_fp, mode) as h5_file:
image_dataset = h5_file.create_dataset(
feature['name'] + '_data',
(num_images, height, width, num_channels),
dtype=np.uint8
)
for i in range(len(dataset_df)):
img = imread(
get_abs_path(
csv_path,
dataset_df[feature['name']][i]
)
)
if img.ndim == 2:
img = img.reshape((img.shape[0], img.shape[1], 1))
if should_resize:
img = resize_image(
img,
(height, width),
preprocessing_parameters['resize_method'],
)
image_dataset[i, :height, :width, :] = img
data[feature['name']] = np.arange(num_images)
def test_get_abs_path():
assert get_abs_path('a', 'b.jpg') == 'a/b.jpg'
assert get_abs_path(None, 'b.jpg') == 'b.jpg'
def add_feature_data(feature, dataset_df, data, metadata,
preprocessing_parameters):
set_default_value(feature['preprocessing'], 'in_memory',
preprocessing_parameters['in_memory'])
if (not 'audio_feature' in preprocessing_parameters):
raise ValueError(
'audio_feature dictionary has to be present in preprocessing for audio.'
)
if (not 'type' in preprocessing_parameters['audio_feature']):
raise ValueError(
'type key has to be present in audio_feature dictionary for audio.'
)
csv_path = None
if hasattr(dataset_df, 'csv'):
csv_path = os.path.dirname(os.path.abspath(dataset_df.csv))
if (csv_path is None
and not os.path.isabs(dataset_df[feature['name']][0])):
raise ValueError('Audio file paths must be absolute')
num_audio_utterances = len(dataset_df)
padding_value = preprocessing_parameters['padding_value']
normalization_type = preprocessing_parameters['norm']
feature_name = feature['name']
feature_dim = metadata[feature_name]['feature_dim']
max_length = metadata[feature_name]['max_length']
audio_feature_dict = preprocessing_parameters['audio_feature']
audio_file_length_limit_in_s = preprocessing_parameters[
'audio_file_length_limit_in_s']
if num_audio_utterances == 0:
raise ValueError(
'There are no audio files in the dataset provided.')
audio_stats = {
'count': 0,
'mean': 0,
'var': 0,
'std': 0,
'max': 0,
'min': float('inf'),
'cropped': 0,
'max_length_in_s': audio_file_length_limit_in_s
}
if feature['preprocessing']['in_memory']:
data[feature['name']] = np.empty(
(num_audio_utterances, max_length, feature_dim),
dtype=np.float32)
for i in range(len(dataset_df)):
filepath = get_abs_path(csv_path,
dataset_df[feature['name']][i])
audio_feature = AudioBaseFeature._read_audio_and_transform_to_feature(
filepath, audio_feature_dict, feature_dim, max_length,
padding_value, normalization_type, audio_stats)
if (normalization_type == 'per_file'):
mean = np.mean(audio_feature, axis=0)
std = np.std(audio_feature, axis=0)
data[feature['name']][i, :, :] = np.divide(
(audio_feature - mean), std)
elif (normalization_type == 'global'):
raise ValueError('not implemented yet')
else:
data[feature['name']][i, :, :] = audio_feature
audio_stats['std'] = np.sqrt(audio_stats['var'] /
float(audio_stats['count']))
print_statistics = """
{} audio files loaded.
Statistics of audio file lengths:
- mean: {:.4f}
- std: {:.4f}
- max: {:.4f}
- min: {:.4f}
- cropped audio_files: {}
Max length was given as {}.
""".format(audio_stats['count'], audio_stats['mean'],
audio_stats['std'], audio_stats['max'],
audio_stats['min'], audio_stats['cropped'],
audio_stats['max_length_in_s'])
print(print_statistics)