def __init__(self,
device,
batch_size,
relative,
use_wildcard,
num_threads=3,
device_id=0,
num_gpus=1):
super(ReshapePipeline, self).__init__(batch_size,
num_threads,
device_id,
seed=7865,
exec_async=True,
exec_pipelined=True)
self.device = device
self.input = ops.readers.Caffe(path=caffe_db_folder,
shard_id=device_id,
num_shards=num_gpus)
self.decode = ops.ImageDecoder(device="cpu", output_type=types.RGB)
W = 320
H = 224
self.resize = ops.Resize(device="cpu", resize_x=W, resize_y=H)
WC = -1 if use_wildcard else W * 3
if relative:
rel_shape = (-1, 3) if use_wildcard else (1, 3)
self.reshape = ops.Reshape(device=device,
rel_shape=rel_shape,
layout="ab")
else:
self.reshape = ops.Reshape(device=device,
shape=(H, WC),
layout="ab")
def __init__(self,
batch_size,
num_threads,
device_id,
file_list,
sequence_length,
seg_num,
seg_length,
resize_shorter_scale,
crop_target_size,
is_training=False,
initial_prefetch_size=10,
num_shards=1,
shard_id=0,
dali_mean=0.,
dali_std=1.0):
super(VideoPipe, self).__init__(batch_size, num_threads, device_id)
self.input = ops.VideoReader(device="gpu",
file_list=file_list,
sequence_length=sequence_length,
seg_num=seg_num,
seg_length=seg_length,
is_training=is_training,
num_shards=num_shards,
shard_id=shard_id,
random_shuffle=is_training,
initial_fill=initial_prefetch_size)
# the sequece data read by ops.VideoReader is of shape [F, H, W, C]
# Because the ops.Resize does not support sequence data,
# it will be transposed into [H, W, F, C],
# then reshaped to [H, W, FC], and then resized like a 2-D image.
self.transpose = ops.Transpose(device="gpu", perm=[1, 2, 0, 3])
self.reshape = ops.Reshape(device="gpu",
rel_shape=[1.0, 1.0, -1],
layout='HWC')
self.resize = ops.Resize(device="gpu",
resize_shorter=resize_shorter_scale)
# crops and mirror are applied by ops.CropMirrorNormalize.
# Normalization will be implemented in paddle due to the difficulty of dimension broadcast,
# It is not sure whether dimension broadcast can be implemented correctly by dali, just take the Paddle Op instead.
self.pos_rng_x = ops.Uniform(range=(0.0, 1.0))
self.pos_rng_y = ops.Uniform(range=(0.0, 1.0))
self.mirror_generator = ops.Uniform(range=(0.0, 1.0))
self.cast_mirror = ops.Cast(dtype=types.DALIDataType.INT32)
self.crop_mirror_norm = ops.CropMirrorNormalize(
device="gpu",
crop=[crop_target_size, crop_target_size],
mean=dali_mean,
std=dali_std)
self.reshape_back = ops.Reshape(device="gpu",
shape=[
seg_num, seg_length * 3,
crop_target_size, crop_target_size
],
layout='FCHW')
self.cast_label = ops.Cast(device="gpu",
dtype=types.DALIDataType.INT64)
def define_graph(self):
device = self.device
return [
# no-op
ops.Reshape(device=device, shape=[1])(types.Constant(1.25)),
# flatten with reshape op
ops.Reshape(device=device)
(types.Constant(np.array([[1, 2], [3, 4]], dtype=np.uint16),
device=device),
shape=types.Constant([4]))
]
def __init__(self,
batch_size,
output_type,
input_type,
use_input,
num_threads=3,
device_id=0,
num_gpus=1):
super(CVPipeline, self).__init__(batch_size,
num_threads,
device_id,
seed=7865,
exec_async=False,
exec_pipelined=False)
self.use_input = use_input
self.name = "cv"
self.input = ops.CaffeReader(path=caffe_db_folder,
shard_id=device_id,
num_shards=num_gpus)
self.decode = ops.ImageDecoder(device="cpu", output_type=types.RGB)
if self.use_input:
self.transform_source = ops.ExternalSource(
lambda: gen_transforms(self.batch_size, 10))
self.warp = ops.PythonFunction(
function=CVWarp(output_type, input_type))
else:
self.warp = ops.PythonFunction(function=CVWarp(
output_type, input_type, [[0.1, 0.9, 10], [0.8, -0.2, -20]]))
self.set_layout = ops.Reshape(layout="HWC")
self.iter = 0
def __init__(self,
batch_size,
layout,
iterator,
pos_size_iter,
num_threads=1,
device_id=0,
num_gpus=1,
axes=None,
axis_names=None,
normalized_anchor=True,
normalized_shape=True):
super(SliceSynthDataPipelinePythonOp,
self).__init__(batch_size,
num_threads,
device_id,
seed=12345,
exec_async=False,
exec_pipelined=False)
self.device = "cpu"
self.layout = layout
self.iterator = iterator
self.pos_size_iter = pos_size_iter
self.inputs = ops.ExternalSource()
self.input_crop_pos = ops.ExternalSource()
self.input_crop_size = ops.ExternalSource()
function = partial(slice_func_helper, axes, axis_names, self.layout,
normalized_anchor, normalized_shape)
self.slice = ops.PythonFunction(function=function)
self.set_layout = ops.Reshape(layout=layout)
def __init__(self,
function,
batch_size,
iterator,
data_shape,
data_layout,
num_threads=1,
device_id=0):
super(Crop3dPythonOpPipeline, self).__init__(batch_size,
num_threads,
device_id,
exec_async=False,
exec_pipelined=False)
self.iterator = iterator
self.inputs = ops.ExternalSource()
self.data_shape = data_shape
self.data_layout = data_layout
def crop_func(image):
return function(image,
layout=self.data_layout,
shape=self.data_shape)
self.crop = ops.PythonFunction(function=crop_func)
self.set_layout = ops.Reshape(layout=data_layout)
def __init__(self,
batch_size,
pos_size_iter,
num_threads=1,
device_id=0,
num_gpus=1,
axes=None,
axis_names=None,
normalized_anchor=True,
normalized_shape=True):
super(SlicePythonOp, self).__init__(batch_size,
num_threads,
device_id,
seed=12345,
exec_async=False,
exec_pipelined=False)
self.device = "cpu"
self.layout = "HWC"
self.pos_size_iter = pos_size_iter
self.input = ops.CaffeReader(path=caffe_db_folder,
random_shuffle=False)
self.decode = ops.ImageDecoder(device='cpu', output_type=types.RGB)
self.input_crop_pos = ops.ExternalSource()
self.input_crop_size = ops.ExternalSource()
function = partial(slice_func_helper, axes, axis_names, self.layout,
normalized_anchor, normalized_shape)
self.slice = ops.PythonFunction(function=function)
self.set_layout = ops.Reshape(layout="HWC")
def __init__(self,
function,
batch_size,
data_layout,
iterator,
anchor,
shape,
axis_names,
axes,
fill_value,
erase_func=erase_func,
num_threads=1,
device_id=0):
super(ErasePythonPipeline, self).__init__(batch_size,
num_threads,
device_id,
exec_async=False,
exec_pipelined=False)
self.iterator = iterator
self.inputs = ops.ExternalSource()
self.data_layout = data_layout
function = partial(erase_func, anchor, shape, axis_names, axes,
data_layout, fill_value)
self.erase = ops.PythonFunction(function=function)
self.set_layout = ops.Reshape(layout=data_layout)
def __init__(self,
batch_size,
num_threads,
device,
device_id=0,
shard_id=0,
num_shards=1,
seed=0):
super(TestPipeline, self).__init__(batch_size, num_threads, device_id,
seed)
self.device = device
self.input = ops.COCOReader(file_root=file_root,
annotations_file=annotations_file,
shard_id=shard_id,
num_shards=num_shards,
ratio=False,
save_img_ids=True)
self.decode = ops.ImageDecoder(
device='mixed' if device is 'gpu' else 'cpu',
output_type=types.RGB)
self.resize = ops.Resize(device=device,
image_type=types.RGB,
resize_x=224,
resize_y=224,
interp_type=types.INTERP_LINEAR)
self.cmn = ops.CropMirrorNormalize(device=device,
output_dtype=types.FLOAT,
image_type=types.RGB,
mean=[128., 128., 128.],
std=[1., 1., 1.])
self.cast = ops.Cast(device=device, dtype=types.INT16)
self.reshape = ops.Reshape(device=device, shape=[1, 1])
def __init__(self,
function,
batch_size,
iterator,
data_shape,
data_layout,
num_threads=1,
device_id=0,
dictionary={},
default_value=0.0):
super(LookupTablePythonOpPipeline, self).__init__(batch_size,
num_threads,
device_id,
exec_async=False,
exec_pipelined=False)
self.iterator = iterator
self.inputs = ops.ExternalSource()
self.data_shape = data_shape
self.data_layout = data_layout
def lookup_table_func(input_data):
return function(input_data,
shape=data_shape,
dictionary=dictionary,
default_value=default_value)
self.lookup = ops.PythonFunction(function=lookup_table_func)
self.set_layout = ops.Reshape(layout=data_layout)
def __init__(self, batch_size, num_threads, device_id, _seed, image_dir):
super(CommonPipeline, self).__init__(batch_size, num_threads, device_id, seed=_seed, exec_async=False,
exec_pipelined=False)
self.input = ops.FileReader(file_root=image_dir)
self.decode = ops.ImageDecoder(device = 'cpu', output_type=types.RGB)
self.resize = ops.PythonFunction(function=resize)
self.set_layout = ops.Reshape(layout="HWC")
def __init__(self, batch_size, num_threads, device_id, data_dir, crop):
super(HybridTrainPipe, self).__init__(batch_size, num_threads,
device_id, data_dir, crop)
self.pad = ops.Paste(device="gpu",
fill_value=0,
ratio=1.1,
min_canvas_size=crop)
self.res = ops.RandomResizedCrop(device="gpu",
size=crop,
random_area=[0.9, 1.1],
random_aspect_ratio=1.33333)
self.cutmix = ops.PythonFunction(function=cut_mixe_image,
num_outputs=2,
device='gpu')
self.cmnp = ops.CropMirrorNormalize(
device="gpu",
output_dtype=types.FLOAT,
output_layout=types.NCHW,
image_type=types.RGB,
mean=[0.485 * 255, 0.456 * 255, 0.406 * 255],
std=[0.229 * 255, 0.224 * 255, 0.225 * 255])
self.coin = ops.CoinFlip(probability=0.5)
self.rotated = ops.Rotate(device="gpu", keep_size=True)
self.rotated_rng = ops.Uniform(range=(-5.0, 5.0))
self.brightness = ops.Brightness(device="gpu")
self.brightness_rng = ops.Uniform(range=(0.8, 1.2))
self.reshape = ops.Reshape(device="gpu", layout="HWC")
self.one_hot = ops.OneHot(num_classes=3,
dtype=types.INT32,
device="cpu")
self.jitter_rng = ops.CoinFlip(probability=0.3)
self.jittered = ops.Jitter(device="gpu")
def __init__(self, DATA_PATH, input_height, batch_size, num_threads,
device_id):
super(SimCLRTrainDataTransform, self).__init__(batch_size,
num_threads,
device_id,
seed=12)
self.COPIES = 3
self.input_height = input_height
self.input = ops.FileReader(file_root=DATA_PATH,
random_shuffle=True,
seed=12)
self.coin = ops.CoinFlip(probability=0.5)
self.uniform = ops.Uniform(range=[0.7, 1.3]) #-1 to 1
#read image (I think that has to be cpu, do a mixed operation to decode into gpu)
self.decode = ops.ImageDecoder(device='mixed', output_type=types.RGB)
self.crop = ops.RandomResizedCrop(size=self.input_height, device="gpu")
self.flip = ops.Flip(vertical=self.coin(),
horizontal=self.coin(),
device="gpu")
self.colorjit_gray = ops.ColorTwist(brightness=self.uniform(),
contrast=self.uniform(),
hue=self.uniform(),
saturation=self.uniform(),
device="gpu")
self.blur = ops.GaussianBlur(window_size=int(0.1 * self.input_height),
device="gpu")
self.swapaxes = ops.Reshape(
shape=[-1, self.input_height, self.input_height], device="gpu")
def __init__(self, device, batch_size, use_wildcard, num_threads=3, device_id=0, num_gpus=1):
super(ReshapeWithInput, self).__init__(batch_size, num_threads, device_id, seed=7865, exec_async=False, exec_pipelined=False)
self.device = device
self.input = ops.CaffeReader(path = caffe_db_folder, shard_id = device_id, num_shards = num_gpus)
self.decode = ops.ImageDecoder(device = "cpu", output_type = types.RGB)
fn = CollapseChannelsWildcard if use_wildcard else CollapseChannels
self.gen_shapes = ops.PythonFunction(function=fn)
self.reshape = ops.Reshape(device = device, layout = "ab");
def __init__(self, device, batch_size, relative, use_wildcard, num_threads=3, device_id=0, num_gpus=1):
super(ReshapeWithArgInput, self).__init__(batch_size, num_threads, device_id, seed=7865, exec_async=False, exec_pipelined=False)
self.device = device
self.input = ops.CaffeReader(path = caffe_db_folder, shard_id = device_id, num_shards = num_gpus)
self.resize = ops.Resize(device = "cpu");
self.decode = ops.ImageDecoder(device = "cpu", output_type = types.RGB)
self.gen_shapes = ops.PythonFunction(function=MakeTallFunc(relative, use_wildcard))
self.reshape = ops.Reshape(device = device);
self.relative = relative
def __init__(self, batch_size,function, num_threads=1, device_id=0, num_gpus=1 ):
super(WaterPythonPipeline, self).__init__(batch_size,
num_threads,
device_id,
exec_async=False,
exec_pipelined=False)
self.input = ops.CaffeReader(path = caffe_db_folder, shard_id = device_id, num_shards = num_gpus)
self.decode = ops.ImageDecoder(device = "cpu", output_type = types.RGB)
self.water = ops.PythonFunction(function=function)
self.set_layout = ops.Reshape(layout="HWC")
def __init__(self,
device_id,
n_devices,
file_root,
file_list,
batch_size,
sample_rate=16000,
window_size=.02,
window_stride=.01,
nfeatures=64,
nfft=512,
frame_splicing_factor=3,
silence_threshold=-80,
dither=.00001,
preemph_coeff=.97,
lowfreq=0.0,
highfreq=0.0,
num_threads=1):
super().__init__(batch_size, num_threads, device_id, seed=42)
self.dither = dither
self.frame_splicing_factor = frame_splicing_factor
self.read = ops.readers.File(file_root=file_root, file_list=file_list, device="cpu",
shard_id=device_id, num_shards=n_devices)
self.decode = ops.AudioDecoder(device="cpu", dtype=types.FLOAT, downmix=True)
self.normal_distribution = ops.random.Normal(device="cpu")
self.preemph = ops.PreemphasisFilter(preemph_coeff=preemph_coeff)
self.spectrogram = ops.Spectrogram(device="cpu", nfft=nfft,
window_length=window_size * sample_rate,
window_step=window_stride * sample_rate)
self.mel_fbank = ops.MelFilterBank(device="cpu", sample_rate=sample_rate, nfilter=nfeatures,
normalize=True, freq_low=lowfreq, freq_high=highfreq)
self.log_features = ops.ToDecibels(device="cpu", multiplier=np.log(10), reference=1.0,
cutoff_db=-80)
self.get_shape = ops.Shapes(device="cpu")
self.normalize = ops.Normalize(axes=[0], device="cpu")
self.splicing_transpose = ops.Transpose(device="cpu", perm=[1, 0])
self.splicing_reshape = ops.Reshape(device="cpu", rel_shape=[-1, frame_splicing_factor])
self.splicing_pad = ops.Pad(axes=[0], fill_value=0, align=frame_splicing_factor, shape=[1],
device="cpu")
self.get_nonsilent_region = ops.NonsilentRegion(device="cpu", cutoff_db=silence_threshold)
self.trim_silence = ops.Slice(device="cpu", axes=[0])
self.to_float = ops.Cast(dtype=types.FLOAT)
def __init__(self, function, batch_size, num_threads=1, device_id=0):
super(MultichannelPythonOpPipeline,
self).__init__(batch_size,
num_threads,
device_id,
exec_async=False,
exec_pipelined=False)
self.reader = ops.FileReader(file_root=multichannel_tiff_root)
self.decoder = ops.ImageDecoder(device='cpu',
output_type=types.ANY_DATA)
self.oper = ops.PythonFunction(function=function)
self.set_layout = ops.Reshape(layout="HWC")
def __init__(self, batch_size, layout, data_iterator):
super(SynthPythonFlipPipeline, self).__init__(batch_size, seed=1234, num_threads=4,
device_id=0, exec_async=False,
exec_pipelined=False)
self.iterator = data_iterator
self.layout = layout
self.input = ops.ExternalSource()
self.coin = ops.CoinFlip(seed=1234)
h_dim, v_dim, d_dim = find_dims(layout)
fun = lambda d, hor, ver, depth: numpy_flip(d, h_dim, v_dim, d_dim, hor, ver, depth)
self.python_flip = ops.PythonFunction(function=fun)
self.set_layout = ops.Reshape(layout=layout)
def __init__(self, device, batch_size, dims, axes, axis_names, batch=False,
out_type=None, in_type=None, shift=None, scale=None,
num_threads=3, device_id=0, num_gpus=1):
super(NormalizePipeline, self).__init__(
batch_size, num_threads, device_id, seed=7865,
exec_async=False, exec_pipelined=False)
common_args = {
"device": device,
"axes": axes,
"axis_names": axis_names,
"batch": batch,
"dtype": dali_type(out_type),
"shift": shift,
"scale": scale
}
self.in_type = in_type
self.out_type = out_type
self.device = device
self.input = ops.ExternalSource()
self.add_layout = None
if axis_names is not None:
layout = ''
for i in range(dims):
layout += chr(ord('a') + i)
self.add_layout = ops.Reshape(layout=layout)
self.batch = batch
self.dims = dims
self.has_axes = axes is not None or axis_names is not None
self.scale = scale
self.shift = shift
self.is_integral = out_type is not None and out_type is not np.float32
if axis_names is not None:
axes = []
for a in axis_names:
axes.append(ord(a) - ord('a'))
self.axes = axes
self.axis_names = axis_names
self.ddof = 2 if axes is not None and len(axes) > 0 else 0
self.eps = 0.25
self.mean = ops.PythonFunction(function=custom_mean(batch, axes), batch_processing=True)
self.stddev = ops.PythonFunction(function=custom_stddev(batch, axes), batch_processing=True)
self.normalize = ops.Normalize(**common_args, ddof=self.ddof)
self.scalar_mean = ops.Normalize(**common_args, mean=1, ddof=self.ddof, epsilon=self.eps)
self.scalar_stddev = ops.Normalize(**common_args, stddev=2, epsilon=self.eps)
self.scalar_params = ops.Normalize(**common_args, mean=1, stddev=2)
def __new__(cls, shape=None, **kwargs):
"""Create a ``Reshape`` operator.
Parameters
----------
shape : Sequence[int], optional
The optional output shape.
Returns
-------
nvidia.dali.ops.Reshape
The operator.
"""
return ops.Reshape(shape=shape,
device=context.get_device_type(),
**kwargs)
def __init__(self,
function,
batch_size,
layout,
iterator,
num_threads=1,
device_id=0):
super(CropSequencePythonOpPipeline,
self).__init__(batch_size,
num_threads,
device_id,
exec_async=False,
exec_pipelined=False)
self.layout = layout
self.iterator = iterator
self.inputs = ops.ExternalSource()
self.crop = ops.PythonFunction(function=function)
self.set_layout = ops.Reshape(layout=layout)
def __init__(self,
device,
batch_size,
num_threads=3,
device_id=0,
num_gpus=1):
super(ReshapePipeline, self).__init__(batch_size,
num_threads,
device_id,
seed=7865,
exec_async=True,
exec_pipelined=True)
self.device = device
self.input = ops.CaffeReader(path=caffe_db_folder,
shard_id=device_id,
num_shards=num_gpus)
self.decode = ops.ImageDecoder(device="cpu", output_type=types.RGB)
self.resize = ops.Resize(device="cpu", resize_x=224, resize_y=224)
self.reshape = ops.Reshape(device=device,
shape=(224, 224 * 3),
layout="ab")
def __init__(self,
batch_size,
output_type,
input_type,
fixed_size,
num_threads=3,
device_id=0,
num_gpus=1):
super(CVPipeline, self).__init__(batch_size,
num_threads,
device_id,
seed=7865,
exec_async=False,
exec_pipelined=False)
self.name = "cv"
self.input = ops.CaffeReader(path=caffe_db_folder,
shard_id=device_id,
num_shards=num_gpus)
self.decode = ops.ImageDecoder(device="cpu", output_type=types.RGB)
self.rotate = ops.PythonFunction(
function=CVRotate(output_type, input_type, fixed_size))
self.set_layout = ops.Reshape(layout="HWC")
self.uniform = ops.Uniform(range=(-180.0, 180.0), seed=42)
self.iter = 0
def __init__(self,
directory,
supervised: bool = True,
sequence_length: int = 11,
batch_size: int = 1,
num_workers: int = 1,
gpu_id: int = 0,
shuffle: bool = True,
crop_size: tuple = (256, 256),
resize: tuple = None,
brightness: float = 0.25,
contrast: float = 0.1,
mean: list = [0.5, 0.5, 0.5],
std: list = [0.5, 0.5, 0.5],
conv_mode='3d',
image_shape=(256, 256),
validate: bool = False):
super().__init__(batch_size,
num_workers,
gpu_id,
prefetch_queue_depth=1)
self.input = ops.VideoReader(additional_decode_surfaces=1,
channels=3,
device="gpu",
dtype=types.FLOAT,
enable_frame_num=False,
enable_timestamps=False,
file_root=directory,
image_type=types.RGB,
initial_fill=1,
lazy_init=False,
normalized=True,
num_shards=1,
pad_last_batch=False,
prefetch_queue_depth=1,
random_shuffle=shuffle,
sequence_length=sequence_length,
skip_vfr_check=True,
step=-1,
shard_id=0,
stick_to_shard=False,
stride=1)
self.uniform = ops.Uniform(range=(0.0, 1.0))
self.cmn = ops.CropMirrorNormalize(device='gpu',
crop=crop_size,
mean=mean,
std=std,
output_layout=types.NFHWC)
self.coin = ops.CoinFlip(probability=0.5)
self.brightness_val = ops.Uniform(
range=[1 - brightness, 1 + brightness])
self.contrast_val = ops.Uniform(range=[1 - contrast, 1 + contrast])
self.supervised = supervised
self.half = ops.Constant(fdata=0.5)
self.zero = ops.Constant(idata=0)
self.cast_to_long = ops.Cast(device='gpu', dtype=types.INT64)
if crop_size is not None:
H, W = crop_size
else:
# default
H, W = image_shape
# print('CONV MODE!!! {}'.format(conv_mode))
if conv_mode == '3d':
self.transpose = ops.Transpose(device="gpu", perm=[3, 0, 1, 2])
self.reshape = None
elif conv_mode == '2d':
self.transpose = ops.Transpose(device='gpu', perm=[0, 3, 1, 2])
self.reshape = ops.Reshape(device='gpu', shape=[-1, H, W])
self.validate = validate
def __init__(self,
device_id,
num_threads,
resample_range: list,
sample_rate=16000,
window_size=0.02,
window_stride=0.01,
window="hann",
normalize="per_feature",
n_fft=None,
preemph=0.97,
nfilt=64,
lowfreq=0,
highfreq=0,
log=True,
dither=constant,
pad_to=8,
max_duration=15.0,
frame_splicing=3,
batch_size=1,
total_samples=16,
audio_fp16_input=True,
device='gpu'):
super().__init__(batch_size, num_threads, device_id,
exec_async=True, exec_pipelined=True, seed =12, prefetch_queue_depth=1)
self._dali_init_log(locals())
if torch.distributed.is_initialized():
shard_id = torch.distributed.get_rank()
n_shards = torch.distributed.get_world_size()
else:
shard_id = 0
n_shards = 1
torch_windows = {
'hann': torch.hann_window,
'hamming': torch.hamming_window,
'blackman': torch.blackman_window,
'bartlett': torch.bartlett_window,
'none': None,
}
self.audio_fp16_input=audio_fp16_input
self.total_samples = total_samples
self.win_length = int(sample_rate * window_size) # frame size
self.hop_length = int(sample_rate * window_stride)
self.n_fft = n_fft or 2 ** math.ceil(math.log2(self.win_length))
self.normalize = normalize
self.log = log
self.dither = dither
self.frame_splicing = frame_splicing
self.nfilt = nfilt
self.preemph = preemph
self.pad_to = pad_to
self.highfreq = highfreq or sample_rate / 2
window_fn = torch_windows.get(window, None)
window_tensor = window_fn(self.win_length,
periodic=False) if window_fn else None
self.sample_rate = sample_rate
self.window_size = window_size
self.window_stride = window_stride
self.window = window_tensor
self.lowfreq = lowfreq
self.log = log
self.device = device
win_unpadded = self.window.tolist()
win_padded = win_unpadded + [0] * (self.n_fft - len(win_unpadded))
print("self.n_fft = {}".format(self.n_fft))
print("self.hop_length = {}".format(self.hop_length))
print("self.win_length = {}".format(self.win_length))
print("self.window_tensor = {}".format(self.window))
print("self.sample_rate = {}".format(self.sample_rate))
print("self.window_size = {}".format(self.window_size))
print("self.window_stride = {}".format(self.window_stride))
print("self.lowfreq = {}".format(self.lowfreq))
print("self.device = {}".format(self.device))
self.extsrc = ops.ExternalSource(name="INPUT_0", device=self.device, no_copy=True)
self.preemph = ops.PreemphasisFilter(preemph_coeff=preemph, device=self.device)
self.spectrogram = ops.Spectrogram(device=self.device,
nfft=self.n_fft,
center_windows=True,
window_fn=win_padded,
window_length=len(win_padded),
window_step=self.hop_length
)
self.mel_fbank = ops.MelFilterBank(device=self.device,
sample_rate=self.sample_rate,
nfilter=self.nfilt,
freq_high=self.highfreq,
freq_low=self.lowfreq,
normalize=normalize
)
self.log_features = ops.ToDecibels(device=self.device, multiplier=np.log(10), reference=1.0,
cutoff_db=math.log(1e-20))
self.get_shape = ops.Shapes(device=self.device)
self.normalize = ops.Normalize(axes=[0], device=self.device, ddof=1)
self.pad = ops.Pad(axes=[0,1], fill_value=0, shape=[502,240], device=self.device)
# Frame splicing
self.splicing_transpose = ops.Transpose(device=self.device, perm=[1, 0])
self.splicing_reshape = ops.Reshape(device=self.device, rel_shape=[-1, self.frame_splicing])
self.splicing_pad = ops.Pad(axes=[0], fill_value=0, align=self.frame_splicing, shape=[1], device=self.device)
self.to_float16 = ops.Cast(dtype=types.FLOAT16, device=self.device)
self.to_float32 = ops.Cast(dtype=types.FLOAT, device=self.device)
self.samples_done = 0
