__author__ = 'Andres'
tf.reset_default_graph()
train_filename = '../test_w5120_g1024_h512_ex63501.tfrecords'
valid_filename = '../test_w5120_g1024_h512_ex63501.tfrecords'
signal_length = 5120
gap_length = 1024
batch_size = 256
fft_window_length = 512
fft_hop_size = 128
aTargetModel = EmptyTfGraph(shapeOfInput=(batch_size, signal_length), name="Target Model")
anStftForTheInpaintingSetting = PreAndPostProcessor(signalLength=signal_length,
gapLength=gap_length,
fftWindowLength=fft_window_length,
fftHopSize=fft_hop_size)
anStftForTheInpaintingSetting.addStftForGapTo(aTargetModel)
aTargetModel.divideComplexOutputIntoMagAndPhase() # (256, 11, 257, 2)
aModel = EmptyTfGraph(shapeOfInput=(batch_size, signal_length), name="context encoder")
anStftForTheInpaintingSetting.addStftForTheContextTo(aModel)
aModel.divideComplexOutputIntoMagAndPhase()
aModel.addReshape((batch_size, 16, 257, 4))
with tf.variable_scope("Encoder"):
filter_shapes = [(7, 89), (3, 17), (2, 6), (1, 5), (1, 3)]
tf.reset_default_graph()
if 'omenx' in socket.gethostname():
train_filename = '/store/nati/datasets/Nsynth/train_w5120_g1024_h512.tfrecords'
valid_filename = '/store/nati/datasets/Nsynth/valid_w5120_g1024_h512.tfrecords'
else:
train_filename = '/scratch/snx3000/nperraud/data/NSynth/train_w5120_g1024_h512.tfrecords'
valid_filename = '/scratch/snx3000/nperraud/data/NSynth/valid_w5120_g1024_h512.tfrecords'
window_size = 5120
gap_length = 1024
batch_size = 256
fft_frame_length = 512
fft_frame_step = 128
aTargetModel = EmptyTfGraph(shapeOfInput=(batch_size, window_size),
name="Target Model")
with tf.name_scope('Remove_unnecesary_sides_before_stft'):
signal = aTargetModel.output()
signal_without_unnecesary_sides = signal[:, 1664:3456]
aTargetModel.setOutputTo(signal_without_unnecesary_sides)
aTargetModel.addSTFT(frame_length=fft_frame_length, frame_step=fft_frame_step)
aTargetModel.divideComplexOutputIntoRealAndImaginaryParts(
) # (256, 11, 257, 2)
aModel = EmptyTfGraph(shapeOfInput=(batch_size, window_size),
name="context encoder")
with tf.name_scope('Remove_gap_before_stft'):
signal = aModel.output()
left_side = signal[:, :2048]
import tensorflow as tf
from network.emptyTFGraph import EmptyTfGraph
from utils.legacy.contextEncoder import ContextEncoderNetwork
__author__ = 'Andres'
tf.reset_default_graph()
train_filename = 'train_full_w5120_g1024_h512_ex18978619.tfrecords'
valid_filename = 'valid_full_w5120_g1024_h512_ex893971.tfrecords'
window_size = 5120
gap_length = 1024
batch_size = 256
aModel = EmptyTfGraph(shapeOfInput=(batch_size, window_size - gap_length), name="context encoder")
dataset = aModel.output()
first_half = dataset[:, :(window_size - gap_length) // 2]
second_half = dataset[:, (window_size - gap_length) // 2:]
stacked_halfs = tf.stack([first_half, second_half], axis=2)
aModel.setOutputTo(stacked_halfs)
with tf.variable_scope("Encoder"):
aModel.addReshape((batch_size, 1, (window_size - gap_length) // 2, 2))
filter_shapes = [(1, 129), (1, 65), (1, 33), (1, 17), (1, 17), (1, 17)]
input_channels = [2, 32, 128, 512, 256, 128]
output_channels = [*input_channels[1:], 64]
strides = [[1, 1, 2, 1]] * len(input_channels)
names = ['First_Conv', 'Second_Conv', 'Third_Conv', 'Fourth_Conv', 'Fifth_Conv', 'Six_Conv']
aModel.addSeveralConvLayers(filter_shapes=filter_shapes, input_channels=input_channels,
from tensorflow.contrib import slim
from network.emptyTFGraph import EmptyTfGraph
from utils.legacy.stftMagContextEncoder import StftTestContextEncoder
__author__ = 'Andres'
tf.reset_default_graph()
train_filename = '../test_w5120_g1024_h512_ex63501.tfrecords'
valid_filename = '../test_w5120_g1024_h512_ex63501.tfrecords'
window_size = 5120
gap_length = 1024
batch_size = 256
aModel = EmptyTfGraph(shapeOfInput=(batch_size, window_size),
name="context encoder")
signal = aModel.output()
with tf.name_scope('Energy_Spectogram'):
fft_frame_length = 512
fft_frame_step = 128
stft = tf.contrib.signal.stft(signals=signal,
frame_length=fft_frame_length,
frame_step=fft_frame_step)
sides_stft = tf.stack((stft[:, :15, :], stft[:, 15 + 7:, :]), axis=3)
mag_stft = tf.abs(sides_stft) # (256, 15, 257, 2)
aModel.setOutputTo(mag_stft)
from tensorflow.contrib.signal.python.ops import window_ops
from network.emptyTFGraph import EmptyTfGraph
from utils.legacy.contextEncoder import ContextEncoderNetwork
__author__ = 'Andres'
tf.reset_default_graph()
train_filename = '../test_w5120_g1024_h512_ex63501.tfrecords'
valid_filename = '../test_w5120_g1024_h512_ex63501.tfrecords'
window_size = 5120
gap_length = 1024
batch_size = 256
aModel = EmptyTfGraph(shapeOfInput=(batch_size, window_size - gap_length),
name="context encoder")
dataset = aModel.output()
signal_length = window_size - gap_length
first_half = dataset[:, :signal_length // 2]
second_half = dataset[:, signal_length // 2:]
stacked_halfs = tf.stack([first_half, second_half], axis=1)
with tf.name_scope('Energy_Spectogram'):
fft_frame_length = 512
fft_frame_step = 128
window_fn = functools.partial(window_ops.hann_window, periodic=True)
stft = tf.contrib.signal.stft(signals=stacked_halfs,
frame_length=fft_frame_length,
frame_step=fft_frame_step,
import tensorflow as tf
from network.emptyTFGraph import EmptyTfGraph
from utils.legacy.stftMagContextEncoder import StftTestContextEncoder
__author__ = 'Andres'
tf.reset_default_graph()
train_filename = 'test_full_w5120_g1024_h512_ex292266.tfrecords'
valid_filename = 'test_full_w5120_g1024_h512_ex292266.tfrecords'
window_size = 5120
gap_length = 1024
batch_size = 256
aModel = EmptyTfGraph(shapeOfInput=(batch_size, window_size - gap_length),
name="context encoder")
dataset = aModel.output()
signal_length = window_size - gap_length
first_half = dataset[:, :signal_length // 2]
second_half = dataset[:, signal_length // 2:]
stacked_halfs = tf.stack([first_half, second_half], axis=1)
with tf.name_scope('Energy_Spectogram'):
fft_frame_length = 512
fft_frame_step = 128
stft = tf.contrib.signal.stft(signals=stacked_halfs,
frame_length=fft_frame_length,
frame_step=fft_frame_step)
mag_stft = tf.abs(stft) # (256, 2, 13, 257)
mag_stft = tf.reshape(mag_stft, (batch_size, 13, 257, 2))