def __init__(self,
fmin=65,
fmax=2100,
unique_filters=True,
models=None,
**kwargs):
from ..models import CHROMA_DNN
from ..audio.signal import SignalProcessor, FramedSignalProcessor
from ..audio.stft import ShortTimeFourierTransformProcessor
from ..audio.spectrogram import LogarithmicFilteredSpectrogramProcessor
from madmom.ml.nn import NeuralNetworkEnsemble
# signal pre-processing
sig = SignalProcessor(num_channels=1, sample_rate=44100)
frames = FramedSignalProcessor(frame_size=8192, fps=10)
stft = ShortTimeFourierTransformProcessor() # caching FFT window
spec = LogarithmicFilteredSpectrogramProcessor(
num_bands=24, fmin=fmin, fmax=fmax, unique_filters=unique_filters)
# split the spectrogram into overlapping frames
spec_signal = SignalProcessor(sample_rate=10)
spec_frames = FramedSignalProcessor(frame_size=15, hop_size=1, fps=10)
# predict chroma bins with a DNN
nn = NeuralNetworkEnsemble.load(models or CHROMA_DNN, **kwargs)
# instantiate a SequentialProcessor
super(DeepChromaProcessor, self).__init__([
sig, frames, stft, spec, spec_signal, spec_frames, _dcp_flatten, nn
])
def Do():
nn = NeuralNetworkEnsemble.load(DOWNBEATS_BLSTM)
assert len(nn.processors) == 2
assert type(nn.processors[0]) == madmom.processors.ParallelProcessor
assert nn.processors[1] == madmom.ml.nn.average_predictions
# 8个相同的网络
pp = nn.processors[0]
# for p in pp.processors:
# print(p)
# 每个网络是个三层双向网络
network = pp.processors[0]
assert type(network) == madmom.ml.nn.NeuralNetwork
BiLayers = network.layers
print('biLayers size', len(BiLayers))
PrintLayerParam(BiLayers[0])
PrintLayerParam(BiLayers[1])
PrintLayerParam(BiLayers[2])
PrintFwdLayer(BiLayers[3])
print(type(BiLayers))
# print(BiLayers[3]) # a feedForwardLayer
# BiLayers.pop()
# return
layer = BiLayers[0]
assert type(layer) == madmom.ml.nn.layers.BidirectionalLayer
lstmLayer = layer.fwd_layer
assert type(lstmLayer) == madmom.ml.nn.layers.LSTMLayer
# Test1(lstmLayer.input_gate)
# Test2(lstmLayer)
# Test3(lstmLayer)
# Test4(layer)
Test5(network)
# GateParameter(lstmLayer.cell)
# GateParameter(lstmLayer.input_gate)
# GateParameter(lstmLayer.forget_gate)
# GateParameter(lstmLayer.output_gate)
print(type(lstmLayer.cell.activation_fn))
print(lstmLayer.cell.activation_fn.__name__)
# print(lstmLayer.cell.activation_fn == )
print(lstmLayer.input_gate.activation_fn)
print(lstmLayer.activation_fn)
def __init__(self, fmin=65, fmax=2100, unique_filters=True, models=None,
**kwargs):
from ..models import CHROMA_DNN
from ..audio.signal import SignalProcessor, FramedSignalProcessor
from ..audio.spectrogram import LogarithmicFilteredSpectrogramProcessor
from madmom.ml.nn import NeuralNetworkEnsemble
sig = SignalProcessor(num_channels=1, sample_rate=44100)
frames = FramedSignalProcessor(frame_size=8192, fps=10)
spec = LogarithmicFilteredSpectrogramProcessor(
num_bands=24, fmin=fmin, fmax=fmax, unique_filters=unique_filters)
spec_frames = FramedSignalProcessor(frame_size=15, hop_size=1)
nn = NeuralNetworkEnsemble.load(models or CHROMA_DNN, **kwargs)
super(DeepChromaProcessor, self).__init__([
sig, frames, spec, spec_frames, _dcp_flatten, nn
])
def __init__(self, fmin=65, fmax=2100, unique_filters=True, models=None,
**kwargs):
from ..models import CHROMA_DNN
from ..audio.signal import SignalProcessor, FramedSignalProcessor
from ..audio.stft import ShortTimeFourierTransformProcessor
from ..audio.spectrogram import LogarithmicFilteredSpectrogramProcessor
from madmom.ml.nn import NeuralNetworkEnsemble
# signal pre-processing
sig = SignalProcessor(num_channels=1, sample_rate=44100)
frames = FramedSignalProcessor(frame_size=8192, fps=10)
stft = ShortTimeFourierTransformProcessor() # caching FFT window
spec = LogarithmicFilteredSpectrogramProcessor(
num_bands=24, fmin=fmin, fmax=fmax, unique_filters=unique_filters)
# split the spectrogram into overlapping frames
spec_signal = SignalProcessor(sample_rate=10)
spec_frames = FramedSignalProcessor(frame_size=15, hop_size=1, fps=10)
# predict chroma bins with a DNN
nn = NeuralNetworkEnsemble.load(models or CHROMA_DNN, **kwargs)
# instantiate a SequentialProcessor
super(DeepChromaProcessor, self).__init__([
sig, frames, stft, spec, spec_signal, spec_frames, _dcp_flatten, nn
])
def build_cnn(madmom_processor_filename):
from madmom.audio.signal import SignalProcessor, FramedSignalProcessor
from madmom.audio.stft import ShortTimeFourierTransformProcessor
from madmom.audio.spectrogram import (FilteredSpectrogramProcessor,
LogarithmicSpectrogramProcessor)
from madmom.ml.nn import NeuralNetworkEnsemble
# define pre-processing chain
sig = SignalProcessor(num_channels=1, sample_rate=44100)
frames = FramedSignalProcessor(frame_size=4096, hop_size=441 * 2)
stft = ShortTimeFourierTransformProcessor() # caching FFT window
filt = FilteredSpectrogramProcessor(num_bands=24, fmin=30, fmax=10000)
# this is the money param! it was not whitelisted in 'canonicalize_audio_options'!
spec = LogarithmicSpectrogramProcessor(add=1)
# pre-processes everything sequentially
pre_processor = SequentialProcessor([
sig, frames, stft, filt, spec, _cnn_pad
])
# process the pre-processed signal with a NN
nn = NeuralNetworkEnsemble.load([madmom_processor_filename])
return madmom.processors.SequentialProcessor([pre_processor, nn])
def __init__(self, sr=44100, **kwargs):
from madmom.audio.signal import SignalProcessor, FramedSignalProcessor
from madmom.audio.stft import ShortTimeFourierTransformProcessor
from madmom.audio.spectrogram import (FilteredSpectrogramProcessor,
LogarithmicSpectrogramProcessor)
from madmom.ml.nn import NeuralNetworkEnsemble
sr_ratio = 44100 / sr
# define pre-processing chain
sig = SignalProcessor(num_channels=1, sample_rate=sr)
frames = FramedSignalProcessor(frame_size=4096 // sr_ratio,
fps=50 // sr_ratio)
stft = ShortTimeFourierTransformProcessor() # caching FFT window
filt = FilteredSpectrogramProcessor(num_bands=24, fmin=30, fmax=10000)
spec = LogarithmicSpectrogramProcessor(add=1)
# pre-processes everything sequentially
pre_processor = SequentialProcessor(
(sig, frames, stft, filt, spec, _cnn_pad))
# process the pre-processed signal with a NN
nn = NeuralNetworkEnsemble.load(VIENNA_MODEL_PATH)
# instantiate a SequentialProcessor
super().__init__((pre_processor, nn))
self.adsr = ADSRMaestro()