自己写的读取声音文件识别序号的神经网络代码,读取wav文件没有问题,fc1层的时候出错,我是学生,希望大佬帮忙指正。
str.encode('utf-8')
import numpy
import scipy.io.wavfile
from scipy.fftpack import dct
import torch
import torch.nn as nn
import torch.optim as optim
def Read_wav(wav_name):
sample_rate, signal = scipy.io.wavfile.read(wav_name) # File assumed to be in the same directory
signal = signal[0:int(3.5 * sample_rate)] # Keep the first 3.5 seconds
pre_emphasis = 0.97
emphasized_signal = numpy.append(signal[0], signal[1:] - pre_emphasis * signal[:-1])
frame_size = 0.025;frame_stride = 0.01
frame_length, frame_step = frame_size * sample_rate, frame_stride * sample_rate # Convert from seconds to samples
signal_length = len(emphasized_signal)
frame_length = int(round(frame_length))
frame_step = int(round(frame_step))
num_frames = int(
numpy.ceil(float(numpy.abs(signal_length - frame_length)) / frame_step)) # Make sure that we have at least 1 frame
pad_signal_length = num_frames * frame_step + frame_length
z = numpy.zeros((pad_signal_length - signal_length))
pad_signal = numpy.append(emphasized_signal, z) # Pad Signal to make sure that all frames have equal number of samples without truncating any samples from the original signal
indices = numpy.tile(numpy.arange(0, frame_length), (num_frames, 1)) + numpy.tile(
numpy.arange(0, num_frames * frame_step, frame_step), (frame_length, 1)).T
frames = pad_signal[indices.astype(numpy.int32, copy=False)]
frames *= numpy.hamming(frame_length)
# frames *= 0.54 - 0.46 * numpy.cos((2 * numpy.pi * n) / (frame_length - 1)) # Explicit Implementation **
NFFT = 512# or 216
mag_frames = numpy.absolute(numpy.fft.rfft(frames, NFFT)) # Magnitude of the FFT
pow_frames = ((1.0 / NFFT) * ((mag_frames) ** 2)) # Power Spectrum
nfilt = 40
low_freq_mel = 0
high_freq_mel = (2595 * numpy.log10(1 + (sample_rate / 2) / 700)) # Convert Hz to Mel
mel_points = numpy.linspace(low_freq_mel, high_freq_mel, nfilt + 2) # Equally spaced in Mel scale
hz_points = (700 * (10 ** (mel_points / 2595) - 1)) # Convert Mel to Hz
bin = numpy.floor((NFFT + 1) * hz_points / sample_rate)
fbank = numpy.zeros((nfilt, int(numpy.floor(NFFT / 2 + 1))))
for m in range(1, nfilt + 1):
f_m_minus = int(bin[m - 1]) # left
f_m = int(bin[m]) # center
f_m_plus = int(bin[m + 1]) # right
for k in range(f_m_minus, f_m):
fbank[m - 1, k] = (k - bin[m - 1]) / (bin[m] - bin[m - 1])
for k in range(f_m, f_m_plus):
fbank[m - 1, k] = (bin[m + 1] - k) / (bin[m + 1] - bin[m])
filter_banks = numpy.dot(pow_frames, fbank.T)
filter_banks = numpy.where(filter_banks == 0, numpy.finfo(float).eps, filter_banks) # Numerical Stability
filter_banks = 20 * numpy.log10(filter_banks)
num_ceps = 12
mfcc = dct(filter_banks, type=2, axis=1, norm='ortho')[:, 1 : (num_ceps + 1)] # Keep 2-13
#(nframes, ncoeff) = mfcc.shape
#n = numpy.arange(ncoeff)
#lift = 1 + (cep_lifter / 2) * numpy.sin(numpy.pi * n / cep_lifter)
#mfcc *= lift #*
filter_banks -= (numpy.mean(filter_banks, axis=0) + 1e-8)
mfcc -= (numpy.mean(mfcc, axis=0) + 1e-8)
#return filter_banks.shape
mfcc = mfcc.reshape(-1,1)[:2484]
return mfcc.reshape(1,-1)#[1,2484]
count_number = 3
# 定义网络结构
class Net(nn.Module):
def __init__(self,count_number):
super(Net, self).__init__()
self.fc1 = nn.Linear(2484,1)#3
self.softmax = nn.Softmax(dim=1)
def forward(self,x):
x = torch.FloatTensor(x)
x = x.view(-1,1)
x = self.fc1(x)
x = self.softmax(x)
return x
LR = 0.0003
# 定义模型
model = Net(count_number)
# 定义代价函数
entropy_loss = nn.CrossEntropyLoss()
#定义优化器
optimizer = optim.Adam(model.parameters(), LR)
def train(t,labels):
# 获得数据和对应的标签
inputs = torch.FloatTensor(Read_wav(t))#[1,2484]
#input('实际说话人:{0:Hu,1:Cao,2:Peng }')
target = torch.ones(1)
print(target)
out = model(inputs).reshape(3)#[1,3]
print(out)
# 计算损失值
loss = entropy_loss(out, target)
# 梯度清0
optimizer.zero_grad()
# 计算梯度
loss.backward()
# 修改权值
optimizer.step()
for i in range(1,201):
train('0 (%s).wav' %(i) , 0)