Phoneme Classification
分类训练
训练一个深度神经网络分类器来预测语音语料库TIMIT中每一帧的音素。
范例
数据准备
导入数据
import numpy as np
print('Loading data ...')
data_root='./timit_11/'
# 分别导入训练数据,训练标签,测试数据
train = np.load(data_root + 'train_11.npy')
train_label = np.load(data_root + 'train_label_11.npy')
test = np.load(data_root + 'test_11.npy')
print('Size of training data: {}'.format(train.shape))
print('Size of testing data: {}'.format(test.shape))
创建自定义数据集
import torch
from torch.utils.data import Dataset
# 定义数据集格式,data是数据,label是对应的标签,如果label为空,则表示需要预测
class TIMITDataset(Dataset):
def __init__(self, X, y=None):
self.data = torch.from_numpy(X).float()
if y is not None:
y = y.astype(np.int)
self.label = torch.LongTensor(y)
else:
self.label = None
def __getitem__(self, idx):
if self.label is not None:
return self.data[idx], self.label[idx]
else:
return self.data[idx]
def __len__(self):
return len(self.data)
分割数据
# 将训练数据二八分,一部分用于训练,一部分用于验证
VAL_RATIO = 0.2
percent = int(train.shape[0] * (1 - VAL_RATIO))
train_x, train_y, val_x, val_y = train[:percent], train_label[:percent], train[percent:], train_label[percent:]
print('Size of training set: {}'.format(train_x.shape))
print('Size of validation set: {}'.format(val_x.shape))
将数据导入DataLoader
# 将数据导入到DataLoader中,每一次batch的大小为64,训练阶段shuffle为True是为了打乱数据得到更好的训练效果,而验证阶段则不需要
BATCH_SIZE = 64
from torch.utils.data import DataLoader
train_set = TIMITDataset(train_x, train_y)
val_set = TIMITDataset(val_x, val_y)
train_loader = DataLoader(train_set, batch_size=BATCH_SIZE, shuffle=True) #only shuffle the training data
val_loader = DataLoader(val_set, batch_size=BATCH_SIZE, shuffle=False)
清空不必要的内存
# 由于数据集的大小非常大,所以最好清除不再使用的内存
import gc
del train, train_label, train_x, train_y, val_x, val_y
gc.collect()
创建自定义模型
# 定义训练模型
import torch
import torch.nn as nn
class Classifier(nn.Module):
def __init__(self):
super(Classifier, self).__init__()
self.layer1 = nn.Linear(429, 1024)
self.layer2 = nn.Linear(1024, 512)
self.layer3 = nn.Linear(512, 128)
self.out = nn.Linear(128, 39)
self.act_fn = nn.Sigmoid()
# 前向传播函数,每过一层就走一次激活函数
def forward(self, x):
x = self.layer1(x)
x = self.act_fn(x)
x = self.layer2(x)
x = self.act_fn(x)
x = self.layer3(x)
x = self.act_fn(x)
x = self.out(x)
return x
训练
检查device
#check device
def get_device():
return 'cuda' if torch.cuda.is_available() else 'cpu'
设置随机种子
# 设置同样的种子以确保实验的可重复性
# fix random seed
def same_seeds(seed):
torch.manual_seed(seed)
if torch.cuda.is_available():
torch.cuda.manual_seed(seed)
torch.cuda.manual_seed_all(seed)
np.random.seed(seed)
torch.backends.cudnn.benchmark = False
torch.backends.cudnn.deterministic = True
设置训练属性
# fix random seed for reproducibility
same_seeds(0)
# get device
device = get_device()
print(f'DEVICE: {device}')
# training parameters
num_epoch = 20 # number of training epoch
learning_rate = 0.0001 # learning rate
# ckpt检查点文件
# the path where checkpoint saved
model_path = './model.ckpt'
# 定义模型,损失函数以及优化器
# create model, define a loss function, and optimizer
model = Classifier().to(device)
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)
开始训练
# start training
best_acc = 0.0
for epoch in range(num_epoch):
train_acc = 0.0
train_loss = 0.0
val_acc = 0.0
val_loss = 0.0
# training
model.train() # set the model to training mode
for i, data in enumerate(train_loader):
inputs, labels = data
inputs, labels = inputs.to(device), labels.to(device)
optimizer.zero_grad()
outputs = model(inputs)
# 计算Loss函数
batch_loss = criterion(outputs, labels)
# 获取输出中概率最大的类别的索引,作为预测结果。
_, train_pred = torch.max(outputs, 1) # get the index of the class with the highest probability
# 计算损失并反向传播计算每个参数的梯度
batch_loss.backward()
# 梯度更新并更新优化器的参数
optimizer.step()
# 将预测结果和真实标签都从GPU移到CPU,然后逐个元素比较生成一个Bool数组
# 然后通过.sum()对Bool数组求和,得到当前批次中正确预测的数量
# .item()将张量转为Python的标量类型,以便进行累加
train_acc += (train_pred.cpu() == labels.cpu()).sum().item()
# .item()将张量转为Python的标量类型,以便进行累加
train_loss += batch_loss.item()
# validation
if len(val_set) > 0:
model.eval() # set the model to evaluation mode
with torch.no_grad():
for i, data in enumerate(val_loader):
inputs, labels = data
inputs, labels = inputs.to(device), labels.to(device)
outputs = model(inputs)
batch_loss = criterion(outputs, labels)
_, val_pred = torch.max(outputs, 1)
val_acc += (val_pred.cpu() == labels.cpu()).sum().item() # get the index of the class with the highest probability
val_loss += batch_loss.item()
print('[{:03d}/{:03d}] Train Acc: {:3.6f} Loss: {:3.6f} | Val Acc: {:3.6f} loss: {:3.6f}'.format(
epoch + 1, num_epoch, train_acc/len(train_set), train_loss/len(train_loader), val_acc/len(val_set), val_loss/len(val_loader)
))
# if the model improves, save a checkpoint at this epoch
if val_acc > best_acc:
best_acc = val_acc
torch.save(model.state_dict(), model_path)
print('saving model with acc {:.3f}'.format(best_acc/len(val_set)))
else:
print('[{:03d}/{:03d}] Train Acc: {:3.6f} Loss: {:3.6f}'.format(
epoch + 1, num_epoch, train_acc/len(train_set), train_loss/len(train_loader)
))
# if not validating, save the last epoch
if len(val_set) == 0:
torch.save(model.state_dict(), model_path)
print('saving model at last epoch')
测试
设置测试集
# create testing dataset
test_set = TIMITDataset(test, None)
test_loader = DataLoader(test_set, batch_size=BATCH_SIZE, shuffle=False)
# create model and load weights from checkpoint
model = Classifier().to(device)
model.load_state_dict(torch.load(model_path))
开始预测
predict = []
model.eval() # set the model to evaluation mode
with torch.no_grad():
for i, data in enumerate(test_loader):
inputs = data
inputs = inputs.to(device)
outputs = model(inputs)
_, test_pred = torch.max(outputs, 1) # get the index of the class with the highest probability
for y in test_pred.cpu().numpy():
predict.append(y)
写入CSV文件
with open('prediction.csv', 'w') as f:
f.write('Id,Class\n')
for i, y in enumerate(predict):
f.write('{},{}\n'.format(i, y))