李宏毅机器学习2022 HW2
语音音素分类，是一个41分类问题。给定前k个和后k个frame，来预测中间的一个label。
直接运行代码训练，通过Simple Baseline。
简单添加网络层数，增加训练轮次，可以通过Medium Baseline。
通过添加Dropout，BatchNorm，调整使用的frame数量，以及隐层数目，可以通过Strong Baseline。
代码入下：
首先下载数据集
# Main link
!wget -O libriphone.zip "https://github.com/xraychen/shiny-robot/releases/download/v1.0/libriphone.zip"
# Backup Link 0
# !pip install --upgrade gdown
# !gdown --id '1o6Ag-G3qItSmYhTheX6DYiuyNzWyHyTc' --output libriphone.zip
# Backup link 1
# !pip install --upgrade gdown
# !gdown --id '1R1uQYi4QpX0tBfUWt2mbZcncdBsJkxeW' --output libriphone.zip
# Backup link 2
# !wget -O libriphone.zip "https://www.dropbox.com/s/wqww8c5dbrl2ka9/libriphone.zip?dl=1"
# Backup link 3
# !wget -O libriphone.zip "https://www.dropbox.com/s/p2ljbtb2bam13in/libriphone.zip?dl=1"
!unzip -q libriphone.zip
!ls libriphone
准备数据
import os
import random
import pandas as pd
import torch
from tqdm import tqdm
def load_feat(path):
feat = torch.load(path)
return feat
def shift(x, n):
if n < 0:
left = x[0].repeat(-n, 1)
right = x[:n]
elif n > 0:
right = x[-1].repeat(n, 1)
left = x[n:]
else:
return x
return torch.cat((left, right), dim=0)
def concat_feat(x, concat_n):
assert concat_n % 2 == 1 # n must be odd
if concat_n < 2:
return x
seq_len, feature_dim = x.size(0), x.size(1)
x = x.repeat(1, concat_n)
x = x.view(seq_len, concat_n, feature_dim).permute(1, 0, 2) # concat_n, seq_len, feature_dim
mid = (concat_n // 2)
for r_idx in range(1, mid+1):
x[mid + r_idx, :] = shift(x[mid + r_idx], r_idx)
x[mid - r_idx, :] = shift(x[mid - r_idx], -r_idx)
return x.permute(1, 0, 2).view(seq_len, concat_n * feature_dim)
def preprocess_data(split, feat_dir, phone_path, concat_nframes, train_ratio=0.8, train_val_seed=1337):
class_num = 41 # NOTE: pre-computed, should not need change
mode = 'train' if (split == 'train' or split == 'val') else 'test'
label_dict = {}
if mode != 'test':
phone_file = open(os.path.join(phone_path, f'{mode}_labels.txt')).readlines()
for line in phone_file:
line = line.strip('\n').split(' ')
label_dict[line[0]] = [int(p) for p in line[1:]]
if split == 'train' or split == 'val':
# split training and validation data
usage_list = open(os.path.join(phone_path, 'train_split.txt')).readlines()
random.seed(train_val_seed)
random.shuffle(usage_list)
percent = int(len(usage_list) * train_ratio)
usage_list = usage_list[:percent] if split == 'train' else usage_list[percent:]
elif split == 'test':
usage_list = open(os.path.join(phone_path, 'test_split.txt')).readlines()
else:
raise ValueError('Invalid \'split\' argument for dataset: PhoneDataset!')
usage_list = [line.strip('\n') for line in usage_list]
print('[Dataset] - # phone classes: ' + str(class_num) + ', number of utterances for ' + split + ': ' + str(len(usage_list)))
max_len = 3000000
X = torch.empty(max_len, 39 * concat_nframes)
if mode != 'test':
y = torch.empty(max_len, dtype=torch.long)
idx = 0
for i, fname in tqdm(enumerate(usage_list)):
feat = load_feat(os.path.join(feat_dir, mode, f'{fname}.pt'))
cur_len = len(feat)
feat = concat_feat(feat, concat_nframes)
if mode != 'test':
label = torch.LongTensor(label_dict[fname])
X[idx: idx + cur_len, :] = feat
if mode != 'test':
y[idx: idx + cur_len] = label
idx += cur_len
X = X[:idx, :]
if mode != 'test':
y = y[:idx]
print(f'[INFO] {split} set')
print(X.shape)
if mode != 'test':
print(y.shape)
return X, y
else:
return X
定义数据集
import torch
from torch.utils.data import Dataset
from torch.utils.data import DataLoader
class LibriDataset(Dataset):
def __init__(self, X, y=None):
self.data = X
if y is not None:
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)
定义模型
import torch
import torch.nn as nn
import torch.nn.functional as F
class BasicBlock(nn.Module): # 基础模块 一个线性层
def __init__(self, input_dim, output_dim):
super(BasicBlock, self).__init__()
self.block = nn.Sequential(
nn.Linear(input_dim, 512),
nn.ReLU(),
nn.BatchNorm1d(512),
nn.Dropout(0.25),
nn.Linear(512, 1024),
nn.ReLU(),
nn.BatchNorm1d(1024),
nn.Dropout(0.25)
)
def forward(self, x):
x = self.block(x)
return x
class Classifier(nn.Module):
def __init__(self, input_dim, output_dim=41, hidden_layers=1, hidden_dim=256):
super(Classifier, self).__init__()
self.fc = nn.Sequential(
BasicBlock(input_dim, hidden_dim),
*[BasicBlock(hidden_dim, hidden_dim) for _ in range(hidden_layers)],
nn.Linear(hidden_dim, output_dim)
) # block(in, 256) + block(256, 256) + Linear(256, 41)
def forward(self, x):
x = self.fc(x)
return x
设置超参数
# data prarameters
concat_nframes = 19 # the number of frames to concat with, n must be odd (total 2k+1 = n frames)
train_ratio = 0.8 # the ratio of data used for training, the rest will be used for validation
# training parameters
seed = 0 # random seed
batch_size = 512 # batch size
num_epoch = 50 # the number of training epoch
learning_rate = 0.0002 # learning rate
model_path = './model.ckpt' # the path where the checkpoint will be saved
# model parameters
input_dim = 39 * concat_nframes # the input dim of the model, you should not change the value
hidden_layers = 3 # the number of hidden layers
hidden_dim = 1024 # the hidden dim
准备数据集和模型
import gc
# preprocess data
train_X, train_y = preprocess_data(split='train', feat_dir='./libriphone/feat', phone_path='./libriphone', concat_nframes=concat_nframes, train_ratio=train_ratio)
val_X, val_y = preprocess_data(split='val', feat_dir='./libriphone/feat', phone_path='./libriphone', concat_nframes=concat_nframes, train_ratio=train_ratio)
# get dataset
train_set = LibriDataset(train_X, train_y)
val_set = LibriDataset(val_X, val_y)
# remove raw feature to save memory
del train_X, train_y, val_X, val_y
gc.collect()
# get dataloader
train_loader = DataLoader(train_set, batch_size=batch_size, shuffle=True)
val_loader = DataLoader(val_set, batch_size=batch_size, shuffle=False)
device = 'cuda:0' if torch.cuda.is_available() else 'cpu'
print(f'DEVICE: {device}')
import numpy as np
#fix 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
# fix random seed
same_seeds(seed)
# create model, define a loss function, and optimizer
model = Classifier(input_dim=input_dim, hidden_layers=hidden_layers, hidden_dim=hidden_dim).to(device)
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.AdamW(model.parameters(), lr=learning_rate)
训练
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, batch in enumerate(tqdm(train_loader)):
features, labels = batch
features = features.to(device)
labels = labels.to(device)
optimizer.zero_grad()
outputs = model(features)
loss = criterion(outputs, labels)
loss.backward()
optimizer.step()
_, train_pred = torch.max(outputs, 1) # get the index of the class with the highest probability
train_acc += (train_pred.detach() == labels.detach()).sum().item()
train_loss += loss.item()
# validation
if len(val_set) > 0:
model.eval() # set the model to evaluation mode
with torch.no_grad():
for i, batch in enumerate(tqdm(val_loader)):
features, labels = batch
features = features.to(device)
labels = labels.to(device)
outputs = model(features)
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 += 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')
del train_loader, val_loader
gc.collect()
测试
# load data
test_X = preprocess_data(split='test', feat_dir='./libriphone/feat', phone_path='./libriphone', concat_nframes=concat_nframes)
test_set = LibriDataset(test_X, None)
test_loader = DataLoader(test_set, batch_size=batch_size, shuffle=False)
# load model
model = Classifier(input_dim=input_dim, hidden_layers=hidden_layers, hidden_dim=hidden_dim).to(device)
model.load_state_dict(torch.load(model_path))
test_acc = 0.0
test_lengths = 0
pred = np.array([], dtype=np.int32)
model.eval()
with torch.no_grad():
for i, batch in enumerate(tqdm(test_loader)):
features = batch
features = features.to(device)
outputs = model(features)
_, test_pred = torch.max(outputs, 1) # get the index of the class with the highest probability
pred = np.concatenate((pred, test_pred.cpu().numpy()), axis=0)
with open('prediction.csv', 'w') as f:
f.write('Id,Class\n')
for i, y in enumerate(pred):
f.write('{},{}\n'.format(i, y))
准确率如图：
kaggle提交结果：
