CIFAR10与ResNet实战 + RNN

具体见代码

CIFAR参数：

pytorch torchvision.transforms.Normalize()中的mean和std参数---解惑_xys430381_1的专栏-CSDN博客_torchvision.transforms.normalize

时间序列表示方法

one_hot占用内存高，语义相近

解决办法：一次送多个(batch)句子进入

RNN原理

[3，20] => 3个句子，20个memory

# nn.RNN(input,hidden,num)
rnn = nn.RNN(100,10)
rnn._parameters.keys()
>>> odict_keys(['weight_ih_l0', 'weight_hh_l0', 'bias_ih_l0', 'bias_hh_l0'])
rnn.weight_hh_l0.shape
>>> torch.Size([10, 10])

rnn = nn.RNN(100,20,4)
x = torch.randn(10,3,100)
out,h = rnn(x)

cell1 = nn.RNNCell(100, 20)
h1 = torch.zeros(3, 20)
for xt in x:
    h1 = cell1(xt, h1)
print(h1.shape)

cell1 = nn.RNNCell(100, 30)
cell2 = nn.RNNCell(30, 20)
h1 = torch.zeros(3, 30)
h2 = torch.zeros(3, 20)
for xt in x:
    h1 = cell1(xt, h1)
    h2 = cell2(h1, h2)
print(h2.shape)

时间序列预测实战

略

梯度爆炸 —— 梯度限制在10以内

loss = criteon(output,y)
model.zero_grad()
loss.backward()
for p in model.parameters():
    torch.nn.utils.clip_grad_norm(p,10)
optimizer.step()

梯度离散 —— LSTM

三道门 —— 输入门、输出门、遗忘门

out,(ht,ct) = lstm(x,[ht_1,ct_1])

情感分类实战

CoLAB —— 谷歌显卡！！

import torch
from torch import nn, optim
from torchtext import data, datasets

print('GPU:', torch.cuda.is_available())

torch.manual_seed(123)

TEXT = data.Field(tokenize='spacy')
LABEL = data.LabelField(dtype=torch.float)
train_data, test_data = datasets.IMDB.splits(TEXT, LABEL)

print('len of train data:', len(train_data))
print('len of test data:', len(test_data))

print(train_data.examples[15].text)
print(train_data.examples[15].label)

# word2vec, glove
TEXT.build_vocab(train_data, max_size=10000, vectors='glove.6B.100d')
LABEL.build_vocab(train_data)


batchsz = 30
device = torch.device('cuda')
train_iterator, test_iterator = data.BucketIterator.splits(
    (train_data, test_data),
    batch_size = batchsz,
    device=device
)

class RNN(nn.Module):
    
    def __init__(self, vocab_size, embedding_dim, hidden_dim):
        """
        """
        super(RNN, self).__init__()
        
        # [0-10001] => [100]
        self.embedding = nn.Embedding(vocab_size, embedding_dim)
        # [100] => [256]
        self.rnn = nn.LSTM(embedding_dim, hidden_dim, num_layers=2, 
                           bidirectional=True, dropout=0.5)
        # [256*2] => [1]
        self.fc = nn.Linear(hidden_dim*2, 1)
        self.dropout = nn.Dropout(0.5)
        
        
    def forward(self, x):
        """
        x: [seq_len, b] vs [b, 3, 28, 28]
        """
        # [seq, b, 1] => [seq, b, 100]
        embedding = self.dropout(self.embedding(x))
        
        # output: [seq, b, hid_dim*2]
        # hidden/h: [num_layers*2, b, hid_dim]
        # cell/c: [num_layers*2, b, hid_di]
        output, (hidden, cell) = self.rnn(embedding)
        
        # [num_layers*2, b, hid_dim] => 2 of [b, hid_dim] => [b, hid_dim*2]
        hidden = torch.cat([hidden[-2], hidden[-1]], dim=1)
        
        # [b, hid_dim*2] => [b, 1]
        hidden = self.dropout(hidden)
        out = self.fc(hidden)
        
        return out

rnn = RNN(len(TEXT.vocab), 100, 256)

pretrained_embedding = TEXT.vocab.vectors
print('pretrained_embedding:', pretrained_embedding.shape)
rnn.embedding.weight.data.copy_(pretrained_embedding)
print('embedding layer inited.')

optimizer = optim.Adam(rnn.parameters(), lr=1e-3)
criteon = nn.BCEWithLogitsLoss().to(device)
rnn.to(device)

import numpy as np

def binary_acc(preds, y):
    """
    get accuracy
    """
    preds = torch.round(torch.sigmoid(preds))
    correct = torch.eq(preds, y).float()
    acc = correct.sum() / len(correct)
    return acc

def train(rnn, iterator, optimizer, criteon):
    
    avg_acc = []
    rnn.train()
    
    for i, batch in enumerate(iterator):
        
        # [seq, b] => [b, 1] => [b]
        pred = rnn(batch.text).squeeze(1)
        # 
        loss = criteon(pred, batch.label)
        acc = binary_acc(pred, batch.label).item()
        avg_acc.append(acc)
        
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()
        
        if i%10 == 0:
            print(i, acc)
        
    avg_acc = np.array(avg_acc).mean()
    print('avg acc:', avg_acc)
    
    
def eval(rnn, iterator, criteon):
    
    avg_acc = []
    
    rnn.eval()
    
    with torch.no_grad():
        for batch in iterator:

            # [b, 1] => [b]
            pred = rnn(batch.text).squeeze(1)

            #
            loss = criteon(pred, batch.label)

            acc = binary_acc(pred, batch.label).item()
            avg_acc.append(acc)
        
    avg_acc = np.array(avg_acc).mean()
    
    print('>>test:', avg_acc)

for epoch in range(10):
    
    eval(rnn, test_iterator, criteon)
    train(rnn, train_iterator, optimizer, criteon)