《动手学深度学习》学习笔记2

1、循环神经网络进阶

import numpy as np
import torch
from torch import nn, optim
import torch.nn.functional as F
import sys
sys.path.append("../input/")
import d2l_jay9460 as d2l
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')

(corpus_indices, char_to_idx, idx_to_char, vocab_size) = d2l.load_data_jay_lyrics()

GRU模型

def gru(inputs, state, params):
    W_xz, W_hz, b_z, W_xr, W_hr, b_r, W_xh, W_hh, b_h, W_hq, b_q = params
    H, = state
    outputs = []
    for X in inputs:
        Z = torch.sigmoid(torch.matmul(X, W_xz) + torch.matmul(H, W_hz) + b_z)
        R = torch.sigmoid(torch.matmul(X, W_xr) + torch.matmul(H, W_hr) + b_r)
        H_tilda = torch.tanh(torch.matmul(X, W_xh) + R * torch.matmul(H, W_hh) + b_h)
        H = Z * H + (1 - Z) * H_tilda
        Y = torch.matmul(H, W_hq) + b_q
        outputs.append(Y)
    return outputs, (H,)

LSTM模型

def lstm(inputs, state, params):
    [W_xi, W_hi, b_i, W_xf, W_hf, b_f, W_xo, W_ho, b_o, W_xc, W_hc, b_c, W_hq, b_q] = params
    (H, C) = state
    outputs = []
    for X in inputs:
        I = torch.sigmoid(torch.matmul(X, W_xi) + torch.matmul(H, W_hi) + b_i)
        F = torch.sigmoid(torch.matmul(X, W_xf) + torch.matmul(H, W_hf) + b_f)
        O = torch.sigmoid(torch.matmul(X, W_xo) + torch.matmul(H, W_ho) + b_o)
        C_tilda = torch.tanh(torch.matmul(X, W_xc) + torch.matmul(H, W_hc) + b_c)
        C = F * C + I * C_tilda
        H = O * C.tanh()
        Y = torch.matmul(H, W_hq) + b_q
        outputs.append(Y)
    return outputs, (H, C)

深度循环神经网络

num_hiddens=256
num_epochs, num_steps, batch_size, lr, clipping_theta = 160, 35, 32, 1e2, 1e-2
pred_period, pred_len, prefixes = 40, 50, ['分开', '不分开']

lr = 1e-2 # 注意调整学习率

gru_layer = nn.LSTM(input_size=vocab_size, hidden_size=num_hiddens,num_layers=2)
model = d2l.RNNModel(gru_layer, vocab_size).to(device)
d2l.train_and_predict_rnn_pytorch(model, num_hiddens, vocab_size, device,
                                corpus_indices, idx_to_char, char_to_idx,
                                num_epochs, num_steps, lr, clipping_theta,
                                batch_size, pred_period, pred_len, prefixes)

双向循环神经网络

num_hiddens=256
num_epochs, num_steps, batch_size, lr, clipping_theta = 160, 35, 32, 1e2, 1e-2
pred_period, pred_len, prefixes = 40, 50, ['分开', '不分开']

lr = 1e-2 # 注意调整学习率

gru_layer = nn.LSTM(input_size=vocab_size, hidden_size=num_hiddens,num_layers=2)
model = d2l.RNNModel(gru_layer, vocab_size).to(device)
d2l.train_and_predict_rnn_pytorch(model, num_hiddens, vocab_size, device,
                                corpus_indices, idx_to_char, char_to_idx,
                                num_epochs, num_steps, lr, clipping_theta,
                                batch_size, pred_period, pred_len, prefixes)

2、机器翻译相关技术

数据预处理

with open('/home/kesci/input/fraeng6506/fra.txt', 'r') as f:
      raw_text = f.read()
print(raw_text[0:1000])
def preprocess_raw(text):
    text = text.replace('\u202f', ' ').replace('\xa0', ' ')
    out = ''
    for i, char in enumerate(text.lower()):
        if char in (',', '!', '.') and i > 0 and text[i-1] != ' ':
            out += ' '
        out += char
    return out

text = preprocess_raw(raw_text)
print(text[0:1000])

分词

num_examples = 50000
source, target = [], []
for i, line in enumerate(text.split('\n')):
    if i > num_examples:
        break
    parts = line.split('\t')
    if len(parts) >= 2:
        source.append(parts[0].split(' '))
        target.append(parts[1].split(' '))
        
source[0:3], target[0:3]

建词典

def build_vocab(tokens):
    tokens = [token for line in tokens for token in line]
    return d2l.data.base.Vocab(tokens, min_freq=3, use_special_tokens=True)

src_vocab = build_vocab(source)
len(src_vocab)

Encoder-Decoder

class Encoder(nn.Module):
    def __init__(self, **kwargs):
        super(Encoder, self).__init__(**kwargs)

    def forward(self, X, *args):
        raise NotImplementedError
class Decoder(nn.Module):
    def __init__(self, **kwargs):
        super(Decoder, self).__init__(**kwargs)

    def init_state(self, enc_outputs, *args):
        raise NotImplementedError

    def forward(self, X, state):
        raise NotImplementedError
class EncoderDecoder(nn.Module):
    def __init__(self, encoder, decoder, **kwargs):
        super(EncoderDecoder, self).__init__(**kwargs)
        self.encoder = encoder
        self.decoder = decoder

    def forward(self, enc_X, dec_X, *args):
        enc_outputs = self.encoder(enc_X, *args)
        dec_state = self.decoder.init_state(enc_outputs, *args)
        return self.decoder(dec_X, dec_state)

Sequence to Sequence模型

class Seq2SeqEncoder(d2l.Encoder):
    def __init__(self, vocab_size, embed_size, num_hiddens, num_layers,
                 dropout=0, **kwargs):
        super(Seq2SeqEncoder, self).__init__(**kwargs)
        self.num_hiddens=num_hiddens
        self.num_layers=num_layers
        self.embedding = nn.Embedding(vocab_size, embed_size)
        self.rnn = nn.LSTM(embed_size,num_hiddens, num_layers, dropout=dropout)
   
    def begin_state(self, batch_size, device):
        return [torch.zeros(size=(self.num_layers, batch_size, self.num_hiddens),  device=device),
                torch.zeros(size=(self.num_layers, batch_size, self.num_hiddens),  device=device)]
    def forward(self, X, *args):
        X = self.embedding(X) # X shape: (batch_size, seq_len, embed_size)
        X = X.transpose(0, 1)  # RNN needs first axes to be time
        # state = self.begin_state(X.shape[1], device=X.device)
        out, state = self.rnn(X)
        # The shape of out is (seq_len, batch_size, num_hiddens).
        # state contains the hidden state and the memory cell
        # of the last time step, the shape is (num_layers, batch_size, num_hiddens)
        return out, state
encoder = Seq2SeqEncoder(vocab_size=10, embed_size=8,num_hiddens=16, num_layers=2)
X = torch.zeros((4, 7),dtype=torch.long)
output, state = encoder(X)
output.shape, len(state), state[0].shape, state[1].shape

Decoder

class Seq2SeqDecoder(d2l.Decoder):
    def __init__(self, vocab_size, embed_size, num_hiddens, num_layers,
                 dropout=0, **kwargs):
        super(Seq2SeqDecoder, self).__init__(**kwargs)
        self.embedding = nn.Embedding(vocab_size, embed_size)
        self.rnn = nn.LSTM(embed_size,num_hiddens, num_layers, dropout=dropout)
        self.dense = nn.Linear(num_hiddens,vocab_size)

    def init_state(self, enc_outputs, *args):
        return enc_outputs[1]

    def forward(self, X, state):
        X = self.embedding(X).transpose(0, 1)
        out, state = self.rnn(X, state)
        # Make the batch to be the first dimension to simplify loss computation.
        out = self.dense(out).transpose(0, 1)
        return out, state
decoder = Seq2SeqDecoder(vocab_size=10, embed_size=8,num_hiddens=16, num_layers=2)
state = decoder.init_state(encoder(X))
out, state = decoder(X, state)
out.shape, len(state), state[0].shape, state[1].shape

3、注意力机制

softmax屏蔽

def SequenceMask(X, X_len,value=-1e6):
    maxlen = X.size(1)
    #print(X.size(),torch.arange((maxlen),dtype=torch.float)[None, :],'\n',X_len[:, None] )
    mask = torch.arange((maxlen),dtype=torch.float)[None, :] >= X_len[:, None]   
    #print(mask)
    X[mask]=value
    return X
def masked_softmax(X, valid_length):
    # X: 3-D tensor, valid_length: 1-D or 2-D tensor
    softmax = nn.Softmax(dim=-1)
    if valid_length is None:
        return softmax(X)
    else:
        shape = X.shape
        if valid_length.dim() == 1:
            try:
                valid_length = torch.FloatTensor(valid_length.numpy().repeat(shape[1], axis=0))#[2,2,3,3]
            except:
                valid_length = torch.FloatTensor(valid_length.cpu().numpy().repeat(shape[1], axis=0))#[2,2,3,3]
        else:
            valid_length = valid_length.reshape((-1,))
        # fill masked elements with a large negative, whose exp is 0
        X = SequenceMask(X.reshape((-1, shape[-1])), valid_length)
 
        return softmax(X).reshape(shape)

点积注意力

 Save to the d2l package.
class DotProductAttention(nn.Module): 
    def __init__(self, dropout, **kwargs):
        super(DotProductAttention, self).__init__(**kwargs)
        self.dropout = nn.Dropout(dropout)

    # query: (batch_size, #queries, d)
    # key: (batch_size, #kv_pairs, d)
    # value: (batch_size, #kv_pairs, dim_v)
    # valid_length: either (batch_size, ) or (batch_size, xx)
    def forward(self, query, key, value, valid_length=None):
        d = query.shape[-1]
        # set transpose_b=True to swap the last two dimensions of key
        
        scores = torch.bmm(query, key.transpose(1,2)) / math.sqrt(d)
        attention_weights = self.dropout(masked_softmax(scores, valid_length))
        print("attention_weight\n",attention_weights)
        return torch.bmm(attention_weights, value)

多层感知机注意力

# Save to the d2l package.
class MLPAttention(nn.Module):  
    def __init__(self, units,ipt_dim,dropout, **kwargs):
        super(MLPAttention, self).__init__(**kwargs)
        # Use flatten=True to keep query's and key's 3-D shapes.
        self.W_k = nn.Linear(ipt_dim, units, bias=False)
        self.W_q = nn.Linear(ipt_dim, units, bias=False)
        self.v = nn.Linear(units, 1, bias=False)
        self.dropout = nn.Dropout(dropout)

    def forward(self, query, key, value, valid_length):
        query, key = self.W_k(query), self.W_q(key)
        #print("size",query.size(),key.size())
        # expand query to (batch_size, #querys, 1, units), and key to
        # (batch_size, 1, #kv_pairs, units). Then plus them with broadcast.
        features = query.unsqueeze(2) + key.unsqueeze(1)
        #print("features:",features.size())  #--------------开启
        scores = self.v(features).squeeze(-1) 
        attention_weights = self.dropout(masked_softmax(scores, valid_length))
        return torch.bmm(attention_weights, value)

4、Transformer

多头注意力层

class MultiHeadAttention(nn.Module):
    def __init__(self, input_size, hidden_size, num_heads, dropout, **kwargs):
        super(MultiHeadAttention, self).__init__(**kwargs)
        self.num_heads = num_heads
        self.attention = DotProductAttention(dropout)
        self.W_q = nn.Linear(input_size, hidden_size, bias=False)
        self.W_k = nn.Linear(input_size, hidden_size, bias=False)
        self.W_v = nn.Linear(input_size, hidden_size, bias=False)
        self.W_o = nn.Linear(hidden_size, hidden_size, bias=False)
    
    def forward(self, query, key, value, valid_length):
        # query, key, and value shape: (batch_size, seq_len, dim),
        # where seq_len is the length of input sequence
        # valid_length shape is either (batch_size, )
        # or (batch_size, seq_len).

        # Project and transpose query, key, and value from
        # (batch_size, seq_len, hidden_size * num_heads) to
        # (batch_size * num_heads, seq_len, hidden_size).
        
        query = transpose_qkv(self.W_q(query), self.num_heads)
        key = transpose_qkv(self.W_k(key), self.num_heads)
        value = transpose_qkv(self.W_v(value), self.num_heads)
        
        if valid_length is not None:
            # Copy valid_length by num_heads times
            device = valid_length.device
            valid_length = valid_length.cpu().numpy() if valid_length.is_cuda else valid_length.numpy()
            if valid_length.ndim == 1:
                valid_length = torch.FloatTensor(np.tile(valid_length, self.num_heads))
            else:
                valid_length = torch.FloatTensor(np.tile(valid_length, (self.num_heads,1)))

            valid_length = valid_length.to(device)
            
        output = self.attention(query, key, value, valid_length)
        output_concat = transpose_output(output, self.num_heads)
        return self.W_o(output_concat)
def transpose_qkv(X, num_heads):
    # Original X shape: (batch_size, seq_len, hidden_size * num_heads),
    # -1 means inferring its value, after first reshape, X shape:
    # (batch_size, seq_len, num_heads, hidden_size)
    X = X.view(X.shape[0], X.shape[1], num_heads, -1)
    
    # After transpose, X shape: (batch_size, num_heads, seq_len, hidden_size)
    X = X.transpose(2, 1).contiguous()

    # Merge the first two dimensions. Use reverse=True to infer shape from
    # right to left.
    # output shape: (batch_size * num_heads, seq_len, hidden_size)
    output = X.view(-1, X.shape[2], X.shape[3])
    return output


# Saved in the d2l package for later use
def transpose_output(X, num_heads):
    # A reversed version of transpose_qkv
    X = X.view(-1, num_heads, X.shape[1], X.shape[2])
    X = X.transpose(2, 1).contiguous()
    return X.view(X.shape[0], X.shape[1], -1)

基于位置的前馈网络

# Save to the d2l package.
class PositionWiseFFN(nn.Module):
    def __init__(self, input_size, ffn_hidden_size, hidden_size_out, **kwargs):
        super(PositionWiseFFN, self).__init__(**kwargs)
        self.ffn_1 = nn.Linear(input_size, ffn_hidden_size)
        self.ffn_2 = nn.Linear(ffn_hidden_size, hidden_size_out)
        
        
    def forward(self, X):
        return self.ffn_2(F.relu(self.ffn_1(X)))

Add and Norm

# Save to the d2l package.
class AddNorm(nn.Module):
    def __init__(self, hidden_size, dropout, **kwargs):
        super(AddNorm, self).__init__(**kwargs)
        self.dropout = nn.Dropout(dropout)
        self.norm = nn.LayerNorm(hidden_size)
    
    def forward(self, X, Y):
        return self.norm(self.dropout(Y) + X)

位置编码

class PositionalEncoding(nn.Module):
    def __init__(self, embedding_size, dropout, max_len=1000):
        super(PositionalEncoding, self).__init__()
        self.dropout = nn.Dropout(dropout)
        self.P = np.zeros((1, max_len, embedding_size))
        X = np.arange(0, max_len).reshape(-1, 1) / np.power(
            10000, np.arange(0, embedding_size, 2)/embedding_size)
        self.P[:, :, 0::2] = np.sin(X)
        self.P[:, :, 1::2] = np.cos(X)
        self.P = torch.FloatTensor(self.P)
    
    def forward(self, X):
        if X.is_cuda and not self.P.is_cuda:
            self.P = self.P.cuda()
        X = X + self.P[:, :X.shape[1], :]
        return self.dropout(X)

编码器

class EncoderBlock(nn.Module):
    def __init__(self, embedding_size, ffn_hidden_size, num_heads,
                 dropout, **kwargs):
        super(EncoderBlock, self).__init__(**kwargs)
        self.attention = MultiHeadAttention(embedding_size, embedding_size, num_heads, dropout)
        self.addnorm_1 = AddNorm(embedding_size, dropout)
        self.ffn = PositionWiseFFN(embedding_size, ffn_hidden_size, embedding_size)
        self.addnorm_2 = AddNorm(embedding_size, dropout)

    def forward(self, X, valid_length):
        Y = self.addnorm_1(X, self.attention(X, X, X, valid_length))
        return self.addnorm_2(Y, self.ffn(Y))

class TransformerEncoder(d2l.Encoder):
    def __init__(self, vocab_size, embedding_size, ffn_hidden_size,
                 num_heads, num_layers, dropout, **kwargs):
        super(TransformerEncoder, self).__init__(**kwargs)
        self.embedding_size = embedding_size
        self.embed = nn.Embedding(vocab_size, embedding_size)
        self.pos_encoding = PositionalEncoding(embedding_size, dropout)
        self.blks = nn.ModuleList()
        for i in range(num_layers):
            self.blks.append(
                EncoderBlock(embedding_size, ffn_hidden_size,
                             num_heads, dropout))

    def forward(self, X, valid_length, *args):
        X = self.pos_encoding(self.embed(X) * math.sqrt(self.embedding_size))
        for blk in self.blks:
            X = blk(X, valid_length)
        return X

解码器

class DecoderBlock(nn.Module):
    def __init__(self, embedding_size, ffn_hidden_size, num_heads,dropout,i,**kwargs):
        super(DecoderBlock, self).__init__(**kwargs)
        self.i = i
        self.attention_1 = MultiHeadAttention(embedding_size, embedding_size, num_heads, dropout)
        self.addnorm_1 = AddNorm(embedding_size, dropout)
        self.attention_2 = MultiHeadAttention(embedding_size, embedding_size, num_heads, dropout)
        self.addnorm_2 = AddNorm(embedding_size, dropout)
        self.ffn = PositionWiseFFN(embedding_size, ffn_hidden_size, embedding_size)
        self.addnorm_3 = AddNorm(embedding_size, dropout)
    
    def forward(self, X, state):
        enc_outputs, enc_valid_length = state[0], state[1]
        
        # state[2][self.i] stores all the previous t-1 query state of layer-i
        # len(state[2]) = num_layers
        
        # If training:
        #     state[2] is useless.
        # If predicting:
        #     In the t-th timestep:
        #         state[2][self.i].shape = (batch_size, t-1, hidden_size)
        # Demo:
        # love dogs ! [EOS]
        #  |    |   |   |
        #   Transformer 
        #    Decoder
        #  |   |   |   |
        #  I love dogs !
        
        if state[2][self.i] is None:
            key_values = X
        else:
            # shape of key_values = (batch_size, t, hidden_size)
            key_values = torch.cat((state[2][self.i], X), dim=1) 
        state[2][self.i] = key_values
        
        if self.training:
            batch_size, seq_len, _ = X.shape
            # Shape: (batch_size, seq_len), the values in the j-th column are j+1
            valid_length = torch.FloatTensor(np.tile(np.arange(1, seq_len+1), (batch_size, 1))) 
            valid_length = valid_length.to(X.device)
        else:
            valid_length = None

        X2 = self.attention_1(X, key_values, key_values, valid_length)
        Y = self.addnorm_1(X, X2)
        Y2 = self.attention_2(Y, enc_outputs, enc_outputs, enc_valid_length)
        Z = self.addnorm_2(Y, Y2)
        return self.addnorm_3(Z, self.ffn(Z)), state
decoder_blk = DecoderBlock(24, 48, 8, 0.5, 0)
X = torch.ones((2, 100, 24))
state = [encoder_blk(X, valid_length), valid_length, [None]]
decoder_blk(X, state)[0].shape

class TransformerDecoder(d2l.Decoder):
    def __init__(self, vocab_size, embedding_size, ffn_hidden_size,
                 num_heads, num_layers, dropout, **kwargs):
        super(TransformerDecoder, self).__init__(**kwargs)
        self.embedding_size = embedding_size
        self.num_layers = num_layers
        self.embed = nn.Embedding(vocab_size, embedding_size)
        self.pos_encoding = PositionalEncoding(embedding_size, dropout)
        self.blks = nn.ModuleList()
        for i in range(num_layers):
            self.blks.append(
                DecoderBlock(embedding_size, ffn_hidden_size, num_heads,
                             dropout, i))
        self.dense = nn.Linear(embedding_size, vocab_size)

    def init_state(self, enc_outputs, enc_valid_length, *args):
        return [enc_outputs, enc_valid_length, [None]*self.num_layers]

    def forward(self, X, state):
        X = self.pos_encoding(self.embed(X) * math.sqrt(self.embedding_size))
        for blk in self.blks:
            X, state = blk(X, state)
        return self.dense(X), state

5、过拟合，欠拟合及解决方案

丢弃法

def dropout(X, drop_prob):
    X = X.float()
    assert 0 <= drop_prob <= 1
    keep_prob = 1 - drop_prob
    # 这种情况下把全部元素都丢弃
    if keep_prob == 0:
        return torch.zeros_like(X)
    mask = (torch.rand(X.shape) < keep_prob).float()
    
    return mask * X / keep_prob

简洁实现

net = nn.Sequential(
        d2l.FlattenLayer(),
        nn.Linear(num_inputs, num_hiddens1),
        nn.ReLU(),
        nn.Dropout(drop_prob1),
        nn.Linear(num_hiddens1, num_hiddens2), 
        nn.ReLU(),
        nn.Dropout(drop_prob2),
        nn.Linear(num_hiddens2, 10)
        )

for param in net.parameters():
    nn.init.normal_(param, mean=0, std=0.01)
optimizer = torch.optim.SGD(net.parameters(), lr=0.5)
d2l.train_ch3(net, train_iter, test_iter, loss, num_epochs, batch_size, None, None, optimizer)

6、梯度消失、梯度爆炸

协变量偏移

这里我们假设，虽然输入的分布可能随时间而改变，但是标记函数，即条件分布P（y∣x）不会改变。虽然这个问题容易理解，但在实践中也容易忽视。想想区分猫和狗的一个例子。我们的训练数据使用的是猫和狗的真实的照片，但是在测试时，我们被要求对猫和狗的卡通图片进行分类。
显然，这不太可能奏效。训练集由照片组成，而测试集只包含卡通。在一个看起来与测试集有着本质不同的数据集上进行训练，而不考虑如何适应新的情况，这是不是一个好主意。不幸的是，这是一个非常常见的陷阱。

统计学家称这种协变量变化是因为问题的根源在于特征分布的变化（即协变量的变化）。数学上，我们可以说P（x）改变了，但P（y∣x）保持不变。尽管它的有用性并不局限于此，当我们认为x导致y时，协变量移位通常是正确的假设

标签偏移

当我们认为导致偏移的是标签P（y）上的边缘分布的变化，但类条件分布是不变的P（x∣y）时，就会出现相反的问题。当我们认为y导致x时，标签偏移是一个合理的假设。例如，通常我们希望根据其表现来预测诊断结果。在这种情况下，我们认为诊断引起的表现，即疾病引起的症状。有时标签偏移和协变量移位假设可以同时成立。例如，当真正的标签函数是确定的和不变的，那么协变量偏移将始终保持，包括如果标签偏移也保持。有趣的是，当我们期望标签偏移和协变量偏移保持时，使用来自标签偏移假设的方法通常是有利的。这是因为这些方法倾向于操作看起来像标签的对象，这（在深度学习中）与处理看起来像输入的对象（在深度学习中）相比相对容易一些。病因（要预测的诊断结果）导致 症状（观察到的结果）。训练数据集，数据很少只包含流感p(y)的样本。而测试数据集有流感p(y)和流感q(y)，其中不变的是流感症状p(x|y)。

概念偏移

另一个相关的问题出现在概念转换中，即标签本身的定义发生变化的情况。这听起来很奇怪，毕竟猫就是猫。的确，猫的定义可能不会改变，但我们能不能对软饮料也这么说呢？事实证明，如果我们周游美国，按地理位置转移数据来源，我们会发现，即使是如图所示的这个简单术语的定义也会发生相当大的概念转变。
如果我们要建立一个机器翻译系统，分布P（y∣x）可能因我们的位置而异。这个问题很难发现。另一个可取之处是P（y∣x）通常只是逐渐变化。

7、卷积神经网络基础

卷积层简洁实现

X = torch.rand(4, 2, 3, 5)
print(X.shape)

conv2d = nn.Conv2d(in_channels=2, out_channels=3, kernel_size=(3, 5), stride=1, padding=(1, 2))
Y = conv2d(X)
print('Y.shape: ', Y.shape)
print('weight.shape: ', conv2d.weight.shape)
print('bias.shape: ', conv2d.bias.shape)

池化层简洁实现

X = torch.arange(32, dtype=torch.float32).view(1, 2, 4, 4)
pool2d = nn.MaxPool2d(kernel_size=3, padding=1, stride=(2, 1))
Y = pool2d(X)
print(X)
print(Y)

8、LeNet

#net
class Flatten(torch.nn.Module):  #展平操作
    def forward(self, x):
        return x.view(x.shape[0], -1)

class Reshape(torch.nn.Module): #将图像大小重定型
    def forward(self, x):
        return x.view(-1,1,28,28)      #(B x C x H x W)
    
net = torch.nn.Sequential(     #Lelet                                                  
    Reshape(),
    nn.Conv2d(in_channels=1, out_channels=6, kernel_size=5, padding=2), #b*1*28*28  =>b*6*28*28
    nn.Sigmoid(),                                                       
    nn.AvgPool2d(kernel_size=2, stride=2),                              #b*6*28*28  =>b*6*14*14
    nn.Conv2d(in_channels=6, out_channels=16, kernel_size=5),           #b*6*14*14  =>b*16*10*10
    nn.Sigmoid(),
    nn.AvgPool2d(kernel_size=2, stride=2),                              #b*16*10*10  => b*16*5*5
    Flatten(),                                                          #b*16*5*5   => b*400
    nn.Linear(in_features=16*5*5, out_features=120),
    nn.Sigmoid(),
    nn.Linear(120, 84),
    nn.Sigmoid(),
    nn.Linear(84, 10)
)

9、卷积神经网络进阶

AlexNet

import time
import torch
from torch import nn, optim
import torchvision
import numpy as np
import sys
sys.path.append("/home/kesci/input/") 
import d2lzh1981 as d2l
import os
import torch.nn.functional as F

device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')

class AlexNet(nn.Module):
    def __init__(self):
        super(AlexNet, self).__init__()
        self.conv = nn.Sequential(
            nn.Conv2d(1, 96, 11, 4), # in_channels, out_channels, kernel_size, stride, padding
            nn.ReLU(),
            nn.MaxPool2d(3, 2), # kernel_size, stride
            # 减小卷积窗口，使用填充为2来使得输入与输出的高和宽一致，且增大输出通道数
            nn.Conv2d(96, 256, 5, 1, 2),
            nn.ReLU(),
            nn.MaxPool2d(3, 2),
            # 连续3个卷积层，且使用更小的卷积窗口。除了最后的卷积层外，进一步增大了输出通道数。
            # 前两个卷积层后不使用池化层来减小输入的高和宽
            nn.Conv2d(256, 384, 3, 1, 1),
            nn.ReLU(),
            nn.Conv2d(384, 384, 3, 1, 1),
            nn.ReLU(),
            nn.Conv2d(384, 256, 3, 1, 1),
            nn.ReLU(),
            nn.MaxPool2d(3, 2)
        )
         # 这里全连接层的输出个数比LeNet中的大数倍。使用丢弃层来缓解过拟合
        self.fc = nn.Sequential(
            nn.Linear(256*5*5, 4096),
            nn.ReLU(),
            nn.Dropout(0.5),
            #由于使用CPU镜像，精简网络，若为GPU镜像可添加该层
            #nn.Linear(4096, 4096),
            #nn.ReLU(),
            #nn.Dropout(0.5),

            # 输出层。由于这里使用Fashion-MNIST，所以用类别数为10，而非论文中的1000
            nn.Linear(4096, 10),
        )

    def forward(self, img):

        feature = self.conv(img)
        output = self.fc(feature.view(img.shape[0], -1))
        return output

VGG

def vgg_block(num_convs, in_channels, out_channels): #卷积层个数，输入通道数，输出通道数
    blk = []
    for i in range(num_convs):
        if i == 0:
            blk.append(nn.Conv2d(in_channels, out_channels, kernel_size=3, padding=1))
        else:
            blk.append(nn.Conv2d(out_channels, out_channels, kernel_size=3, padding=1))
        blk.append(nn.ReLU())
    blk.append(nn.MaxPool2d(kernel_size=2, stride=2)) # 这里会使宽高减半
    return nn.Sequential(*blk)
conv_arch = ((1, 1, 64), (1, 64, 128), (2, 128, 256), (2, 256, 512), (2, 512, 512))
# 经过5个vgg_block, 宽高会减半5次, 变成 224/32 = 7
fc_features = 512 * 7 * 7 # c * w * h
fc_hidden_units = 4096 # 任意
def vgg(conv_arch, fc_features, fc_hidden_units=4096):
    net = nn.Sequential()
    # 卷积层部分
    for i, (num_convs, in_channels, out_channels) in enumerate(conv_arch):
        # 每经过一个vgg_block都会使宽高减半
        net.add_module("vgg_block_" + str(i+1), vgg_block(num_convs, in_channels, out_channels))
    # 全连接层部分
    net.add_module("fc", nn.Sequential(d2l.FlattenLayer(),
                                 nn.Linear(fc_features, fc_hidden_units),
                                 nn.ReLU(),
                                 nn.Dropout(0.5),
                                 nn.Linear(fc_hidden_units, fc_hidden_units),
                                 nn.ReLU(),
                                 nn.Dropout(0.5),
                                 nn.Linear(fc_hidden_units, 10)
                                ))
    return net

NiN

def nin_block(in_channels, out_channels, kernel_size, stride, padding):
    blk = nn.Sequential(nn.Conv2d(in_channels, out_channels, kernel_size, stride, padding),
                        nn.ReLU(),
                        nn.Conv2d(out_channels, out_channels, kernel_size=1),
                        nn.ReLU(),
                        nn.Conv2d(out_channels, out_channels, kernel_size=1),
                        nn.ReLU())
    return blk
# 已保存在d2lzh_pytorch
class GlobalAvgPool2d(nn.Module):
    # 全局平均池化层可通过将池化窗口形状设置成输入的高和宽实现
    def __init__(self):
        super(GlobalAvgPool2d, self).__init__()
    def forward(self, x):
        return F.avg_pool2d(x, kernel_size=x.size()[2:])

net = nn.Sequential(
    nin_block(1, 96, kernel_size=11, stride=4, padding=0),
    nn.MaxPool2d(kernel_size=3, stride=2),
    nin_block(96, 256, kernel_size=5, stride=1, padding=2),
    nn.MaxPool2d(kernel_size=3, stride=2),
    nin_block(256, 384, kernel_size=3, stride=1, padding=1),
    nn.MaxPool2d(kernel_size=3, stride=2), 
    nn.Dropout(0.5),
    # 标签类别数是10
    nin_block(384, 10, kernel_size=3, stride=1, padding=1),
    GlobalAvgPool2d(), 
    # 将四维的输出转成二维的输出，其形状为(批量大小, 10)
    d2l.FlattenLayer())

GoogLeNet

class Inception(nn.Module):
    # c1 - c4为每条线路里的层的输出通道数
    def __init__(self, in_c, c1, c2, c3, c4):
        super(Inception, self).__init__()
        # 线路1，单1 x 1卷积层
        self.p1_1 = nn.Conv2d(in_c, c1, kernel_size=1)
        # 线路2，1 x 1卷积层后接3 x 3卷积层
        self.p2_1 = nn.Conv2d(in_c, c2[0], kernel_size=1)
        self.p2_2 = nn.Conv2d(c2[0], c2[1], kernel_size=3, padding=1)
        # 线路3，1 x 1卷积层后接5 x 5卷积层
        self.p3_1 = nn.Conv2d(in_c, c3[0], kernel_size=1)
        self.p3_2 = nn.Conv2d(c3[0], c3[1], kernel_size=5, padding=2)
        # 线路4，3 x 3最大池化层后接1 x 1卷积层
        self.p4_1 = nn.MaxPool2d(kernel_size=3, stride=1, padding=1)
        self.p4_2 = nn.Conv2d(in_c, c4, kernel_size=1)

    def forward(self, x):
        p1 = F.relu(self.p1_1(x))
        p2 = F.relu(self.p2_2(F.relu(self.p2_1(x))))
        p3 = F.relu(self.p3_2(F.relu(self.p3_1(x))))
        p4 = F.relu(self.p4_2(self.p4_1(x)))
        return torch.cat((p1, p2, p3, p4), dim=1)  # 在通道维上连结输出