the_annotated_transformer.py

# -*- coding: utf-8 -*-            
# Time : 2022/9/14 11:21
# Author : Regulus
# FileName: main.py
# Explain: The Annotated Transformer
# Software: PyCharm

import os
from os.path import exists
import torch
import torch.nn as nn
from torch.nn.functional import log_softmax, pad
import math
import copy
import time
from torch.optim.lr_scheduler import LambdaLR
import pandas as pd
import altair as alt
from torchtext.data.functional import to_map_style_dataset
from torch.utils.data import DataLoader
from torchtext.vocab import build_vocab_from_iterator
import torchtext.datasets as datasets
import spacy
import GPUtil
import warnings
from torch.utils.data.distributed import DistributedSampler
import torch.distributed as dist
import torch.multiprocessing as mp
from torch.nn.parallel import DistributedDataParallel as DDP


# Set to False to skip notebook execution (e.g. for debugging)
warnings.filterwarnings("ignore")
RUN_EXAMPLES = True


# Some convenience helper functions used throughout the notebook


def is_interactive_notebook():
    return __name__ == "__main__"


def show_example(fn, args=[]):
    if __name__ == "__main__" and RUN_EXAMPLES:
        return fn(*args)


def execute_example(fn, args=[]):
    if __name__ == "__main__" and RUN_EXAMPLES:
        fn(*args)


class DummyOptimizer(torch.optim.Optimizer):
    def __init__(self):
        self.param_groups = [{"lr": 0}]
        None

    def step(self):
        None

    def zero_grad(self, set_to_none=False):
        None


class DummyScheduler:
    def step(self):
        None


def clones(module, N):
    "Produce N identical layers."
    return nn.ModuleList([copy.deepcopy(module) for _ in range(N)])


class Embeddings(nn.Module):
    def __init__(self, d_model, vocab):
        # d_model=512, vocab=当前语言词表大小
        super(Embeddings, self).__init__()
        self.lut = nn.Embedding(vocab, d_model)
        # one-hot转词嵌入，待训练矩阵E，大小为vocab*d_model
        self.d_model = d_model
    def forward(self, x):
        # x ~ (batch.size, sequence.length, one-hot),
        # one-hot 大小=vocab，当前语言词表大小
        return self.lut(x)*math.sqrt(self.d_model)
        # 得到的词嵌入矩阵tensor的维度：(batch.size, sequence.length, 512)


class PositionalEncoding(nn.Module):
    """
    Implement the PE function.
    Reference: https://blog.csdn.net/qq_34771726/article/details/102918440
    """

    def __init__(self, d_model, dropout, max_len=5000):
        super(PositionalEncoding, self).__init__()
        self.dropout = nn.Dropout(p=dropout)

        # Compute the positional encodings once in log space.
        pe = torch.zeros(max_len, d_model)
        position = torch.arange(0, max_len).unsqueeze(1)
        div_term = torch.exp(
            torch.arange(0, d_model, 2) * -(math.log(10000.0) / d_model)
        )
        pe[:, 0::2] = torch.sin(position * div_term)
        pe[:, 1::2] = torch.cos(position * div_term)
        pe = pe.unsqueeze(0)
        self.register_buffer("pe", pe)

    def forward(self, x):
        x = x + self.pe[:, : x.size(1)].requires_grad_(False)
        # 例如，假设x是(30,10,512)的一个tensor，30是batch.size, 10是该batch的序列长度, 512是每个词的词嵌入向量；
        # 则该行代码的第二项是(1, min(10, 5000), 512)=(1,10,512)，
        # 在具体相加的时候，会扩展(1,10,512)为(30,10,512)，
        return self.dropout(x)


def attention(query, key, value, mask=None, dropout=None):
    # query, key, value的形状类似于(30, 8, 10, 64), (30, 8, 11, 64), (30, 8, 11, 64)，
    # 例如30是batch.size，即当前batch中有多少一个序列；8=head.num，注意力头的个数；
    # 10=目标序列中词的个数，64是每个词对应的向量表示；11=源语言序列传过来的memory中，当前序列的词的个数，
    # 64是每个词对应的向量表示。
    # 类似于，这里假定query来自target language sequence；
    # key和value都来自source language sequence.
    """
    Compute 'Scaled Dot Product Attention'
    Reference: https://www.youtube.com/watch?v=ugWDIIOHtPA
    """
    d_k = query.size(-1)
    scores = torch.matmul(query, key.transpose(-2, -1)) / math.sqrt(d_k)  # shape (30, 8, 10, 11)
    if mask is not None:
        scores = scores.masked_fill(mask == 0, -1e9)
    p_attn = scores.softmax(dim=-1)
    if dropout is not None:
        p_attn = dropout(p_attn)
    # return shape (30, 8, 10, 64) 和query的最初的形状一样。另外，返回p_attn，形状为(30,8,10,11).
    # 注意，这里返回p_attn主要是用来可视化显示多头注意力机制。
    return torch.matmul(p_attn, value), p_attn


class MultiHeadedAttention(nn.Module):
    # 一头注意力和多头注意力的参数量是一样的，只是计算注意力得到特征的过程从整体分散到了局部，差异可能是：第一个head语法相关，第二个是偏语义等
    def __init__(self, h, d_model, dropout=0.1):
        # h=8, d_model=512
        "Take in model size and number of heads."
        super(MultiHeadedAttention, self).__init__()
        assert d_model % h == 0
        # We assume d_v always equals d_k
        self.d_k = d_model // h  # d_k=512//8=64
        self.h = h
        self.linears = clones(nn.Linear(d_model, d_model), 4)  # 四个Linear Networks，每个都是可学习的
        self.attn = None
        self.dropout = nn.Dropout(p=dropout)

    def forward(self, query, key, value, mask=None):
        # 注意，输入query的形状类似于(30, 10, 512)，
        # key.size() ~ (30, 11, 512),
        # 以及value.size() ~ (30, 11, 512)
        if mask is not None:
            # Same mask applied to all h heads.
            mask = mask.unsqueeze(1)
        nbatches = query.size(0)

        # 1) Do all the linear projections in batch from d_model => (batch, h, featureNum // h, d_model)
        # 就是把输入进来的特征，通过线性层，分配给每个头
        query, key, value = [
            lin(x).view(nbatches, -1, self.h, self.d_k).transpose(1, 2)
            for lin, x in zip(self.linears, (query, key, value))
        ]

        # 2) Apply attention on all the projected vectors in batch.
        x, self.attn = attention(
            query, key, value, mask=mask, dropout=self.dropout
        )

        # 3) "Concat" using a view and apply a final linear. => (30, 10, 8*64) = (30, 10, 512)
        x = (
            x.transpose(1, 2)
            .contiguous()
            .view(nbatches, -1, self.h * self.d_k)
        )
        del query
        del key
        del value
        return self.linears[-1](x)


class LayerNorm(nn.Module):
    """
    Construct a layernorm module (See citation for details).
    Reference: https://blog.csdn.net/Little_White_9/article/details/123345062
    """
    def __init__(self, features, eps=1e-6):
        # features=d_model=512, eps=epsilon 用与分母的非零化平滑
        # a_2与b_2是可训练的参数向量,(512)
        super(LayerNorm, self).__init__()
        self.a_2 = nn.Parameter(torch.ones(features))
        self.b_2 = nn.Parameter(torch.zeros(features))
        self.eps = eps

    def forward(self, x):
        # x的形状为(batch.size, sequence.len, 512)
        mean = x.mean(-1, keepdim=True)
        std = x.std(-1, keepdim=True)
        return self.a_2 * (x - mean) / (std + self.eps) + self.b_2
        # 对x的最后一个维度取平均值和标准方差，本质上类似于（x-mean）/ std
        # 分母上架的极小值epsilon用来防止std为0


class SublayerConnection(nn.Module):
    """
    A residual connection followed by a layer norm.
    Note for code simplicity the norm is first as opposed to last.
    """
    def __init__(self, size, dropout):
        super(SublayerConnection, self).__init__()
        self.norm = LayerNorm(size)
        self.dropout = nn.Dropout(dropout)

    def forward(self, x, sublayer):
        # x is alike (batch.size, sequence.len, 512)
        # sublayer是一个具体的MultiHeadAttention或者PositionwiseFeedForward对象
        "Apply residual connection to any sublayer with the same size."
        return x + self.dropout(sublayer(self.norm(x)))
        # 操作并不完全与论文一致，Reference：https://zhuanlan.zhihu.com/p/107891957


class PositionwiseFeedForward(nn.Module):
    "Implements FFN equation."

    def __init__(self, d_model, d_ff, dropout=0.1):
        super(PositionwiseFeedForward, self).__init__()
        self.w_1 = nn.Linear(d_model, d_ff)
        self.w_2 = nn.Linear(d_ff, d_model)
        self.dropout = nn.Dropout(dropout)

    def forward(self, x):
        return self.w_2(self.dropout(self.w_1(x).relu()))


class EncoderLayer(nn.Module):
    """
    Encoder is made up of self-attn and feed forward (defined below)
    Reference：https://blog.csdn.net/weixin_42253689/article/details/113838263
    """

    def __init__(self, size, self_attn, feed_forward, dropout):
        # size=d_model=512
        # self_attn = MultiHeadAttention对象, first sublayer
        # feed_forward = PositionwiseFeedForward对象，second sublayer
        # dropout = 0.1 (e.g.)
        super(EncoderLayer, self).__init__()
        self.self_attn = self_attn
        self.feed_forward = feed_forward
        self.sublayer = clones(SublayerConnection(size, dropout), 2)
        self.size = size

    def forward(self, x, mask):
        "Follow Figure 1 (left) for connections."
        # x shape = (30, 10, 512)
        # mask 是(batch.size, 10,10)的矩阵，类似于当前一个词w，有哪些词是w可见的
        # 在encoder中，输入的是一batch的句子，为了进行batch训练，句子结尾进行了padding（P）。
        # 在输入encoder中训练的过程中，先进行多头自注意计算。在这个过程中进行(q * K ^ T) / d_model ^ 1 / 2.
        # 然后要对得到的权重矩阵进行mask，再将结果进行softmax，去除掉不必要padding的影响，然后才和V矩阵相乘。
        x = self.sublayer[0](x, lambda x: self.self_attn(x, x, x, mask))
        return self.sublayer[1](x, self.feed_forward)

class Encoder(nn.Module):
    "Core encoder is a stack of N layers"
    def __init__(self, layer, N):
        # layer = one EncoderLayer object, N=6
        super(Encoder, self).__init__()
        self.layers = clones(layer, N)
        # 深copy，N=6，
        self.norm = LayerNorm(layer.size)
        # 定义一个LayerNorm，layer.size=d_model=512
        # 其中有两个可训练参数a_2和b_2

    def forward(self, x, mask):
        "Pass the input (and mask) through each layer in turn."
        # x is alike (30, 10, 512)
        # (batch.size, sequence.len, d_model)
        # mask是类似于(batch.size, 10, 10)的矩阵
        for layer in self.layers:
            x = layer(x, mask)
            # 进行六次EncoderLayer操作
        return self.norm(x)
        # 最后做一次LayerNorm，最后的输出也是(30, 10, 512) shape


class DecoderLayer(nn.Module):
    "Decoder is made of self-attn, src-attn, and feed forward (defined below)"

    def __init__(self, size, self_attn, src_attn, feed_forward, dropout):
        super(DecoderLayer, self).__init__()
        self.size = size
        self.self_attn = self_attn
        self.src_attn = src_attn
        self.feed_forward = feed_forward
        self.sublayer = clones(SublayerConnection(size, dropout), 3)

    def forward(self, x, memory, src_mask, tgt_mask):
        # todo 这里x和memory是一个东西不
        "Follow Figure 1 (right) for connections."
        m = memory
        # 来自源语言序列的Encoder之后的输出，作为memory供目标语言的序列检索匹配
        x = self.sublayer[0](x, lambda x: self.self_attn(x, x, x, tgt_mask))
        x = self.sublayer[1](x, lambda x: self.self_attn(x, m, m, src_mask))
        # 对这里lambda函数的使用：https://blog.csdn.net/JasonFuyz/article/details/123685297
        return self.sublayer[2](x, self.feed_forward)


class Decoder(nn.Module):
    "Generic N layer decoder with masking."
    def __init__(self, layer, N):
        # layer = DecoderLayer object
        # N = 6
        super(Decoder, self).__init__()
        self.layers = clones(layer, N)
        # 深度copy六次DecoderLayer
        self.norm = LayerNorm(layer.size)
        # 初始化一个LayerNorm

    def forward(self, x, memory, src_mask, tgt_mask):
        for layer in self.layers:
            x = layer(x, memory, src_mask, tgt_mask)
            # 执行六次DecoderLayer
        return self.norm(x)
        # 执行一次LayerNorm


class Generator(nn.Module):
    "Define standard linear + softmax generation step."

    def __init__(self, d_model, vocab):
        super(Generator, self).__init__()
        self.proj = nn.Linear(d_model, vocab)

    def forward(self, x):
        return log_softmax(self.proj(x), dim=-1)


class EncoderDecoder(nn.Module):
    """
    A standard Encoder-Decoder architecture. Base for this and many
    other models.
    """

    def __init__(self, encoder, decoder, src_embed, tgt_embed, generator):
        super(EncoderDecoder, self).__init__()
        self.encoder = encoder
        self.decoder = decoder
        self.src_embed = src_embed
        self.tgt_embed = tgt_embed
        # 源语言和目标语言序列的编码，包括词嵌入和位置编码
        self.generator = generator

    def forward(self, src, tgt, src_mask, tgt_mask):
        "Take in and process masked src and target sequences."
        return self.decode(self.encode(src, src_mask), src_mask, tgt, tgt_mask)

    # 先对源语言进行编码，结果作为memory传递给目标语言的编码器
    def encode(self, src, src_mask):
        return self.encoder(self.src_embed(src), src_mask)

    # 对目标语言序列进行编码
    def decode(self, memory, src_mask, tgt, tgt_mask):
        return self.decoder(self.tgt_embed(tgt), memory, src_mask, tgt_mask)

def subsequent_mask(size):
    """
    Mask out subsequent positions.
    Reference: https://blog.csdn.net/weixin_42253689/article/details/113838263
    """

    attn_shape = (1, size, size)
    subsequent_mask = torch.triu(torch.ones(attn_shape), diagonal=1).type(
        torch.uint8
    )
    # triu: 一个三角矩阵，diagonal以下都设置为0
    return subsequent_mask == 0
    # 反转上面triu得到的上三角矩阵，得到下三角矩阵


def make_model(
        src_vocab, tgt_vocab, N=6, d_model=512, d_ff=512, h=8, dropout=0.1):
    "Helper: Construct a model from hyperparameters."
    c = copy.deepcopy
    attn = MultiHeadedAttention(h, d_model)
    ff = PositionwiseFeedForward(d_model, d_ff, dropout)
    position = PositionalEncoding(d_model, dropout)
    model = EncoderDecoder(
        Encoder(EncoderLayer(d_model, c(attn), c(ff), dropout), N),
        Decoder(DecoderLayer(d_model, c(attn), c(attn), c(ff), dropout), N),
        nn.Sequential(Embeddings(d_model, src_vocab), c(position)),
        nn.Sequential(Embeddings(d_model, tgt_vocab), c(position)),
        Generator(d_model, tgt_vocab),
    )

    # This was important from their code.
    # Initialize parameters with Glorot / fan_avg.
    for p in model.parameters():
        if p.dim() > 1:
            nn.init.xavier_uniform_(p)
    return model


def inference_test():
    """
    测试模型
    """
    # 构架测试模型，原词典和目标词典大小都为11，
    # EncoderLayer和DecoderLayer的数量为2
    test_model = make_model(11, 11, 2)
    test_model.eval()
    # 定义inputs, shape为(1, 10)，即一个句子，该句子10个单词。
    src = torch.LongTensor([[1, 2, 3, 4, 5, 6, 7, 8, 9, 10]])
    # 定义src_mask，即所有的词都是有效的，没有填充词
    src_mask = torch.ones(1, 1, 10)

    # 将输入送给encoder，获取memory
    memory = test_model.encode(src, src_mask)

    # 初始化ys为[[0]]，用于保存预测结果，其中0表示'<bos>'
    ys = torch.zeros(1, 1).type_as(src)

    # 循环调用decoder，一个个的进行预测。例如：假设我们要将“I love you”翻译成
    # “我爱你”，则第一次的`ys`为(<bos>)，然后输出为“I”。然后第二次`ys`为(<bos>, I)
    # 输出为"love"，依次类推，直到decoder输出“<eos>”或达到句子长度。
    for i in range(9):
        # 将encoder的输出memory和之前Decoder的所有输出作为参数，让Decoder来预测下一个token
        out = test_model.decode(
            # ys就是Decoder之前的所有输出
            memory, src_mask, ys, subsequent_mask(ys.size(1)).type_as(src.data)
        )
        # 将Decoder的输出送给generator进行预测。这里只取最后一个词的输出进行预测。
        # 因为你传的tgt的词数是变化的，第一次是(<bos>)，第二次是(<bos>, I)
        # 所以你的out的维度也是变化的，变化的就是(batch_size, 词数，词向量)中词数这个维度
        # 既然只能取一个，那当然是最后一个词最合适。
        prob = test_model.generator(out[:, -1])
        # 取出数值最大的那个，它的index在词典中对应的词就是预测结果
        _, next_word = torch.max(prob, dim=1)
        # 取出预测结果
        next_word = next_word.data[0]
        # 将这一次的预测结果和之前的拼到一块，作为之后Decoder的输入
        ys = torch.cat(
            [ys, torch.empty(1, 1).type_as(src.data).fill_(next_word)], dim=1
        )

    print("Example Untrained Model Prediction:", ys)


def run_tests():
    for _ in range(10):
        inference_test()


# run_tests()


class Batch:
    """Object for holding a batch of data with mask during training."""

    def __init__(self, src, tgt=None, pad=2):  # 2 = <blank>
        """
        src: 和EncoderDecoder#forward中的那个src一致。
             未进行word embedding的句子，例如`[[ 0, 5, 4, 6, 1, 2, 2 ]]`
             上例shape为(1, 7)，即batch size为1，句子大小为7。其中0为bos，
             1为eos, 2为pad

        tgt: 和src类似。是目标句子。
        """
        self.src = src

        self.src_mask = (src != pad).unsqueeze(-2)
        if tgt is not None:
            self.tgt = tgt[:, :-1]
            self.tgt_y = tgt[:, 1:]
            self.tgt_mask = self.make_std_mask(self.tgt, pad)
            self.ntokens = (self.tgt_y != pad).data.sum()

    @staticmethod
    def make_std_mask(tgt, pad):
        "Create a mask to hide padding and future words."
        tgt_mask = (tgt != pad).unsqueeze(-2)
        tgt_mask = tgt_mask & subsequent_mask(tgt.size(-1)).type_as(
            tgt_mask.data
        )
        return tgt_mask


class TrainState:
    """Track number of steps, examples, and tokens processed"""

    step: int = 0  # Steps in the current epoch
    accum_step: int = 0  # Number of gradient accumulation steps
    samples: int = 0  # total # of examples used
    tokens: int = 0  # total # of tokens processed


def run_epoch(
    data_iter,
    model,
    loss_compute,
    optimizer,
    scheduler,
    mode="train",
    accum_iter=1,
    train_state=TrainState(),
):
    """Train a single epoch"""
    start = time.time()
    total_tokens = 0
    total_loss = 0
    tokens = 0
    n_accum = 0
    for i, batch in enumerate(data_iter):
        out = model.forward(
            batch.src, batch.tgt, batch.src_mask, batch.tgt_mask
        )
        loss, loss_node = loss_compute(out, batch.tgt_y, batch.ntokens)
        # loss_node = loss_node / accum_iter
        if mode == "train" or mode == "train+log":
            loss_node.backward()
            train_state.step += 1
            train_state.samples += batch.src.shape[0]
            train_state.tokens += batch.ntokens
            if i % accum_iter == 0:
                optimizer.step()
                optimizer.zero_grad(set_to_none=True)
                n_accum += 1
                train_state.accum_step += 1
            scheduler.step()

        total_loss += loss
        total_tokens += batch.ntokens
        tokens += batch.ntokens
        if i % 40 == 1 and (mode == "train" or mode == "train+log"):
            lr = optimizer.param_groups[0]["lr"]
            elapsed = time.time() - start
            print(
                (
                    "Epoch Step: %6d | Accumulation Step: %3d | Loss: %6.2f "
                    + "| Tokens / Sec: %7.1f | Learning Rate: %6.1e"
                )
                % (i, n_accum, loss / batch.ntokens, tokens / elapsed, lr)
            )
            start = time.time()
            tokens = 0
        del loss
        del loss_node
    return total_loss / total_tokens, train_state


def rate(step, model_size, factor, warmup):
    """
    we have to default the step to 1 for LambdaLR function
    to avoid zero raising to negative power.
    """
    if step == 0:
        step = 1
    return factor * (
        model_size ** (-0.5) * min(step ** (-0.5), step * warmup ** (-1.5))
    )


def example_learning_schedule():
    opts = [
        [512, 1, 4000],  # example 1
        [512, 1, 8000],  # example 2
        [256, 1, 4000],  # example 3
    ]

    dummy_model = torch.nn.Linear(1, 1)
    learning_rates = []

    # we have 3 examples in opts list.
    for idx, example in enumerate(opts):
        # run 20000 epoch for each example
        optimizer = torch.optim.Adam(
            dummy_model.parameters(), lr=1, betas=(0.9, 0.98), eps=1e-9
        )
        lr_scheduler = LambdaLR(
            optimizer=optimizer, lr_lambda=lambda step: rate(step, *example)
        )
        tmp = []
        # take 20K dummy training steps, save the learning rate at each step
        for step in range(20000):
            tmp.append(optimizer.param_groups[0]["lr"])
            optimizer.step()
            lr_scheduler.step()
        learning_rates.append(tmp)

    learning_rates = torch.tensor(learning_rates)

    # Enable altair to handle more than 5000 rows
    alt.data_transformers.disable_max_rows()

    opts_data = pd.concat(
        [
            pd.DataFrame(
                {
                    "Learning Rate": learning_rates[warmup_idx, :],
                    "model_size:warmup": ["512:4000", "512:8000", "256:4000"][
                        warmup_idx
                    ],
                    "step": range(20000),
                }
            )
            for warmup_idx in [0, 1, 2]
        ]
    )

    return (
        alt.Chart(opts_data)
        .mark_line()
        .properties(width=600)
        .encode(x="step", y="Learning Rate", color="model_size:warmup:N")
        .interactive()
    )


# example_learning_schedule()


class LabelSmoothing(nn.Module):
    "Implement label smoothing."

    def __init__(self, size, padding_idx, smoothing=0.0):
        super(LabelSmoothing, self).__init__()
        self.criterion = nn.KLDivLoss(reduction="sum")
        self.padding_idx = padding_idx
        self.confidence = 1.0 - smoothing
        self.smoothing = smoothing
        self.size = size
        self.true_dist = None

    def forward(self, x, target):
        assert x.size(1) == self.size
        true_dist = x.data.clone()
        true_dist.fill_(self.smoothing / (self.size - 2))
        true_dist.scatter_(1, target.data.unsqueeze(1), self.confidence)
        true_dist[:, self.padding_idx] = 0
        mask = torch.nonzero(target.data == self.padding_idx)
        if mask.dim() > 0:
            true_dist.index_fill_(0, mask.squeeze(), 0.0)
        self.true_dist = true_dist
        return self.criterion(x, true_dist.clone().detach())


class SimpleLossCompute:
    "A simple loss compute and train function."

    def __init__(self, generator, criterion):
        self.generator = generator
        self.criterion = criterion

    def __call__(self, x, y, norm):
        x = self.generator(x)
        sloss = (
            self.criterion(
                x.contiguous().view(-1, x.size(-1)), y.contiguous().view(-1)
            )
            / norm
        )
        return sloss.data * norm, sloss


def greedy_decode(model, src, src_mask, max_len, start_symbol):
    memory = model.encode(src, src_mask)
    ys = torch.zeros(1, 1).fill_(start_symbol).type_as(src.data)
    for i in range(max_len - 1):
        out = model.decode(
            memory, src_mask, ys, subsequent_mask(ys.size(1)).type_as(src.data)
        )
        prob = model.generator(out[:, -1])
        _, next_word = torch.max(prob, dim=1)
        next_word = next_word.data[0]
        ys = torch.cat(
            [ys, torch.zeros(1, 1).type_as(src.data).fill_(next_word)], dim=1
        )
    return ys


def example_label_smoothing():
    crit = LabelSmoothing(5, 0, 0.4)
    predict = torch.FloatTensor(
        [
            [0, 0.2, 0.7, 0.1, 0],
            [0, 0.2, 0.7, 0.1, 0],
            [0, 0.2, 0.7, 0.1, 0],
            [0, 0.2, 0.7, 0.1, 0],
            [0, 0.2, 0.7, 0.1, 0],
        ]
    )
    crit(x=predict.log(), target=torch.LongTensor([2, 1, 0, 3, 3]))
    LS_data = pd.concat(
        [
            pd.DataFrame(
                {
                    "target distribution": crit.true_dist[x, y].flatten(),
                    "columns": y,
                    "rows": x,
                }
            )
            for y in range(5)
            for x in range(5)
        ]
    )

    return (
        alt.Chart(LS_data)
        .mark_rect(color="Blue", opacity=1)
        .properties(height=200, width=200)
        .encode(
            alt.X("columns:O", title=None),
            alt.Y("rows:O", title=None),
            alt.Color(
                "target distribution:Q", scale=alt.Scale(scheme="viridis")
            ),
        )
        .interactive()
    )


# show_example(example_label_smoothing)

def loss(x, crit):
    d = x + 3 * 1
    predict = torch.FloatTensor([[0, x / d, 1 / d, 1 / d, 1 / d]])
    return crit(predict.log(), torch.LongTensor([1])).data


def penalization_visualization():
    crit = LabelSmoothing(5, 0, 0.1)
    loss_data = pd.DataFrame(
        {
            "Loss": [loss(x, crit) for x in range(1, 100)],
            "Steps": list(range(99)),
        }
    ).astype("float")

    return (
        alt.Chart(loss_data)
        .mark_line()
        .properties(width=350)
        .encode(
            x="Steps",
            y="Loss",
        )
        .interactive()
    )


# show_example(penalization_visualization)


def data_gen(V, batch_size, nbatches):
    "Generate random data for a src-tgt copy task."
    for i in range(nbatches):
        data = torch.randint(1, V, size=(batch_size, 10))
        data[:, 0] = 1
        src = data.requires_grad_(False).clone().detach()
        tgt = data.requires_grad_(False).clone().detach()
        yield Batch(src, tgt, 0)


def example_simple_model():
    V = 11
    criterion = LabelSmoothing(size=V, padding_idx=0, smoothing=0.0)
    model = make_model(V, V, N=2)

    optimizer = torch.optim.Adam(
        model.parameters(), lr=0.5, betas=(0.9, 0.98), eps=1e-9
    )
    lr_scheduler = LambdaLR(
        optimizer=optimizer,
        lr_lambda=lambda step: rate(
            step, model_size=model.src_embed[0].d_model, factor=1.0, warmup=400
        ),
    )

    batch_size = 80
    for epoch in range(20):
        model.train()
        run_epoch(
            data_gen(V, batch_size, 20),
            model,
            SimpleLossCompute(model.generator, criterion),
            optimizer,
            lr_scheduler,
            mode="train",
        )
        model.eval()
        run_epoch(
            data_gen(V, batch_size, 5),
            model,
            SimpleLossCompute(model.generator, criterion),
            DummyOptimizer(),
            DummyScheduler(),
            mode="eval",
        )[0]

    model.eval()
    src = torch.LongTensor([[0, 1, 2, 3, 4, 5, 6, 7, 8, 9]])
    max_len = src.shape[1]
    src_mask = torch.ones(1, 1, max_len)
    print(greedy_decode(model, src, src_mask, max_len=max_len, start_symbol=0))


# execute_example(example_simple_model)


def load_tokenizers():

    try:
        spacy_de = spacy.load("de_core_news_sm")
    except IOError:
        os.system("python -m spacy download de_core_news_sm")
        spacy_de = spacy.load("de_core_news_sm")

    try:
        spacy_en = spacy.load("en_core_web_sm")
    except IOError:
        os.system("python -m spacy download en_core_web_sm")
        spacy_en = spacy.load("en_core_web_sm")

    return spacy_de, spacy_en


def tokenize(text, tokenizer):
    return [tok.text for tok in tokenizer.tokenizer(text)]


def yield_tokens(data_iter, tokenizer, index):
    for from_to_tuple in data_iter:
        yield tokenizer(from_to_tuple[index])


def build_vocabulary(spacy_de, spacy_en):
    def tokenize_de(text):
        return tokenize(text, spacy_de)

    def tokenize_en(text):
        return tokenize(text, spacy_en)

    print("Building German Vocabulary ...")
    train, val, test = datasets.Multi30k(language_pair=("de", "en"))
    vocab_src = build_vocab_from_iterator(
        yield_tokens(train + val + test, tokenize_de, index=0),
        min_freq=2,
        specials=["<s>", "</s>", "<blank>", "<unk>"],
    )

    print("Building English Vocabulary ...")
    train, val, test = datasets.Multi30k(language_pair=("de", "en"))
    vocab_tgt = build_vocab_from_iterator(
        yield_tokens(train + val + test, tokenize_en, index=1),
        min_freq=2,
        specials=["<s>", "</s>", "<blank>", "<unk>"],
    )

    vocab_src.set_default_index(vocab_src["<unk>"])
    vocab_tgt.set_default_index(vocab_tgt["<unk>"])

    return vocab_src, vocab_tgt


def load_vocab(spacy_de, spacy_en):
    if not exists("vocab.pt"):
        vocab_src, vocab_tgt = build_vocabulary(spacy_de, spacy_en)
        torch.save((vocab_src, vocab_tgt), "vocab.pt")
    else:
        vocab_src, vocab_tgt = torch.load("vocab.pt")
    print("Finished.\nVocabulary sizes:")
    print(len(vocab_src))
    print(len(vocab_tgt))
    return vocab_src, vocab_tgt


if is_interactive_notebook():
    # global variables used later in the script
    spacy_de, spacy_en = show_example(load_tokenizers)
    vocab_src, vocab_tgt = show_example(load_vocab, args=[spacy_de, spacy_en])


def collate_batch(
    batch,
    src_pipeline,
    tgt_pipeline,
    src_vocab,
    tgt_vocab,
    device,
    max_padding=128,
    pad_id=2,
):
    bs_id = torch.tensor([0], device=device)  # <s> token id
    eos_id = torch.tensor([1], device=device)  # </s> token id
    src_list, tgt_list = [], []
    for (_src, _tgt) in batch:
        processed_src = torch.cat(
            [
                bs_id,
                torch.tensor(
                    src_vocab(src_pipeline(_src)),
                    dtype=torch.int64,
                    device=device,
                ),
                eos_id,
            ],
            0,
        )
        processed_tgt = torch.cat(
            [
                bs_id,
                torch.tensor(
                    tgt_vocab(tgt_pipeline(_tgt)),
                    dtype=torch.int64,
                    device=device,
                ),
                eos_id,
            ],
            0,
        )
        src_list.append(
            # warning - overwrites values for negative values of padding - len
            pad(
                processed_src,
                (
                    0,
                    max_padding - len(processed_src),
                ),
                value=pad_id,
            )
        )
        tgt_list.append(
            pad(
                processed_tgt,
                (0, max_padding - len(processed_tgt)),
                value=pad_id,
            )
        )

    src = torch.stack(src_list)
    tgt = torch.stack(tgt_list)
    return (src, tgt)


def create_dataloaders(
    device,
    vocab_src,
    vocab_tgt,
    spacy_de,
    spacy_en,
    batch_size=12000,
    max_padding=128,
    is_distributed=True,
):
    # def create_dataloaders(batch_size=12000):
    def tokenize_de(text):
        return tokenize(text, spacy_de)

    def tokenize_en(text):
        return tokenize(text, spacy_en)

    def collate_fn(batch):
        return collate_batch(
            batch,
            tokenize_de,
            tokenize_en,
            vocab_src,
            vocab_tgt,
            device,
            max_padding=max_padding,
            pad_id=vocab_src.get_stoi()["<blank>"],
        )

    train_iter, valid_iter, test_iter = datasets.Multi30k(
        language_pair=("de", "en")
    )

    train_iter_map = to_map_style_dataset(
        train_iter
    )  # DistributedSampler needs a dataset len()
    train_sampler = (
        DistributedSampler(train_iter_map) if is_distributed else None
    )
    valid_iter_map = to_map_style_dataset(valid_iter)
    valid_sampler = (
        DistributedSampler(valid_iter_map) if is_distributed else None
    )

    train_dataloader = DataLoader(
        train_iter_map,
        batch_size=batch_size,
        shuffle=(train_sampler is None),
        sampler=train_sampler,
        collate_fn=collate_fn,
    )
    valid_dataloader = DataLoader(
        valid_iter_map,
        batch_size=batch_size,
        shuffle=(valid_sampler is None),
        sampler=valid_sampler,
        collate_fn=collate_fn,
    )
    return train_dataloader, valid_dataloader


def train_worker(
    gpu,
    ngpus_per_node,
    vocab_src,
    vocab_tgt,
    spacy_de,
    spacy_en,
    config,
    is_distributed=False,
):
    print(f"Train worker process using GPU: {gpu} for training", flush=True)
    torch.cuda.set_device(gpu)

    pad_idx = vocab_tgt["<blank>"]
    d_model = 512
    model = make_model(len(vocab_src), len(vocab_tgt), N=6)
    model.cuda(gpu)
    module = model
    is_main_process = True
    if is_distributed:
        dist.init_process_group(
            "nccl", init_method="env://", rank=gpu, world_size=ngpus_per_node
        )
        model = DDP(model, device_ids=[gpu])
        module = model.module
        is_main_process = gpu == 0

    criterion = LabelSmoothing(
        size=len(vocab_tgt), padding_idx=pad_idx, smoothing=0.1
    )
    criterion.cuda(gpu)

    train_dataloader, valid_dataloader = create_dataloaders(
        gpu,
        vocab_src,
        vocab_tgt,
        spacy_de,
        spacy_en,
        batch_size=config["batch_size"] // ngpus_per_node,
        max_padding=config["max_padding"],
        is_distributed=is_distributed,
    )

    optimizer = torch.optim.Adam(
        model.parameters(), lr=config["base_lr"], betas=(0.9, 0.98), eps=1e-9
    )
    lr_scheduler = LambdaLR(
        optimizer=optimizer,
        lr_lambda=lambda step: rate(
            step, d_model, factor=1, warmup=config["warmup"]
        ),
    )
    train_state = TrainState()

    for epoch in range(config["num_epochs"]):
        if is_distributed:
            train_dataloader.sampler.set_epoch(epoch)
            valid_dataloader.sampler.set_epoch(epoch)

        model.train()
        print(f"[GPU{gpu}] Epoch {epoch} Training ====", flush=True)
        _, train_state = run_epoch(
            (Batch(b[0], b[1], pad_idx) for b in train_dataloader),
            model,
            SimpleLossCompute(module.generator, criterion),
            optimizer,
            lr_scheduler,
            mode="train+log",
            accum_iter=config["accum_iter"],
            train_state=train_state,
        )

        GPUtil.showUtilization()
        if is_main_process:
            file_path = "%s%.2d.pt" % (config["file_prefix"], epoch)
            torch.save(module.state_dict(), file_path)
        torch.cuda.empty_cache()

        print(f"[GPU{gpu}] Epoch {epoch} Validation ====", flush=True)
        model.eval()
        sloss = run_epoch(
            (Batch(b[0], b[1], pad_idx) for b in valid_dataloader),
            model,
            SimpleLossCompute(module.generator, criterion),
            DummyOptimizer(),
            DummyScheduler(),
            mode="eval",
        )
        print(sloss)
        torch.cuda.empty_cache()

    if is_main_process:
        file_path = "%sfinal.pt" % config["file_prefix"]
        torch.save(module.state_dict(), file_path)


def train_worker(
    gpu,
    ngpus_per_node,
    vocab_src,
    vocab_tgt,
    spacy_de,
    spacy_en,
    config,
    is_distributed=False,
):
    print(f"Train worker process using GPU: {gpu} for training", flush=True)
    torch.cuda.set_device(gpu)

    pad_idx = vocab_tgt["<blank>"]
    d_model = 512
    model = make_model(len(vocab_src), len(vocab_tgt), N=6)
    model.cuda(gpu)
    module = model
    is_main_process = True
    if is_distributed:
        dist.init_process_group(
            "nccl", init_method="env://", rank=gpu, world_size=ngpus_per_node
        )
        model = DDP(model, device_ids=[gpu])
        module = model.module
        is_main_process = gpu == 0

    criterion = LabelSmoothing(
        size=len(vocab_tgt), padding_idx=pad_idx, smoothing=0.1
    )
    criterion.cuda(gpu)

    train_dataloader, valid_dataloader = create_dataloaders(
        gpu,
        vocab_src,
        vocab_tgt,
        spacy_de,
        spacy_en,
        batch_size=config["batch_size"] // ngpus_per_node,
        max_padding=config["max_padding"],
        is_distributed=is_distributed,
    )

    optimizer = torch.optim.Adam(
        model.parameters(), lr=config["base_lr"], betas=(0.9, 0.98), eps=1e-9
    )
    lr_scheduler = LambdaLR(
        optimizer=optimizer,
        lr_lambda=lambda step: rate(
            step, d_model, factor=1, warmup=config["warmup"]
        ),
    )
    train_state = TrainState()

    for epoch in range(config["num_epochs"]):
        if is_distributed:
            train_dataloader.sampler.set_epoch(epoch)
            valid_dataloader.sampler.set_epoch(epoch)

        model.train()
        print(f"[GPU{gpu}] Epoch {epoch} Training ====", flush=True)
        _, train_state = run_epoch(
            (Batch(b[0], b[1], pad_idx) for b in train_dataloader),
            model,
            SimpleLossCompute(module.generator, criterion),
            optimizer,
            lr_scheduler,
            mode="train+log",
            accum_iter=config["accum_iter"],
            train_state=train_state,
        )

        GPUtil.showUtilization()
        if is_main_process:
            file_path = "%s%.2d.pt" % (config["file_prefix"], epoch)
            torch.save(module.state_dict(), file_path)
        torch.cuda.empty_cache()

        print(f"[GPU{gpu}] Epoch {epoch} Validation ====", flush=True)
        model.eval()
        sloss = run_epoch(
            (Batch(b[0], b[1], pad_idx) for b in valid_dataloader),
            model,
            SimpleLossCompute(module.generator, criterion),
            DummyOptimizer(),
            DummyScheduler(),
            mode="eval",
        )
        print(sloss)
        torch.cuda.empty_cache()

    if is_main_process:
        file_path = "%sfinal.pt" % config["file_prefix"]
        torch.save(module.state_dict(), file_path)


def train_distributed_model(vocab_src, vocab_tgt, spacy_de, spacy_en, config):
    ngpus = torch.cuda.device_count()
    os.environ["MASTER_ADDR"] = "localhost"
    os.environ["MASTER_PORT"] = "12356"
    print(f"Number of GPUs detected: {ngpus}")
    print("Spawning training processes ...")
    mp.spawn(
        train_worker,
        nprocs=ngpus,
        args=(ngpus, vocab_src, vocab_tgt, spacy_de, spacy_en, config, True),
    )


def train_model(vocab_src, vocab_tgt, spacy_de, spacy_en, config):
    if config["distributed"]:
        train_distributed_model(
            vocab_src, vocab_tgt, spacy_de, spacy_en, config
        )
    else:
        train_worker(
            0, 1, vocab_src, vocab_tgt, spacy_de, spacy_en, config, False
        )


def load_trained_model():
    config = {
        "batch_size": 32,
        "distributed": False,
        "num_epochs": 8,
        "accum_iter": 10,
        "base_lr": 1.0,
        "max_padding": 72,
        "warmup": 3000,
        "file_prefix": "multi30k_model_",
    }
    model_path = "multi30k_model_final.pt"
    if not exists(model_path):
        train_model(vocab_src, vocab_tgt, spacy_de, spacy_en, config)

    model = make_model(len(vocab_src), len(vocab_tgt), N=6)
    model.load_state_dict(torch.load("multi30k_model_final.pt"))
    return model


if is_interactive_notebook():
    model = load_trained_model()


def check_outputs(
    valid_dataloader,
    model,
    vocab_src,
    vocab_tgt,
    n_examples=15,
    pad_idx=2,
    eos_string="</s>",
):
    results = [()] * n_examples
    for idx in range(n_examples):
        print("\nExample %d ========\n" % idx)
        b = next(iter(valid_dataloader))
        rb = Batch(b[0], b[1], pad_idx)
        greedy_decode(model, rb.src, rb.src_mask, 64, 0)[0]

        src_tokens = [
            vocab_src.get_itos()[x] for x in rb.src[0] if x != pad_idx
        ]
        tgt_tokens = [
            vocab_tgt.get_itos()[x] for x in rb.tgt[0] if x != pad_idx
        ]

        print(
            "Source Text (Input)        : "
            + " ".join(src_tokens).replace("\n", "")
        )
        print(
            "Target Text (Ground Truth) : "
            + " ".join(tgt_tokens).replace("\n", "")
        )
        model_out = greedy_decode(model, rb.src, rb.src_mask, 72, 0)[0]
        model_txt = (
            " ".join(
                [vocab_tgt.get_itos()[x] for x in model_out if x != pad_idx]
            ).split(eos_string, 1)[0]
            + eos_string
        )
        print("Model Output               : " + model_txt.replace("\n", ""))
        results[idx] = (rb, src_tokens, tgt_tokens, model_out, model_txt)
    return results


def run_model_example(n_examples=5):
    global vocab_src, vocab_tgt, spacy_de, spacy_en

    print("Preparing Data ...")
    _, valid_dataloader = create_dataloaders(
        torch.device("cpu"),
        vocab_src,
        vocab_tgt,
        spacy_de,
        spacy_en,
        batch_size=1,
        is_distributed=False,
    )

    print("Loading Trained Model ...")

    model = make_model(len(vocab_src), len(vocab_tgt), N=6)
    model.load_state_dict(
        torch.load("multi30k_model_final.pt", map_location=torch.device("cpu"))
    )

    print("Checking Model Outputs:")
    example_data = check_outputs(
        valid_dataloader, model, vocab_src, vocab_tgt, n_examples=n_examples
    )
    return model, example_data


if __name__ == "__main__":
    # execute_example(example_simple_model)
    # spacy_de, spacy_en = show_example(load_tokenizers)
    # vocab_src, vocab_tgt = show_example(load_vocab, args=[spacy_de, spacy_en])
    # load_trained_model()
    execute_example(run_model_example)