Python，argparse命令行参数断言错误

如何解决Python，argparse命令行参数断言错误

我使用 argparse 的命令行参数返回 AssertionError。我有两个脚本和一个存储三个数据文件的目录。

脚本：

• main.py 负责加载数据
• data.py 对语言数据进行预处理

数据：

• 三个令牌存储在 C:\Users\archive 路径中

data.py 脚本

**#data.py**
import os
from io import open
import torch

class Dictionary(object):
    def __init__(self):
        self.word2idx = {}
        self.idx2word = []

    def add_word(self,word):
        if word not in self.word2idx:
            self.idx2word.append(word)
            self.word2idx[word] = len(self.idx2word) - 1
        return self.word2idx[word]

    def __len__(self):
        return len(self.idx2word)

class Corpus(object):
    def __init__(self,path):
        self.dictionary = Dictionary()
        self.train = self.tokenize(os.path.join(path,'train.txt'))
        self.valid = self.tokenize(os.path.join(path,'valid.txt'))
        self.test = self.tokenize(os.path.join(path,'test.txt'))

    def tokenize(self,path):
        """Tokenizes a text file."""
        assert os.path.exists(path)
        # Add words to the dictionary
        with open(path,'r',encoding="utf8") as f:
            for line in f:
                words = line.split() + ['<eos>']
                for word in words:
                    self.dictionary.add_word(word)

        # Tokenize file content
        with open(path,encoding="utf8") as f:
            idss = []
            for line in f:
                words = line.split() + ['<eos>']
                ids = []
                for word in words:
                    ids.append(self.dictionary.word2idx[word])
                idss.append(torch.tensor(ids).type(torch.int64))
            ids = torch.cat(idss)

        return ids

ma​​in.py 脚本

**#main.py**
import argparse
import time
import math
import os
import torch
import torch.nn as nn
import torch.onnx

import data

parser = argparse.ArgumentParser(description='PyTorch Wikitext-2 RNN/LSTM/GRU/Transformer Language Model')
parser.add_argument('--data',type=str,default='./data/wikitext-2',help='location of the data corpus')
parser.add_argument('--model',default='LSTM',help='type of recurrent net (RNN_TANH,RNN_RELU,LSTM,GRU,Transformer)')
parser.add_argument('--emsize',type=int,default=200,help='size of word embeddings')
parser.add_argument('--nhid',help='number of hidden units per layer')
parser.add_argument('--nlayers',default=2,help='number of layers')
parser.add_argument('--lr',type=float,default=20,help='initial learning rate')
parser.add_argument('--clip',default=0.25,help='gradient clipping')
parser.add_argument('--epochs',default=40,help='upper epoch limit')
parser.add_argument('--batch_size',Metavar='N',help='batch size')
parser.add_argument('--bptt',default=35,help='sequence length')
parser.add_argument('--dropout',default=0.2,help='dropout applied to layers (0 = no dropout)')
parser.add_argument('--tied',action='store_true',help='tie the word embedding and softmax weights')
parser.add_argument('--seed',default=1111,help='random seed')
parser.add_argument('--cuda',help='use CUDA')
parser.add_argument('--log-interval',help='report interval')
parser.add_argument('--save',default='model.pt',help='path to save the final model')
parser.add_argument('--onnx-export',default='',help='path to export the final model in onnx format')
parser.add_argument('--nhead',help='the number of heads in the encoder/decoder of the transformer model')
parser.add_argument('--dry-run',help='verify the code and the model')

args = parser.parse_args()

# Set the random seed manually for reproducibility.
torch.manual_seed(args.seed)
if torch.cuda.is_available():
    if not args.cuda:
        print("WARNING: You have a CUDA device,so you should probably run with --cuda")

device = torch.device("cuda" if args.cuda else "cpu")

###############################################################################
# Load data
###############################################################################

corpus = data.Corpus(args.data)

当我在终端中运行 main.py 时：

$ python main.py 

断言错误显示如下：

File "main.py",line 67,in <module>
    corpus = data.Corpus(args.data)
File "C:\Users\archive\data.py",line 22,in __init__
    self.train = self.tokenize(os.path.join(path,'train.txt'))
File "C:\Users\archive\data.py",line 28,in tokenize
    assert os.path.exists(path)
AssertionError