`RuntimeError：DataLoader workerpids11343，11344意外退出了`

问题描述

https://github.com/python-engineer/pytorch-chatbot#usage

import numpy as np
import random
import json

import torch
import torch.nn as nn
from torch.utils.data import Dataset,DataLoader

from nltk_utils import bag_of_words,tokenize,stem
from model import NeuralNet

with open('intents.json','r') as f:
    intents = json.load(f)

all_words = []
tags = []
xy = []
# loop through each sentence in our intents patterns
for intent in intents['intents']:
    tag = intent['tag']
    # add to tag list
    tags.append(tag)
    for pattern in intent['patterns']:
        # tokenize each word in the sentence
        w = tokenize(pattern)
        # add to our words list
        all_words.extend(w)
        # add to xy pair
        xy.append((w,tag))

# stem and lower each word
ignore_words = ['?','.','!']
all_words = [stem(w) for w in all_words if w not in ignore_words]
# remove duplicates and sort
all_words = sorted(set(all_words))
tags = sorted(set(tags))

print(len(xy),"patterns")
print(len(tags),"tags:",tags)
print(len(all_words),"unique stemmed words:",all_words)

# create training data
X_train = []
y_train = []
for (pattern_sentence,tag) in xy:
    # X: bag of words for each pattern_sentence
    bag = bag_of_words(pattern_sentence,all_words)
    X_train.append(bag)
    # y: PyTorch CrossEntropyLoss needs only class labels,not one-hot
    label = tags.index(tag)
    y_train.append(label)

X_train = np.array(X_train)
y_train = np.array(y_train)

# Hyper-parameters 
num_epochs = 1000
batch_size = 8
learning_rate = 0.001
input_size = len(X_train[0])
hidden_size = 8
output_size = len(tags)
print(input_size,output_size)

class ChatDataset(Dataset):

    def __init__(self):
        self.n_samples = len(X_train)
        self.x_data = X_train
        self.y_data = y_train

    # support indexing such that dataset[i] can be used to get i-th sample
    def __getitem__(self,index):
        return self.x_data[index],self.y_data[index]

    # we can call len(dataset) to return the size
    def __len__(self):
        return self.n_samples

dataset = ChatDataset()
train_loader = DataLoader(dataset=dataset,batch_size=batch_size,shuffle=True,num_workers=2)

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

model = NeuralNet(input_size,hidden_size,output_size).to(device)

# Loss and optimizer
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(),lr=learning_rate)

# Train the model
for epoch in range(num_epochs):
    for (words,labels) in train_loader:
        words = words.to(device)
        labels = labels.to(device)
        
        # Forward pass
        outputs = model(words)
        # if y would be one-hot,we must apply
        # labels = torch.max(labels,1)[1]
        loss = criterion(outputs,labels)
        
        # Backward and optimize
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()
        
    if (epoch+1) % 100 == 0:
        print (f'Epoch [{epoch+1}/{num_epochs}],Loss: {loss.item():.4f}')


print(f'final loss: {loss.item():.4f}')

data = {
"model_state": model.state_dict(),"input_size": input_size,"hidden_size": hidden_size,"output_size": output_size,"all_words": all_words,"tags": tags
}

FILE = "data.pth"
torch.save(data,FILE)

print(f'training complete. file saved to {FILE}')

当我运行train.py文件时（向上）

RuntimeError: DataLoader worker (pid (s) 11343,11344) exited unexpectedly

我遇到错误。

train.py之后，我需要运行chat.py文件。但是，当我运行chat.py文件时，出现以下错误。

FileNotFoundError: [Errno 2] No such file or directory: 'data.pth'

首先，有人知道我在train.py上遇到此错误的原因吗？如果您有帮助，我会很高兴。

解决方法

暂无找到可以解决该程序问题的有效方法，小编努力寻找整理中！

如果你已经找到好的解决方法，欢迎将解决方案带上本链接一起发送给小编。

小编邮箱:dio#foxmail.com (将#修改为@）