raise RuntimeError(f‘DataLoader worker (pid(s) {pids_str}) exited unexpectedly‘) from e Runtime

Mac M1 Pytorch 测试

最近新入手了一个二手的macbook air m1
准备测试一下m1应对机器学习的能力
找到一位老哥的文章以及代码进行测试：
https://blog.csdn.net/KaelCui/article/details/106184158

问题描述

运行范例代码之后出现如下错误提示：
raise RuntimeError(f’DataLoader worker (pid(s) {pids_str}) exited unexpectedly’) from e RuntimeError: DataLoader worker (pid(s) 57383) exited unexpectedly

范例代码如下

import torch 
from torch import nn 
import torchvision 
from torchvision import transforms 
import torch.nn.functional as F 


import os,sys,time
import numpy as np
import pandas as pd
import datetime 
from tqdm import tqdm 
from copy import deepcopy
from torchmetrics import Accuracy


def printlog(info):
    nowtime = datetime.datetime.now().strftime('%Y-%m-%d %H:%M:%S')
    print("\n"+"=========="*8 + "%s"%nowtime)
    print(str(info)+"\n")
    
    
#================================================================================
# 一，准备数据
#================================================================================

transform = transforms.Compose([transforms.ToTensor()])

ds_train = torchvision.datasets.MNIST(root="mnist/",train=True,download=True,transform=transform)
ds_val = torchvision.datasets.MNIST(root="mnist/",train=False,download=True,transform=transform)

dl_train =  torch.utils.data.DataLoader(ds_train, batch_size=128, shuffle=True, num_workers=2)
dl_val =  torch.utils.data.DataLoader(ds_val, batch_size=128, shuffle=False, num_workers=2)


#================================================================================
# 二，定义模型
#================================================================================


def create_net():
    net = nn.Sequential()
    net.add_module("conv1",nn.Conv2d(in_channels=1,out_channels=64,kernel_size = 3))
    net.add_module("pool1",nn.MaxPool2d(kernel_size = 2,stride = 2))
    net.add_module("conv2",nn.Conv2d(in_channels=64,out_channels=512,kernel_size = 3))
    net.add_module("pool2",nn.MaxPool2d(kernel_size = 2,stride = 2))
    net.add_module("dropout",nn.Dropout2d(p = 0.1))
    net.add_module("adaptive_pool",nn.AdaptiveMaxPool2d((1,1)))
    net.add_module("flatten",nn.Flatten())
    net.add_module("linear1",nn.Linear(512,1024))
    net.add_module("relu",nn.ReLU())
    net.add_module("linear2",nn.Linear(1024,10))
    return net

net = create_net()
print(net)

# 评估指标
class Accuracy(nn.Module):
    def __init__(self):
        super().__init__()

        self.correct = nn.Parameter(torch.tensor(0.0),requires_grad=False)
        self.total = nn.Parameter(torch.tensor(0.0),requires_grad=False)

    def forward(self, preds: torch.Tensor, targets: torch.Tensor):
        preds = preds.argmax(dim=-1)
        m = (preds == targets).sum()
        n = targets.shape[0] 
        self.correct += m 
        self.total += n
        
        return m/n

    def compute(self):
        return self.correct.float() / self.total 
    
    def reset(self):
        self.correct -= self.correct
        self.total -= self.total
        
#================================================================================
# 三，训练模型
#================================================================================     

loss_fn = nn.CrossEntropyLoss()
optimizer= torch.optim.Adam(net.parameters(),lr = 0.01)   
metrics_dict = nn.ModuleDict({"acc":Accuracy()})


# =========================移动模型到mps上==============================
device = torch.device("mps" if torch.backends.mps.is_available() else "cpu")
net.to(device)
loss_fn.to(device)
metrics_dict.to(device)
# ====================================================================


epochs = 20 
ckpt_path='checkpoint.pt'

#early_stopping相关设置
monitor="val_acc"
patience=5
mode="max"

history = {}

for epoch in range(1, epochs+1):
    printlog("Epoch {0} / {1}".format(epoch, epochs))

    # 1，train -------------------------------------------------  
    net.train()
    
    total_loss,step = 0,0
    
    loop = tqdm(enumerate(dl_train), total =len(dl_train),ncols=100)
    train_metrics_dict = deepcopy(metrics_dict) 
    
    for i, batch in loop: 
        
        features,labels = batch
        
        # =========================移动数据到mps上==============================
        features = features.to(device)
        labels = labels.to(device)
        # ====================================================================
        
        #forward
        preds = net(features)
        loss = loss_fn(preds,labels)
        
        #backward
        loss.backward()
        optimizer.step()
        optimizer.zero_grad()
            
        #metrics
        step_metrics = {"train_"+name:metric_fn(preds, labels).item() 
                        for name,metric_fn in train_metrics_dict.items()}
        
        step_log = dict({"train_loss":loss.item()},**step_metrics)

        total_loss += loss.item()
        
        step+=1
        if i!=len(dl_train)-1:
            loop.set_postfix(**step_log)
        else:
            epoch_loss = total_loss/step
            epoch_metrics = {"train_"+name:metric_fn.compute().item() 
                             for name,metric_fn in train_metrics_dict.items()}
            epoch_log = dict({"train_loss":epoch_loss},**epoch_metrics)
            loop.set_postfix(**epoch_log)

            for name,metric_fn in train_metrics_dict.items():
                metric_fn.reset()
                
    for name, metric in epoch_log.items():
        history[name] = history.get(name, []) + [metric]
        

    # 2，validate -------------------------------------------------
    net.eval()
    
    total_loss,step = 0,0
    loop = tqdm(enumerate(dl_val), total =len(dl_val),ncols=100)
    
    val_metrics_dict = deepcopy(metrics_dict) 
    
    with torch.no_grad():
        for i, batch in loop: 

            features,labels = batch
            
            # =========================移动数据到mps上==============================
            features = features.to(device)
            labels = labels.to(device)
            # ====================================================================
            
            #forward
            preds = net(features)
            loss = loss_fn(preds,labels)

            #metrics
            step_metrics = {"val_"+name:metric_fn(preds, labels).item() 
                            for name,metric_fn in val_metrics_dict.items()}

            step_log = dict({"val_loss":loss.item()},**step_metrics)

            total_loss += loss.item()
            step+=1
            if i!=len(dl_val)-1:
                loop.set_postfix(**step_log)
            else:
                epoch_loss = (total_loss/step)
                epoch_metrics = {"val_"+name:metric_fn.compute().item() 
                                 for name,metric_fn in val_metrics_dict.items()}
                epoch_log = dict({"val_loss":epoch_loss},**epoch_metrics)
                loop.set_postfix(**epoch_log)

                for name,metric_fn in val_metrics_dict.items():
                    metric_fn.reset()
                    
    epoch_log["epoch"] = epoch           
    for name, metric in epoch_log.items():
        history[name] = history.get(name, []) + [metric]

    # 3，early-stopping -------------------------------------------------
    arr_scores = history[monitor]
    best_score_idx = np.argmax(arr_scores) if mode=="max" else np.argmin(arr_scores)
    if best_score_idx==len(arr_scores)-1:
        torch.save(net.state_dict(),ckpt_path)
        print("<<<<<< reach best {0} : {1} >>>>>>".format(monitor,
             arr_scores[best_score_idx]),file=sys.stderr)
    if len(arr_scores)-best_score_idx>patience:
        print("<<<<<< {} without improvement in {} epoch, early stopping >>>>>>".format(
            monitor,patience),file=sys.stderr)
        break 
    net.load_state_dict(torch.load(ckpt_path))
    
dfhistory = pd.DataFrame(history)


1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224

原因分析：

参考：https://blog.csdn.net/KaelCui/article/details/106184158

解决方案：

command+f 搜索 numworkers
发现两处numworkers = 2
删除即可