Kaggle免费GPU使用攻略

lyhue1991

发布于 2023-02-23 04:03:56

5.1K00

代码可运行

文章被收录于专栏：Python与算法之美Python与算法之美

运行总次数：0

代码可运行

公众号后台回复关键词：gpu，获取B站视频演示教程。

一，注册Kaggle

在国内使用邮箱注册kaggle时会遇到一个人机验证的步骤，可以通过翻墙访问外网的方式完成，但比较麻烦。

推荐使用FireFox浏览器，下载Header Editor进行解决，无需翻墙相对简单。

1，下载安装FireFox浏览器

2，添加Header Editor浏览器插件【找到FireFox浏览器的工具 -> 扩展和主题 —> 搜索 Header Editor -> 添加到FireFox】

3，配置Header Editor插件【找到FireFox右上角Header Editor -> 导出和导入 -> 下载规则中输入如下规则url -> 点击向下箭头加载】

规则url: https://azurezeng.github.io/static/HE-GoogleRedirect.json

4，在kaggle官网用邮箱正常注册kaggle即可。

kaggle官网：https://www.kaggle.com/

5，此后就可以在任何能联网的地方正常登录kaggle，不再需要Header Editor了

二，设置GPU

1，新建notebook. 【点击kaggle主页面左上角+, 选择notebook】

2，开启GPU开关。【点击展开notebook右上角 |< 设置，设置Accelerator为GPU 】

3，查看GPU信息。【NoteBook中使用 nvidia-smi查看】

!nvidia-smi

import torch 
torch.cuda.is_available()

三，上传数据

1，点击展开notebook右上角 |< 设置，找到 Add Data，可以从Kaggle社区发布的数据集中选择一些想要的数据集。

2，也可以选在代表上传的向上箭头，上传数据集文件作为自定义数据集。建议压缩后上传，传输效率较高。

3，此外，也可以通过把数据放在github项目中，用git clone的方式获取。

4，notebook加载进来数据集后，可以在右边数据文件位置点击获取对应路径。

公众号 算法美食屋 回复关键词：pytorch，获取本范例所用数据集eat_pytorch_datasets百度云盘下载链接。

四，CPU训练代码

约14s一个Epoch

import torch 
from torch import nn
from torch.utils.data import Dataset,DataLoader
from torchvision import transforms as T
from torchvision import datasets 


#======================================================================
# 一，准备数据
#======================================================================

transform_img = T.Compose(
    [T.ToTensor()])

def transform_label(x):
    return torch.tensor(x)

ds_train = datasets.ImageFolder("../input/eat-pytorch-datasets/eat_pytorch_datasets/cifar2/train/",
            transform = transform_img,target_transform = transform_label)
ds_val = datasets.ImageFolder("../input/eat-pytorch-datasets/eat_pytorch_datasets/cifar2/test/",
            transform = transform_img,target_transform = transform_label)
print(ds_train.class_to_idx)

dl_train = DataLoader(ds_train,batch_size = 50,shuffle = True, pin_memory=True, num_workers = 8)
dl_val = DataLoader(ds_val,batch_size = 50,shuffle = False, pin_memory=True, num_workers = 8)


%matplotlib inline
%config InlineBackend.figure_format = 'svg'

#查看部分样本
from matplotlib import pyplot as plt 

plt.figure(figsize=(8,8)) 
for i in range(9):
    img,label = ds_train[i]
    img = img.permute(1,2,0) 
    ax=plt.subplot(3,3,i+1)
    ax.imshow(img.numpy())
    ax.set_title("label = %d"%label.item())
    ax.set_xticks([])
    ax.set_yticks([]) 
plt.show()

# Pytorch的图片默认顺序是 Batch,Channel,Width,Height
for features,labels in dl_train:
    print(features.shape,labels.shape) 
    break
    
    
    

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

class Net(nn.Module):
    
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(in_channels=3,out_channels=32,kernel_size = 3)
        self.pool = nn.MaxPool2d(kernel_size = 2,stride = 2)
        self.conv2 = nn.Conv2d(in_channels=32,out_channels=64,kernel_size = 5)
        self.dropout = nn.Dropout2d(p = 0.1)
        self.adaptive_pool = nn.AdaptiveMaxPool2d((1,1))
        self.flatten = nn.Flatten()
        self.linear1 = nn.Linear(64,32)
        self.relu = nn.ReLU()
        self.linear2 = nn.Linear(32,2)
        
    def forward(self,x):
        x = self.conv1(x)
        x = self.pool(x)
        x = self.conv2(x)
        x = self.pool(x)
        x = self.dropout(x)
        x = self.adaptive_pool(x)
        x = self.flatten(x)
        x = self.linear1(x)
        x = self.relu(x)
        x = self.linear2(x)
        return x 
        
net = Net()
print(net)




#======================================================================
# 三，训练模型(CPU)
#======================================================================


import os,sys,time
import numpy as np
import pandas as pd
import datetime 
from tqdm import tqdm 

import torch
from torch import nn 
from copy import deepcopy
from torchmetrics import Accuracy
#注：多分类使用torchmetrics中的评估指标，二分类使用torchkeras.metrics中的评估指标

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

net = Net()

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

epochs = 5 
ckpt_path='checkpoint.pt'

#early_stopping相关设置
monitor="val_acc"
patience=3
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))
    train_metrics_dict = deepcopy(metrics_dict) 
    
    for i, batch in loop: 
        
        features,labels = batch
        #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))
    
    val_metrics_dict = deepcopy(metrics_dict) 
    
    with torch.no_grad():
        for i, batch in loop: 

            features,labels = batch
            
            #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)

五，GPU训练代码

约8s一个Epoch.

import torch 
from torch import nn
from torch.utils.data import Dataset,DataLoader
from torchvision import transforms as T
from torchvision import datasets 


#======================================================================
# 一，准备数据
#======================================================================

transform_img = T.Compose(
    [T.ToTensor()])

def transform_label(x):
    return torch.tensor(x)

ds_train = datasets.ImageFolder("../input/eat-pytorch-datasets/eat_pytorch_datasets/cifar2/train/",
            transform = transform_img,target_transform = transform_label)
ds_val = datasets.ImageFolder("../input/eat-pytorch-datasets/eat_pytorch_datasets/cifar2/test/",
            transform = transform_img,target_transform = transform_label)
print(ds_train.class_to_idx)

dl_train = DataLoader(ds_train,batch_size = 50,shuffle = True, pin_memory=True, num_workers = 8)
dl_val = DataLoader(ds_val,batch_size = 50,shuffle = False, pin_memory=True, num_workers = 8)



%matplotlib inline
%config InlineBackend.figure_format = 'svg'

#查看部分样本
from matplotlib import pyplot as plt 

plt.figure(figsize=(8,8)) 
for i in range(9):
    img,label = ds_train[i]
    img = img.permute(1,2,0) 
    ax=plt.subplot(3,3,i+1)
    ax.imshow(img.numpy())
    ax.set_title("label = %d"%label.item())
    ax.set_xticks([])
    ax.set_yticks([]) 
plt.show()

# Pytorch的图片默认顺序是 Batch,Channel,Width,Height
for features,labels in dl_train:
    print(features.shape,labels.shape) 
    break
    
    
    

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

class Net(nn.Module):
    
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(in_channels=3,out_channels=32,kernel_size = 3)
        self.pool = nn.MaxPool2d(kernel_size = 2,stride = 2)
        self.conv2 = nn.Conv2d(in_channels=32,out_channels=64,kernel_size = 5)
        self.dropout = nn.Dropout2d(p = 0.1)
        self.adaptive_pool = nn.AdaptiveMaxPool2d((1,1))
        self.flatten = nn.Flatten()
        self.linear1 = nn.Linear(64,32)
        self.relu = nn.ReLU()
        self.linear2 = nn.Linear(32,2)
        
    def forward(self,x):
        x = self.conv1(x)
        x = self.pool(x)
        x = self.conv2(x)
        x = self.pool(x)
        x = self.dropout(x)
        x = self.adaptive_pool(x)
        x = self.flatten(x)
        x = self.linear1(x)
        x = self.relu(x)
        x = self.linear2(x)
        return x 
        
net = Net()
print(net)




#======================================================================
# 三，训练模型(CPU)
#======================================================================


import os,sys,time
import numpy as np
import pandas as pd
import datetime 
from tqdm import tqdm 

import torch
from torch import nn 
from copy import deepcopy
from torchmetrics import Accuracy
#注：多分类使用torchmetrics中的评估指标，二分类使用torchkeras.metrics中的评估指标

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

net = Net()

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


#------------------------------移动模型到GPU上------------------------------
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
net.to(device)
loss_fn.to(device)
for name,fn in metrics_dict.items():
    fn.to(device)
#-------------------------------------------------------------------------


epochs = 5
ckpt_path='checkpoint.pt'

#early_stopping相关设置
monitor="val_acc"
patience=3
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))
    train_metrics_dict = deepcopy(metrics_dict) 
    
    for i, batch in loop: 
        
        features,labels = batch
        
        #------------------------------移动数据到GPU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))
    
    val_metrics_dict = deepcopy(metrics_dict) 
    
    with torch.no_grad():
        for i, batch in loop: 

            features,labels = batch
            
            #------------------------------移动数据到GPU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)