kaggle 競賽：手寫數字識別源代碼與相關總結

前言

第一次嘗試Kaggle，是經典的手寫數字識別的例子，其實這個MNIST數據集識別已經玩膩了，只不過這次是在Kaggle上，用他完成一整套的競賽流程，爲以後的大數據競賽做好準備，其實，對我而言，這次的MNIST數據集識別與平時的工作只有兩點不同，分別是在輸入和輸出方面。

重點

1、輸入是CSV文件，如何構建Pytorch數據集形式

2、輸出是標籤，如何轉爲CSV文件進行上傳

以上，接下來開始上代碼。

代碼：

1、導入包

import os
import time

import numpy as np
import pandas as pd

import torch
import torch.nn as nn
import torch.nn.functional as F
from torch.utils.data import DataLoader,TensorDataset

from torchvision import datasets
from torchvision import transforms

import matplotlib.pyplot as plt
from PIL import Image


if torch.cuda.is_available():
    torch.backends.cudnn.deterministic = True

2、超參數

##########################
### SETTINGS
##########################

# Hyperparameters
RANDOM_SEED = 1
LEARNING_RATE = 0.001
BATCH_SIZE = 128
NUM_EPOCHS = 10

# Architecture
NUM_FEATURES = 28*28
NUM_CLASSES = 10

# Other
DEVICE = "cpu"
GRAYSCALE = True

3、數據集建立

traindata_pd = pd.read_csv("./data/train.csv")
traindata_x_np = (traindata_pd.to_numpy()[:, 1:].reshape(-1, 1, 28, 28) / 255.0 - 0.5) / 0.5
traindata_y_np = traindata_pd.to_numpy()[:, 0].astype(int)
traindata_x_t = torch.from_numpy(traindata_x_np).float()
traindata_y_t = torch.from_numpy(traindata_y_np).long()
traindata = TensorDataset(traindata_x_t, traindata_y_t)

testdata_pd = pd.read_csv("./data/test.csv")
testdata_t = torch.from_numpy(((testdata_pd.to_numpy().reshape(-1, 1, 28, 28) / 255.0) - 0.5) / 0.5).float()
testdata = TensorDataset(testdata_t)

4、封裝成Dataloader

train_loader = DataLoader(dataset=traindata, 
                          batch_size=BATCH_SIZE, 
                          shuffle=True)

test_loader = DataLoader(dataset=testdata, 
                         batch_size=BATCH_SIZE, 
                         shuffle=False)
for images, labels in train_loader:  
    print('Image batch dimensions:', images.shape)
    print('Image label dimensions:', labels.shape)
    break
device = torch.device(DEVICE)
torch.manual_seed(0)

for epoch in range(2):

    for batch_idx, (x, y) in enumerate(train_loader):
        
        print('Epoch:', epoch+1, end='')
        print(' | Batch index:', batch_idx, end='')
        print(' | Batch size:', y.size()[0])
        
        x = x.to(device)
        y = y.to(device)
        break

5、模型搭建

##########################
### MODEL
##########################


def conv3x3(in_planes, out_planes, stride=1):
    """3x3 convolution with padding"""
    return nn.Conv2d(in_planes, out_planes, kernel_size=3, stride=stride,
                     padding=1, bias=False)


class BasicBlock(nn.Module):
    expansion = 1

    def __init__(self, inplanes, planes, stride=1, downsample=None):
        super(BasicBlock, self).__init__()
        self.conv1 = conv3x3(inplanes, planes, stride)
        self.bn1 = nn.BatchNorm2d(planes)
        self.relu = nn.ReLU(inplace=True)
        self.conv2 = conv3x3(planes, planes)
        self.bn2 = nn.BatchNorm2d(planes)
        self.downsample = downsample
        self.stride = stride

    def forward(self, x):
        residual = x

        out = self.conv1(x)
        out = self.bn1(out)
        out = self.relu(out)

        out = self.conv2(out)
        out = self.bn2(out)

        if self.downsample is not None:
            residual = self.downsample(x)

        out += residual
        out = self.relu(out)

        return out




class ResNet(nn.Module):

    def __init__(self, block, layers, num_classes, grayscale):
        self.inplanes = 64
        if grayscale:
            in_dim = 1
        else:
            in_dim = 3
        super(ResNet, self).__init__()
        self.conv1 = nn.Conv2d(in_dim, 64, kernel_size=7, stride=2, padding=3,
                               bias=False)
        self.bn1 = nn.BatchNorm2d(64)
        self.relu = nn.ReLU(inplace=True)
        self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
        self.layer1 = self._make_layer(block, 64, layers[0])
        self.layer2 = self._make_layer(block, 128, layers[1], stride=2)
        self.layer3 = self._make_layer(block, 256, layers[2], stride=2)
        self.layer4 = self._make_layer(block, 512, layers[3], stride=2)
        self.avgpool = nn.AvgPool2d(7, stride=1)
        self.fc = nn.Linear(512 * block.expansion, num_classes)

        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
                m.weight.data.normal_(0, (2. / n)**.5)
            elif isinstance(m, nn.BatchNorm2d):
                m.weight.data.fill_(1)
                m.bias.data.zero_()

    def _make_layer(self, block, planes, blocks, stride=1):
        downsample = None
        if stride != 1 or self.inplanes != planes * block.expansion:
            downsample = nn.Sequential(
                nn.Conv2d(self.inplanes, planes * block.expansion,
                          kernel_size=1, stride=stride, bias=False),
                nn.BatchNorm2d(planes * block.expansion),
            )

        layers = []
        layers.append(block(self.inplanes, planes, stride, downsample))
        self.inplanes = planes * block.expansion
        for i in range(1, blocks):
            layers.append(block(self.inplanes, planes))

        return nn.Sequential(*layers)

    def forward(self, x):
        x = self.conv1(x)
        x = self.bn1(x)
        x = self.relu(x)
        x = self.maxpool(x)

        x = self.layer1(x)
        x = self.layer2(x)
        x = self.layer3(x)
        x = self.layer4(x)
        # because MNIST is already 1x1 here:
        # disable avg pooling
        #x = self.avgpool(x)
        
        x = x.view(x.size(0), -1)
        logits = self.fc(x)
        probas = F.softmax(logits, dim=1)
        return logits, probas



def resnet34(num_classes):
    """Constructs a ResNet-34 model."""
    model = ResNet(block=BasicBlock, 
                   layers=[3, 4, 6, 3],
                   num_classes=NUM_CLASSES,
                   grayscale=GRAYSCALE)
    return model

6、訓練過程

torch.manual_seed(RANDOM_SEED)
model = resnet34(NUM_CLASSES)
model.to(DEVICE)

optimizer = torch.optim.Adam(model.parameters(), lr=LEARNING_RATE)  

def compute_accuracy(model, data_loader, device):
    correct_pred, num_examples = 0, 0
    for i, (features, targets) in enumerate(data_loader):
            
        features = features.to(device)
        targets = targets.to(device)

        logits, probas = model(features)
        _, predicted_labels = torch.max(probas, 1)
        num_examples += targets.size(0)
        correct_pred += (predicted_labels == targets).sum()
    return correct_pred.float()/num_examples * 100
    
cost_list = []
start_time = time.time()
for epoch in range(NUM_EPOCHS):
    
    model.train()
    for batch_idx, (features, targets) in enumerate(train_loader):
        
        features = features.to(DEVICE)
        targets = targets.to(DEVICE)
            
        ### FORWARD AND BACK PROP
        logits, probas = model(features)
        cost = F.cross_entropy(logits, targets)
        optimizer.zero_grad()
        
        cost.backward()
        
        ### UPDATE MODEL PARAMETERS
        optimizer.step()
        
        ### LOGGING
        if not batch_idx % 50:
            print ('Epoch: %03d/%03d | Batch %04d/%04d | Cost: %.4f' 
                   %(epoch+1, NUM_EPOCHS, batch_idx, 
                     len(train_loader), cost))
            cost_list.append(cost)
        

    model.eval()
    with torch.set_grad_enabled(False): # save memory during inference
        print('Epoch: %03d/%03d | Train: %.3f%%' % (
              epoch+1, NUM_EPOCHS, 
              compute_accuracy(model, train_loader, device=DEVICE)))
        
    print('Time elapsed: %.2f min' % ((time.time() - start_time)/60))
    
print('Total Training Time: %.2f min' % ((time.time() - start_time)/60))

7、模型存儲、結果導出

torch.save(model,'resnet_34_model.pth')
np.save('cost.npy',cost_list)
model.eval()
pred =[]


with torch.set_grad_enabled(False): # save memory during inference
    for batch_idx, (features) in enumerate(test_loader):
        features = features[0].float()
        logits, probas = model(features)
        _, _pred = torch.max(probas, 1)
        pred += _pred.tolist()

data1 = {'ImageId': [i + 1 for i in range(len(pred))], 'Label': pred}
df1 = pd.DataFrame(data1)
df1.to_csv("./data/submission.csv", index=None)

最後

參考文獻：

[1]、https://blog.csdn.net/qq_16907619/article/details/103765237
[2]、https://github.com/rasbt/deeplearning-models

有用請點贊，疑問可留言。