目录
pytorch --数据加载之 Dataset 与DataLoader详解
前言:
目前阿里天池大赛正式赛已经结束了,还有一个长期赛同学们可以参加,增加自己的cv基础知识
这里就是天池大赛的官方网址啦,想打比赛的小伙伴们可以点击上方的链接注册,里面有很多数据分析,视觉检测以及算法等等的比赛,同时还有很多入门比赛,大家都可以尝试学习
话不多说,正式开始:
备注:默认同学们已经配置好pytorch环境了哈,当然,遇到临时用到的库,再安装也行
基本的流程如下:
用到的库:
import os, sys, glob, shutil, json
os.environ["CUDA_VISIBLE_DEVICES"] = '0'
import cv2
from PIL import Image
import numpy as np
from tqdm import tqdm, tqdm_notebook
# %pylab inline
import torch
torch.manual_seed(0)
torch.backends.cudnn.deterministic = False
torch.backends.cudnn.benchmark = True
1、数据准备
进入天池大赛官网,报名就可以获取 数据啦,在官网的csv文件中有数据集,验证集还有测试机的下载网址:
2、数据加载
直接上代码:
训练集的数据加载:
train_path = sorted(glob.glob('D:/1wangyong\pytorchtrains\街景字符\Data\mchar_train/*.png'))
train_json = json.load(open('D:/1wangyong\pytorchtrains\街景字符\Data\mchar_train.json'))
train_label = [train_json[x]['label'] for x in train_json]
测试集的数据加载和训练集一样:
val_path = sorted(glob.glob('D:/1wangyong\pytorchtrains\街景字符\Data\mchar_val/*.png'))
val_json = json.load(open('D:/1wangyong\pytorchtrains\街景字符\Data\mchar_val.json'))
val_label = [val_json[x]['label'] for x in val_json]
print(len(val_path), len(val_label))
很多文章都写路径最好别带中文哈,因为运行没出现什么问题,就没改,大家不放心的话,路径使用全英文的也可以
3、创建Dataset类
在pytorch中,数据加载完成之后,就要建立一个Dataset类,这个可以在我的博客:
pytorch --数据加载之 Dataset 与DataLoader详解
中查看详细的描述:
class SVHNDataset(Dataset):
def __init__(self, img_path, img_label, transform=None):
self.img_path = img_path
self.img_label = img_label
if transform is not None:
self.transform = transform
else:
self.transform = None
def __getitem__(self, index):
img = Image.open(self.img_path[index]).convert('RGB')
if self.transform is not None:
img = self.transform(img)
lbl = np.array(self.img_label[index], dtype=np.int_)
lbl = list(lbl) + (5 - len(lbl)) * [10]
return img, torch.from_numpy(np.array(lbl[:5]))
def __len__(self):
return len(self.img_path)
4、数据增强、创建DataLoader
这个也是训练集与验证集分开:
测试集:
val_loader = torch.utils.data.DataLoader(
SVHNDataset(val_path, val_label,
transforms.Compose([
transforms.Resize((80, 160)),
transforms.RandomCrop((64, 128)),
# transforms.ColorJitter(0.3, 0.3, 0.2),
# transforms.RandomRotation(5),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [
0.229, 0.224, 0.225])
])),
batch_size=64,
shuffle=False,
num_workers=0,
)
训练集:
train_loader = torch.utils.data.DataLoader(
SVHNDataset(train_path, train_label,
transforms.Compose([
transforms.Resize((80, 160)),
transforms.RandomCrop((64, 128)),
transforms.ColorJitter(0.3, 0.3, 0.2),
transforms.RandomRotation(10),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
])),
batch_size=64,
shuffle=True,
num_workers=0,
)
5、搭建模型:
官网模型:
class SVHN_Model1(nn.Module):
def __init__(self):
super(SVHN_Model1, self).__init__()
model_conv = models.resnet18(pretrained=True)
model_conv.avgpool = nn.AdaptiveAvgPool2d(1)
model_conv = nn.Sequential(*list(model_conv.children())[:-1]) # 去除最后一个fc layer
self.cnn = model_conv
self.fc1 = nn.Linear(512, 11)
self.fc2 = nn.Linear(512, 11)
self.fc3 = nn.Linear(512, 11)
self.fc4 = nn.Linear(512, 11)
self.fc5 = nn.Linear(512, 11)
def forward(self, img):
feat = self.cnn(img)
#print(feat.shape)
feat = feat.view(feat.shape[0], -1)
c1 = self.fc1(feat)
c2 = self.fc2(feat)
c3 = self.fc3(feat)
c4 = self.fc4(feat)
c5 = self.fc5(feat)
return c1, c2, c3, c4, c5
官网给出的模型比较基础,如果只用官网,那肯定没有太大意义:
所以针对网络做出以下改进:
我们可以对使用的backbone网络进行一系列的改进:
1、由resnet18换为更大的resnet152
2、为每一个分类模块加上一层全连接隐藏层
3、为隐含层添加dropout
4、给全连接隐藏层中途添加一个relu函数,增强非线性
由resnet18换为resnet152,更深的模型就拥有更好的表达能力,添加一层隐含层同样起到了增加模型拟合能力的作用,与此同时为隐含层添加dropout来进行一个balance,一定程度上防止过拟合。(只是一些改进技巧,并不最优)
改进后的模型定义代码如下:
class SVHN_Model2(nn.Module):
def __init__(self):
super(SVHN_Model2, self).__init__()
# resnet18
model_conv = models.resnet152(pretrained=True)
model_conv.avgpool = nn.AdaptiveAvgPool2d(1)
model_conv = nn.Sequential(*list(model_conv.children())[:-1]) # 去除最后一个fc layer
self.cnn = model_conv
self.hd_fc1 = nn.Linear(512, 256)
self.hd_fc2 = nn.Linear(512, 256)
self.hd_fc3 = nn.Linear(512, 256)
self.hd_fc4 = nn.Linear(512, 256)
self.hd_fc5 = nn.Linear(512, 256)
self.dropout_1 = nn.Dropout(0.25)
self.dropout_2 = nn.Dropout(0.25)
self.dropout_3 = nn.Dropout(0.25)
self.dropout_4 = nn.Dropout(0.25)
self.dropout_5 = nn.Dropout(0.25)
self.fc1 = nn.Linear(256, 11)
self.fc2 = nn.Linear(256, 11)
self.fc3 = nn.Linear(256, 11)
self.fc4 = nn.Linear(256, 11)
self.fc5 = nn.Linear(256, 11)
def forward(self, img):
feat = self.cnn(img)
feat = feat.view(feat.shape[0], -1)
feat1 = torch.relu(self.hd_fc1(feat))
feat2 = torch.relu(self.hd_fc2(feat))
feat3 = torch.relu(self.hd_fc3(feat))
feat4 = torch.relu(self.hd_fc4(feat))
feat5 = torch.relu(self.hd_fc5(feat))
feat1 = self.dropout_1(feat1)
feat2 = self.dropout_2(feat2)
feat3 = self.dropout_3(feat3)
feat4 = self.dropout_4(feat4)
feat5 = self.dropout_5(feat5)
c1 = self.fc1(feat1)
c2 = self.fc2(feat2)
c3 = self.fc3(feat3)
c4 = self.fc4(feat4)
c5 = self.fc5(feat5)
return c1, c2, c3, c4, c5
6、模型的训练
基础的数据加载、数据增强、以及模型搭建都已经完成,就可以正式训练了:
有的同学可能好奇,那之前的Datase类和DataLoader过程是干嘛用的?
还是,同学们可以看看我之前的博客:pytorch --数据加载之 Dataset 与DataLoader详解
这里面有详细的介绍
训练代码:
model = SVHN_Model2()
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), 0.001)
best_loss = 1000.0
use_cuda = True
if use_cuda:
model = model.cuda()
for epoch in range(100):
start = time.time()
print('start', time.strftime("%Y-%m-%d %H:%M:%S", time.localtime(start)))
train_loss = train(train_loader, model, criterion, optimizer, epoch)
val_loss = validate(val_loader, model, criterion)
val_label = [''.join(map(str, x)) for x in val_loader.dataset.img_label]
val_predict_label = predict(val_loader, model, 1)
val_predict_label = np.vstack([
val_predict_label[:, :11].argmax(1),
val_predict_label[:, 11:22].argmax(1),
val_predict_label[:, 22:33].argmax(1),
val_predict_label[:, 33:44].argmax(1),
val_predict_label[:, 44:55].argmax(1),
]).T
val_label_pred = []
for x in val_predict_label:
val_label_pred.append(''.join(map(str, x[x != 10])))
val_char_acc = np.mean(np.array(val_label_pred) == np.array(val_label))
end = time.time()
print('end', time.strftime("%Y-%m-%d %H:%M:%S", time.localtime(end)))
time_cost = end - start
print(
'Epoch: {0}, Train loss: {1} \t Val loss: {2}, time_cost: {3}'.format(
epoch,
train_loss,
val_loss,
time_cost))
print('Val Acc', val_char_acc)
# 记录下验证集精度
if val_loss < best_loss:
best_loss = val_loss
# print('Find better model in Epoch {0}, saving model.'.format(epoch))
torch.save(model.state_dict(), './model.pt')
我在训练代码中加了一些,开始时间以及结束时间的记录,看一下网络迭代一次额所需时间。不需要的同学可以直接注释掉就OK
如果选用的优化器是Adam的话,大概20轮之内就训练完成了,SGD的话,需要训练久一点:
上述代码使用的Adam
7、模型预测结果
在上述的过程中,我们已经完成了模型的训练了,并且保存了训练最好的模型,我们只需要把模型拿出来做测试就好了:
代码如下:
model = SVHN_Model1().cuda()
test_path = sorted(glob.glob('D:/1wangyong\pytorchtrains\街景字符\Data\mchar_test_a/*.png'))
# test_json = json.load(open('../input/test.json'))
test_label = [[1]] * len(test_path)
# print(len(test_path), len(test_label))
test_loader = torch.utils.data.DataLoader(
SVHNDataset(test_path, test_label,
transforms.Compose([
transforms.Resize((68, 136)),
transforms.RandomCrop((64, 128)),
# transforms.ColorJitter(0.3, 0.3, 0.2),
# transforms.RandomRotation(5),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [
0.229, 0.224, 0.225])
])),
batch_size=40,
shuffle=False,
num_workers=0,
)
# 加载保存的最优模型
model.load_state_dict(torch.load('D:/Projects/wordec/model.pt'))
test_predict_label = predict(test_loader, model, 1)
print(test_predict_label.shape)
print('test_predict_label', test_predict_label)
test_label = [''.join(map(str, x)) for x in test_loader.dataset.img_label]
# print('test_label', test_label)
test_predict_label = np.vstack([
test_predict_label[:, :11].argmax(1),
test_predict_label[:, 11:22].argmax(1),
test_predict_label[:, 22:33].argmax(1),
test_predict_label[:, 33:44].argmax(1),
test_predict_label[:, 44:55].argmax(1),
]).T
test_label_pred = []
for x in test_predict_label:
test_label_pred.append(''.join(map(str, x[x != 10])))
# print("test_label_pred", len(test_label_pred))
df_submit = pd.read_csv('D:/Projects/wordec/input/test_A_sample_submit.csv')
df_submit['file_code'] = test_label_pred
df_submit.to_csv('submit_1018.csv', index=None)
print("finished")
完成上述过程,同学们就已经完成了,一个基础的训练啦。是不是有点小激动呢?
8、成绩提交
进入刚刚的天池大赛官网,找到相关的比赛,提交结果就可以啦!!
备注:(结果就是第七步保存的文件)
快去查看自己的排名吧!!!