建站上市公司,免费 网站 如何做,网店装修,制作网站的过程细节Pytorch从零开始实战——咖啡豆识别
本系列来源于365天深度学习训练营
原作者K同学 文章目录 Pytorch从零开始实战——咖啡豆识别环境准备数据集模型选择训练模型可视化模型预测其他问题总结 环境准备
本文基于Jupyter notebook#xff0c;使用Python3.8#xff0c;Pytor…Pytorch从零开始实战——咖啡豆识别
本系列来源于365天深度学习训练营
原作者K同学 文章目录 Pytorch从零开始实战——咖啡豆识别环境准备数据集模型选择训练模型可视化模型预测其他问题总结 环境准备
本文基于Jupyter notebook使用Python3.8Pytorch2.0.1cu118torchvision0.15.2需读者自行配置好环境且有一些深度学习理论基础。本次实验的目的是手写VGG并且测试多GPU。 第一步导入常用包
import torch
import torch.nn as nn
import matplotlib.pyplot as plt
import torchvision
import torchvision.transforms as transforms
import torchvision.datasets as datasets
import torch.nn.functional as F
import random
from time import time
import numpy as np
import pandas as pd
import datetime
import gc
import os
import copy
os.environ[KMP_DUPLICATE_LIB_OK]True # 用于避免jupyter环境突然关闭
torch.backends.cudnn.benchmarkTrue # 用于加速GPU运算的代码设置随机数种子
torch.manual_seed(428)
torch.cuda.manual_seed(428)
torch.cuda.manual_seed_all(428)
random.seed(428)
np.random.seed(428)创建设备对象并且查看GPU数量
device torch.device(cuda if torch.cuda.is_available() else cpu)
device, torch.cuda.device_count()数据集
本次使用的数据集是咖啡豆图片它分为四个类别Dark、Green、Light、Medium一共有1200张图片不同的类别存放在不同的文件夹中文件夹名是类别名。 使用pathlib查看类别
import pathlib
data_dir ./data/beans
data_dir pathlib.Path(data_dir) # 转成pathlib.Path对象
data_paths list(data_dir.glob(*))
classNames [str(path).split(/)[2] for path in data_paths]
classNames # [Dark, Green, Medium, Light]使用transforms对数据集进行统一处理并且根据文件夹名映射对应标签
train_transforms transforms.Compose([transforms.Resize([224, 224]),transforms.ToTensor(),transforms.Normalize(mean[0.485, 0.456, 0.406], std[0.229, 0.224, 0.225]) # 标准化
])total_data datasets.ImageFolder(./data/beans/, transformtrain_transforms)
total_data.class_to_idx # {Dark: 0, Green: 1, Light: 2, Medium: 3}随机查看5张图片
def plotsample(data):fig, axs plt.subplots(1, 5, figsize(10, 10)) #建立子图for i in range(5):num random.randint(0, len(data) - 1) #首先选取随机数随机选取五次#抽取数据中对应的图像对象make_grid函数可将任意格式的图像的通道数升为3而不改变图像原始的数据#而展示图像用的imshow函数最常见的输入格式也是3通道npimg torchvision.utils.make_grid(data[num][0]).numpy()nplabel data[num][1] #提取标签 #将图像由(3, weight, height)转化为(weight, height, 3)并放入imshow函数中读取axs[i].imshow(np.transpose(npimg, (1, 2, 0))) axs[i].set_title(nplabel) #给每个子图加上标签axs[i].axis(off) #消除每个子图的坐标轴plotsample(total_data)根据8比2划分数据集和测试集并且利用DataLoader划分批次和随机打乱
train_size int(0.8 * len(total_data))
test_size len(total_data) - train_size
train_ds, test_ds torch.utils.data.random_split(total_data, [train_size, test_size])batch_size 32
train_dl torch.utils.data.DataLoader(train_ds,batch_sizebatch_size,shuffleTrue,)
test_dl torch.utils.data.DataLoader(test_ds,batch_sizebatch_size,shuffleTrue,)len(train_dl.dataset), len(test_dl.dataset) # (960, 240)模型选择
本次实验使用VGG16模型如下
class Model(nn.Module):def __init__(self):super().__init__()self.block1 nn.Sequential(nn.Conv2d(3, 64, kernel_size3, stride1, padding1),nn.ReLU(),nn.Conv2d(64, 64, kernel_size3, stride1, padding1),nn.ReLU(),nn.MaxPool2d(2))self.block2 nn.Sequential(nn.Conv2d(64, 128, kernel_size3, stride1, padding1),nn.ReLU(),nn.Conv2d(128, 128, kernel_size3, stride1, padding1),nn.ReLU(),nn.MaxPool2d(2))self.block3 nn.Sequential(nn.Conv2d(128, 256, kernel_size3, stride1, padding1),nn.ReLU(),nn.Conv2d(256, 256, kernel_size3, stride1, padding1),nn.ReLU(),nn.Conv2d(256, 256, kernel_size3, stride1, padding1),nn.ReLU(),nn.MaxPool2d(2))self.block4 nn.Sequential(nn.Conv2d(256, 512, kernel_size3, stride1, padding1),nn.ReLU(),nn.Conv2d(512, 512, kernel_size3, stride1, padding1),nn.ReLU(),nn.Conv2d(512, 512, kernel_size3, stride1, padding1),nn.ReLU(),nn.MaxPool2d(2))self.block5 nn.Sequential(nn.Conv2d(512, 512, kernel_size3, stride1, padding1),nn.ReLU(),nn.Conv2d(512, 512, kernel_size3, stride1, padding1),nn.ReLU(),nn.Conv2d(512, 512, kernel_size3, stride1, padding1),nn.ReLU(),nn.MaxPool2d(2))self.fc nn.Sequential(nn.Linear(7 * 7 * 512, 4096),nn.ReLU(),nn.Linear(4096, 4096),nn.ReLU(),nn.Linear(4096, len(classNames)))def forward(self, x):x self.block1(x)x self.block2(x)x self.block3(x)x self.block4(x)x self.block5(x)x x.view(-1, 7 * 7 * 512)x self.fc(x)return x使用summary查看模型结构并且将模型转成多GPU并行运算的模型
from torchsummary import summary
# 将模型转移到GPU中
model Model()
model model.to(device)
if torch.cuda.device_count() 1: # 检查电脑是否有多块GPUprint(fLets use {torch.cuda.device_count()} GPUs!)model nn.DataParallel(model) # 将模型对象转变为多GPU并行运算的模型summary(model, input_size(3, 224, 224))训练
定义训练函数
def train(dataloader, model, loss_fn, opt):size len(dataloader.dataset)num_batches len(dataloader)train_acc, train_loss 0, 0for X, y in dataloader:X, y X.to(device), y.to(device)pred model(X)loss loss_fn(pred, y)opt.zero_grad()loss.backward()opt.step()train_acc (pred.argmax(1) y).type(torch.float).sum().item()train_loss loss.item()train_acc / sizetrain_loss / num_batchesreturn train_acc, train_loss定义测试函数
def test(dataloader, model, loss_fn):size len(dataloader.dataset)num_batches len(dataloader)test_acc, test_loss 0, 0with torch.no_grad():for X, y in dataloader:X, y X.to(device), y.to(device)pred model(X)loss loss_fn(pred, y)test_acc (pred.argmax(1) y).type(torch.float).sum().item()test_loss loss.item()test_acc / sizetest_loss / num_batchesreturn test_acc, test_loss定义损失函数、优化算法、学习率本次使用的是Adam优化算法
loss_fn nn.CrossEntropyLoss()
learn_rate 0.0001
opt torch.optim.Adam(model.parameters(), lrlearn_rate)开始训练准确率还是非常高的
import time
epochs 30
train_loss []
train_acc []
test_loss []
test_acc []T1 time.time()best_acc 0
best_model 0for epoch in range(epochs):model.train()epoch_train_acc, epoch_train_loss train(train_dl, model, loss_fn, opt)model.eval() # 确保模型不会进行训练操作epoch_test_acc, epoch_test_loss test(test_dl, model, loss_fn)if epoch_test_acc best_acc:best_acc epoch_test_accbest_model copy.deepcopy(model)train_acc.append(epoch_train_acc)train_loss.append(epoch_train_loss)test_acc.append(epoch_test_acc)test_loss.append(epoch_test_loss)print(epoch:%d, train_acc:%.1f%%, train_loss:%.3f, test_acc:%.1f%%, test_loss:%.3f% (epoch 1, epoch_train_acc * 100, epoch_train_loss, epoch_test_acc * 100, epoch_test_loss))T2 time.time()
print(程序运行时间:%s秒 % (T2 - T1))PATH ./best_model.pth # 保存的参数文件名
if best_model is not None:torch.save(best_model.state_dict(), PATH)print(保存最佳模型)
print(Done)模型可视化
使用matplotlib可视化训练、测试过程
import warnings
warnings.filterwarnings(ignore) #忽略警告信息
plt.rcParams[font.sans-serif] [SimHei] # 用来正常显示中文标签
plt.rcParams[axes.unicode_minus] False # 用来正常显示负号
plt.rcParams[figure.dpi] 100 #分辨率epochs_range range(epochs)plt.figure(figsize(12, 3))
plt.subplot(1, 2, 1)plt.plot(epochs_range, train_acc, labelTraining Accuracy)
plt.plot(epochs_range, test_acc, labelTest Accuracy)
plt.legend(loclower right)
plt.title(Training and Validation Accuracy)plt.subplot(1, 2, 2)
plt.plot(epochs_range, train_loss, labelTraining Loss)
plt.plot(epochs_range, test_loss, labelTest Loss)
plt.legend(locupper right)
plt.title(Training and Validation Loss)
plt.show()模型预测
定义模型预测函数
from PIL import Image classes list(total_data.class_to_idx)def predict_one_image(image_path, model, transform, classes):test_img Image.open(image_path).convert(RGB)plt.imshow(test_img) # 展示预测的图片test_img transform(test_img)img test_img.to(device).unsqueeze(0)model.eval()output model(img)_,pred torch.max(output,1)pred_class classes[pred]print(f预测结果是{pred_class}) 开始单张图片预测
predict_one_image(image_path./data/beans/Dark/dark (1).png, modelmodel, transformtrain_transforms, classesclasses) # 预测结果是Dark查看最优的模型的准确率和损失
best_model.eval()
epoch_test_acc, epoch_test_loss test(test_dl, best_model, loss_fn)
epoch_test_acc, epoch_test_loss # (0.9916666666666667, 0.0399394309388299)其他问题
本次实验又使用了单GPU进行训练
# 单GPU
from torchsummary import summary
# 将模型转移到GPU中
model Model()
model model.to(device)结果如下
总结
本次实验主要手写了经典网络架构VGG16并且使用两张GPU和一张GPU进行实验但惊奇的发现一张GPU运行时间是164秒两张GPU运行时间是318秒明明算力提高了反而训练时间更加慢了经过资料的查询大概原因是数据量很小GPU之间传递数据占用时间相对大于加速运算时间所以训练时间反而变长了。
