第P7周—咖啡豆识别（1）

数据集及wen件目录介绍：

数据集：工作台 - Heywhale.com

一、前期工作

1.1 数据详情

import torch
import torch.nn as nn
import torchvision.transforms as transforms
import torchvision
from torchvision import transforms, datasets
import os,PIL,pathlib,warningswarnings.filterwarnings("ignore")             #忽略警告信息device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
print(device)import os,PIL,random,pathlibdata_dir = 'D:/P7/49-data/'
data_dir = pathlib.Path(data_dir)data_paths  = list(data_dir.glob('*'))
classeNames = [str(path).split("\\")[3] for path in data_paths]
print(classeNames)image_count = len(list(data_dir.glob('*/*.png')))print("图片总数为：",image_count)

1.2 图片预处理：

详见：写文章-CSDN创作中心https://mp.csdn.net/mp_blog/creation/editor/133411331

train_transforms = transforms.Compose([transforms.Resize([224, 224]),  # 将输入图片resize成统一尺寸# transforms.RandomHorizontalFlip(), # 随机水平翻转transforms.ToTensor(),          # 将PIL Image或numpy.ndarray转换为tensor，并归一化到[0,1]之间transforms.Normalize(           # 标准化处理-->转换为标准正太分布（高斯分布），使模型更容易收敛mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])  # 其中 mean=[0.485,0.456,0.406]与std=[0.229,0.224,0.225] 从数据集中随机抽样计算得到的。
])test_transform = transforms.Compose([transforms.Resize([224, 224]),  # 将输入图片resize成统一尺寸transforms.ToTensor(),          # 将PIL Image或numpy.ndarray转换为tensor，并归一化到[0,1]之间transforms.Normalize(           # 标准化处理-->转换为标准正太分布（高斯分布），使模型更容易收敛mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])  # 其中 mean=[0.485,0.456,0.406]与std=[0.229,0.224,0.225] 从数据集中随机抽样计算得到的。
])total_data = datasets.ImageFolder("D:/P7/49-data",transform=train_transforms)
print(total_data)

标签量化处理：

print(total_data.class_to_idx)

1.4 划分数据集

train_size = int(0.8 * len(total_data))
test_size  = len(total_data) - train_size
train_dataset, test_dataset = torch.utils.data.random_split(total_data, [train_size, test_size])
print(train_dataset, test_dataset)

二、搭建VGG—16模型

import torch.nn.functional as Fclass vgg16(nn.Module):def __init__(self):super(vgg16, self).__init__()# 卷积块1self.block1 = nn.Sequential(nn.Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),nn.ReLU(),nn.Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),nn.ReLU(),nn.MaxPool2d(kernel_size=(2, 2), stride=(2, 2)))# 卷积块2self.block2 = nn.Sequential(nn.Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),nn.ReLU(),nn.Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),nn.ReLU(),nn.MaxPool2d(kernel_size=(2, 2), stride=(2, 2)))# 卷积块3self.block3 = nn.Sequential(nn.Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),nn.ReLU(),nn.Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),nn.ReLU(),nn.Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),nn.ReLU(),nn.MaxPool2d(kernel_size=(2, 2), stride=(2, 2)))# 卷积块4self.block4 = nn.Sequential(nn.Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),nn.ReLU(),nn.Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),nn.ReLU(),nn.Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),nn.ReLU(),nn.MaxPool2d(kernel_size=(2, 2), stride=(2, 2)))# 卷积块5self.block5 = nn.Sequential(nn.Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),nn.ReLU(),nn.Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),nn.ReLU(),nn.Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),nn.ReLU(),nn.MaxPool2d(kernel_size=(2, 2), stride=(2, 2)))# 全连接网络层，用于分类self.classifier = nn.Sequential(nn.Linear(in_features=512*7*7, out_features=4096),nn.ReLU(),nn.Linear(in_features=4096, out_features=4096),nn.ReLU(),nn.Linear(in_features=4096, out_features=4))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 = torch.flatten(x, start_dim=1)x = self.classifier(x)return xdevice = "cuda" if torch.cuda.is_available() else "cpu"
print("Using {} device".format(device))model = vgg16().to(device)
print(model)