首页 > 专利技术

深度学习实战---猫狗大战（pytorch实现）

深度学习实战---猫狗⼤战（pytorch实现）

数据准备

微软的数据集已经分好类，直接使⽤就⾏，

数据划分

我们将猫和狗的图⽚分别移动到训练集和验证集中，其中90%的数据作为训练集，10%的图⽚作为验证集，使⽤ve（）来移动图⽚。

新建⽂件夹train,test，将数据集放⼊train中，利⽤代码将10%的数据移动到test中

⽂件移动代码

import os

import shutil

source_path = r"E:\猫狗⼤战数据集\PetImages"

train_dir = os.path.join(source_path, "train")

test_dir = os.path.join(source_path,"test")

train_dir_list = os.listdir(train_dir)

for dir in train_dir_list:

category_dir_path = os.path.join(train_dir, dir)

image_file_list = os.listdir(category_dir_path)

num = int(0.1*len(image_file_list))

#移动10%⽂件到对应⽬录

for i in range(num):

移动后

数据可视化

import matplotlib.pyplot as plt

import numpy

import os

from PIL import Image #读取图⽚模块

from matplotlib.image import imread

source_path = r"E:\猫狗⼤战数据集\PetImages"

#分别从Dog,Cat⽂件夹中选取10张图⽚显⽰

train_Dog_dir = os.path.join(source_path, "train","Dog")

train_Cat_dir = os.path.join(source_path, "train","Cat")

Dog_image_list = os.listdir(train_Dog_dir)

Cat_image_list = os.listdir(train_Cat_dir)

show_image = [os.path.join(train_Dog_dir,Dog_image_list[i]) for i in range(10)] d([os.path.join(train_Cat_dir,Cat_image_list[i]) for i in range(10)]) for i in show_image:

print(i)蜂窝纸板托盘

plt.figure()

for i in range(1,20):

plt.subplot(4,5,i)

img = Image.open(show_image[i-1])

plt.imshow(img)

plt.show()

效果图：

可以看出图⽚的尺⼨不同，在数据预处理时需要将图⽚resize,

使⽤预训练模型（resnet）进⾏训练

from torchvision import datasets, transforms

import torch.utils.data

as nn

dels as models

import torch.optim as optim

from visdom import Visdom

if __name__ == '__main__':

#数据处理

data_transform = transforms.Compose([

transforms.Resize(128),

transforms.CenterCrop(128),

transforms.ToTensor(),

transforms.Normalize(mean=[0.5, 0.5, 0.5], std=[0.5, 0.5, 0.5])

])

train_dataset = datasets.ImageFolder(root=r'E:/猫狗⼤战数据集/PetImages/train/', transform=data_transform) train_loader = torch.utils.data.DataLoader(train_dataset, batch_size=4, shuffle=True, num_workers=4)

test_dataset = datasets.ImageFolder(root=r'E:/猫狗⼤战数据集/PetImages/test/', transform=data_transform) test_loader = torch.utils.data.DataLoader(test_dataset, batch_size=4, shuffle=True, num_workers=4)

#损失函数

criteon = nn.CrossEntropyLoss()

#加载预训练模型

transfer_model = snet18(pretrained=True)

dim_in = transfer_model.fc.in_features

transfer_model.fc = nn.Linear(dim_in, 2)

#优化器adam

optimizer = optim.Adam(transfer_model.parameters(), lr=0.01)

#加载模型到GPU

transfer_model = transfer_model.cuda()

viz = Visdom()

viz.line([[0.0,0.0]],[0.],win='train',opts=dict(title="train_loss&&acc", legend=['loss','acc']))

viz.line([[0.0,0.0]], [0.], win='test', opts=dict(title="test loss&&acc.",legend=['loss', 'acc']))

global_step =0水封井

#模型训练

ain()

for epoch in range(10):

train_acc_num =0

test_acc_num =0

for batch_idx,(data,target) in enumerate(train_loader):

data, target = data.cuda(), target.cuda()

#投⼊数据，得到预测值

logits = transfer_model(data)

_,pred = torch.max(logits.data,1)

#print(pred, target)

loss = criteon(logits, target)

<_grad()

loss.backward()

optimizer.step()

#准确度计算

沉没度

train_acc_num += pred.eq(target).float().sum().item()

#print("准确数:",train_acc_num," ",batch_idx, " ",len(data))

train_acc = train_acc_num/((batch_idx+1)*len(data))

#print(train_acc)

#print(train_acc.item())

global_step +=1

viz.line([[loss.item(), train_acc]],[global_step],win='train',update='append')

if batch_idx %200 ==0:

print('Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f},acc:{}'.format(

epoch, batch_idx * len(data), len(train_loader.dataset),

秸秆腐熟剂epoch, batch_idx * len(data), len(train_loader.dataset),

100. * batch_idx / len(train_loader), loss.item(),train_acc))

test_loss =0

for data, target in test_loader:

cap3data, target = data.cuda(), target.cuda()

logits = transfer_model(data)

test_loss += criteon(logits,target).item()

_, pred = torch.max(logits.data, 1)

# 准确度计算

test_acc_num += pred.eq(target).float().sum().item()

viz.line([[test_loss / len(test_loader.dataset), test_acc_num / len(test_loader.dataset)]],

[global_step], win='test', update='append')

test_acc = train_acc_num / len(test_loader.dataset)

viz.images(data.view(-1, 3, 128, 128), win='x')

<(str(pred.detach().cpu().numpy()), win='pred',

opts=dict(title='pred'))

test_loss /= len(test_loader.dataset)

print('\nTest set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)\n'.format(

test_loss, test_acc, len(test_loader.dataset),

100. * test_acc / len(test_loader.dataset)))

Train Epoch: 0 [0/22498 (0%)] Loss: 1.061759,acc:0.25

Train Epoch: 0 [800/22498 (4%)] Loss: 0.708053,acc:0.5174129353233831 Train Epoch: 0 [1600/22498 (7%)] Loss: 0.403057,acc:0.5155860349127181 Train Epoch: 0 [2400/22498 (11%)] Loss: 0.721054,acc:0.5033277870216306 Train Epoch: 0 [3200/22498 (14%)] Loss: 0.629318,acc:0.5037453183520599

其中visdom是模型可视化模块

>headcall

本文发布于:2024-09-22 07:21:41，感谢您对本站的认可！

本文链接：https://www.17tex.com/tex/3/215949.html

上一篇：五年级下册英语Unit3 My school calendar知识点总结复习及练习 (含答案) 人教PEP

下一篇：go-for-it-人教版(新目标)英语-七年级-上册-单词-词汇表-带英标