手写经典卷积神经网络-AlexNet

论文：

torch实现：

数据集分割处理脚本spile_data.py

定义一个AlexNet网络model.py

训练脚本train.py

预测脚本predict.py

论文：

ImageNet Classification with Deep Convolutional Neural Networks

https://papers.nips.cc/paper/2012/file/c399862d3b9d6b76c8436e924a68c45b-Paper.pdf

torch实现：

本文测试场景为花的分类，数据集下载地址：

http://download.tensorflow.org/example_images/flower_photos.tgz

数据集分割处理脚本spile_data.py

import os
from shutil import copy
import randomdef mkfile(file):if not os.path.exists(file):os.makedirs(file)file = 'flower_data/flower_photos'
flower_class = [cla for cla in os.listdir(file) if ".txt" not in cla]
mkfile('flower_data/train')
for cla in flower_class:mkfile('flower_data/train/'+cla)mkfile('flower_data/val')
for cla in flower_class:mkfile('flower_data/val/'+cla)split_rate = 0.1
for cla in flower_class:cla_path = file + '/' + cla + '/'images = os.listdir(cla_path)num = len(images)eval_index = random.sample(images, k=int(num*split_rate))for index, image in enumerate(images):if image in eval_index:image_path = cla_path + imagenew_path = 'flower_data/val/' + clacopy(image_path, new_path)else:image_path = cla_path + imagenew_path = 'flower_data/train/' + clacopy(image_path, new_path)print("\r[{}] processing [{}/{}]".format(cla, index+1, num), end="")  # processing barprint()print("processing done!")

定义一个AlexNet网络model.py

import torch.nn as nn
import torchclass AlexNet(nn.Module):def __init__(self, num_classes=1000, init_weights=False):super(AlexNet, self).__init__()self.features = nn.Sequential(  #打包nn.Conv2d(3, 48, kernel_size=11, stride=4, padding=2),  # input[3, 224, 224]  output[48, 55, 55] 自动舍去小数点后nn.ReLU(inplace=True), #inplace 可以载入更大模型nn.MaxPool2d(kernel_size=3, stride=2),                  # output[48, 27, 27] kernel_num为原论文一半nn.Conv2d(48, 128, kernel_size=5, padding=2),           # output[128, 27, 27]nn.ReLU(inplace=True),nn.MaxPool2d(kernel_size=3, stride=2),                  # output[128, 13, 13]nn.Conv2d(128, 192, kernel_size=3, padding=1),          # output[192, 13, 13]nn.ReLU(inplace=True),nn.Conv2d(192, 192, kernel_size=3, padding=1),          # output[192, 13, 13]nn.ReLU(inplace=True),nn.Conv2d(192, 128, kernel_size=3, padding=1),          # output[128, 13, 13]nn.ReLU(inplace=True),nn.MaxPool2d(kernel_size=3, stride=2),                  # output[128, 6, 6])self.classifier = nn.Sequential(nn.Dropout(p=0.5),#全链接nn.Linear(128 * 6 * 6, 2048),nn.ReLU(inplace=True),nn.Dropout(p=0.5),nn.Linear(2048, 2048),nn.ReLU(inplace=True),nn.Linear(2048, num_classes),)if init_weights:self._initialize_weights()def forward(self, x):x = self.features(x)x = torch.flatten(x, start_dim=1) #展平   或者view()x = self.classifier(x)return xdef _initialize_weights(self):for m in self.modules():if isinstance(m, nn.Conv2d):nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu') #何教授方法if m.bias is not None:nn.init.constant_(m.bias, 0)elif isinstance(m, nn.Linear):nn.init.normal_(m.weight, 0, 0.01)  #正态分布赋值nn.init.constant_(m.bias, 0)

训练脚本train.py

import torch
import torch.nn as nn
from torchvision import transforms, datasets, utils
import matplotlib.pyplot as plt
import numpy as np
import torch.optim as optim
from model import AlexNet
import os
import json
import time#device : GPU or CPU
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
print(device)#数据转换
data_transform = {"train": transforms.Compose([transforms.RandomResizedCrop(224),transforms.RandomHorizontalFlip(),transforms.ToTensor(),transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))]),"val": transforms.Compose([transforms.Resize((224, 224)),  # cannot 224, must (224, 224)transforms.ToTensor(),transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])}#data_root = os.path.abspath(os.path.join(os.getcwd(), "../.."))  # get data root path
data_root = os.getcwd()
image_path = data_root + "/flower_data/"  # flower data set path
train_dataset = datasets.ImageFolder(root=image_path + "/train",transform=data_transform["train"])
train_num = len(train_dataset)# {'daisy':0, 'dandelion':1, 'roses':2, 'sunflower':3, 'tulips':4}
flower_list = train_dataset.class_to_idx
cla_dict = dict((val, key) for key, val in flower_list.items())
# write dict into json file
json_str = json.dumps(cla_dict, indent=4)
with open('class_indices.json', 'w') as json_file:json_file.write(json_str)batch_size = 32
train_loader = torch.utils.data.DataLoader(train_dataset,batch_size=batch_size, shuffle=True,num_workers=0)validate_dataset = datasets.ImageFolder(root=image_path + "/val",transform=data_transform["val"])
val_num = len(validate_dataset)
validate_loader = torch.utils.data.DataLoader(validate_dataset,batch_size=batch_size, shuffle=True,num_workers=0)test_data_iter = iter(validate_loader)
test_image, test_label = test_data_iter.next()
#print(test_image[0].size(),type(test_image[0]))
#print(test_label[0],test_label[0].item(),type(test_label[0]))#显示图像，之前需把validate_loader中batch_size改为4
# def imshow(img):
#     img = img / 2 + 0.5  # unnormalize
#     npimg = img.numpy()
#     plt.imshow(np.transpose(npimg, (1, 2, 0)))
#     plt.show()
#
# print(' '.join('%5s' % cla_dict[test_label[j].item()] for j in range(4)))
# imshow(utils.make_grid(test_image))net = AlexNet(num_classes=5, init_weights=True)net.to(device)
#损失函数:这里用交叉熵
loss_function = nn.CrossEntropyLoss()
#优化器 这里用Adam
optimizer = optim.Adam(net.parameters(), lr=0.0002)
#训练参数保存路径
save_path = './AlexNet.pth'
#训练过程中最高准确率
best_acc = 0.0#开始进行训练和测试，训练一轮，测试一轮
for epoch in range(10):# trainnet.train()    #训练过程中，使用之前定义网络中的dropoutrunning_loss = 0.0t1 = time.perf_counter()total = 0correct = 0.0for step, data in enumerate(train_loader, start=0):images, labels = dataoptimizer.zero_grad()outputs = net(images.to(device))loss = loss_function(outputs, labels.to(device))loss.backward()optimizer.step()# print statisticsrunning_loss += loss.item()# print train processrate = (step + 1) / len(train_loader)a = "*" * int(rate * 50)b = "." * int((1 - rate) * 50)print("\rtrain loss: {:^3.0f}%[{}->{}]{:.3f}".format(int(rate * 100), a, b, loss), end="")print()print(time.perf_counter()-t1)# validatenet.eval()    #测试过程中不需要dropout，使用所有的神经元acc = 0.0  # accumulate accurate number / epochwith torch.no_grad():for val_data in validate_loader:val_images, val_labels = val_dataoutputs = net(val_images.to(device))predict_y = torch.max(outputs, dim=1)[1]acc += (predict_y == val_labels.to(device)).sum().item()val_accurate = acc / val_numif val_accurate > best_acc:best_acc = val_accuratetorch.save(net.state_dict(), save_path)print('[epoch %d] train_loss: %.3f  test_accuracy: %.3f' %(epoch + 1, running_loss / step, val_accurate))print('Finished Training')

预测脚本predict.py

import torch
from model import AlexNet
from PIL import Image
from torchvision import transforms
import matplotlib.pyplot as plt
import jsondata_transform = transforms.Compose([transforms.Resize((224, 224)),transforms.ToTensor(),transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])# load image
img = Image.open("./2.jpg").convert('RGB')  #验证太阳花
#img = Image.open("./roses.jpg")     #验证玫瑰花
plt.imshow(img)
# [N, C, H, W]
img = data_transform(img)
# expand batch dimension
img = torch.unsqueeze(img, dim=0)# read class_indict
try:json_file = open('./class_indices.json', 'r')class_indict = json.load(json_file)
except Exception as e:print(e)exit(-1)# create model
model = AlexNet(num_classes=5)
# load model weights
model_weight_path = "./AlexNet.pth"
model.load_state_dict(torch.load(model_weight_path))
model.eval()
with torch.no_grad():# predict classoutput = torch.squeeze(model(img))predict = torch.softmax(output, dim=0)predict_cla = torch.argmax(predict).numpy()
print(class_indict[str(predict_cla)], predict[predict_cla].item())
plt.show()

手写经典卷积神经网络-AlexNet相关推荐

手写经典卷积神经网络-LeNet
目录论文: keras torch版本: 训练: 测试和可视化论文: 论文名:Gradient-Based Learning Applied to Document Recognition ker ...
经典卷积神经网络-AlexNet
AlexNet 学习目标知道AlexNet网络结构能够利用AlexNet完成图像分类 2012年,AlexNet横空出世,该模型的名字源于论文第一作者的姓名Alex Krizhevsky .Ale ...
TensorFlow 手写实现卷积神经网络CNN
目录一:卷积神经网络基础概念二:MNIST数据集三:卷积神经网络搭建过程一:卷积神经网络基础概念普通的深层神经网络,层与层之间通过全连接进行稠密矩阵运算,矩阵中的权重系数比较多(参数多),影 ...
经典卷积神经网络--AlexNet的详解
一.AlexNet的概述 AlexNet由Geoffrey和他的学生Alex提出,并在2012年的ILSVRC竞赛中获得了第一名.Alexnet共有8层结构,前5层为卷积层,后三层为全连接层. Ale ...
Pytorch之CNN：基于Pytorch框架实现经典卷积神经网络的算法(LeNet、AlexNet、VGG、NIN、GoogleNet、ResNet)——从代码认知CNN经典架构
Pytorch之CNN:基于Pytorch框架实现经典卷积神经网络的算法(LeNet.AlexNet.VGG.NIN.GoogleNet.ResNet)--从代码认知CNN经典架构目录 CNN经典算 ...
【深度学习基础】经典卷积神经网络
点击上方"小白学视觉",选择加"星标"或"置顶" 重磅干货,第一时间送达导语卷积神经网络(Convolutional Neural Ne ...
AI基础：经典卷积神经网络
导语卷积神经网络(Convolutional Neural Networks, CNN)是一类包含卷积计算且具有深度结构的前馈神经网络(Feedforward Neural Networks),是深 ...
一文总结经典卷积神经网络CNN模型
一般的DNN直接将全部信息拉成一维进行全连接,会丢失图像的位置等信息. CNN(卷积神经网络)更适合计算机视觉领域.下面总结从1998年至今的优秀CNN模型,包括LeNet.AlexNet.ZFNet ...
CNN(经典卷积神经网络)来了！
导语卷积神经网络(Convolutional Neural Networks, CNN)是一类包含卷积计算且具有深度结构的前馈神经网络(Feedforward Neural Networks),是深 ...

手写经典卷积神经网络-AlexNet

论文：

torch实现：

数据集分割处理脚本spile_data.py

定义一个AlexNet网络model.py

训练脚本train.py

预测脚本predict.py

手写经典卷积神经网络-AlexNet相关推荐

最新文章

热门文章