AlexNet是一个经典的卷积神经网络模型,由Alex Krizhevsky等人在2012年提出。ImageNet ISVRC是计算机视觉领域里一个十分重要的比赛,AlexNet是2012年ISLVRC 2012竞赛的冠军,分类准确率由传统的70%+提升到80%+。也是在那年之后,深度学习开始迅速发展。
ISLVRC 2012
训练集:1,281,167张已标注图片
验证集:50,000张已标注图片
测试集:100,000张未标注图片
AlexNet共有8层网络结构,第1、2、5层使用较小的卷积核(11x11、5x5和3x3),并采用ReLU激活函数;第3、4层则使用池化层进行下采样;第6、7层是全连接层,最后一层是softmax分类层。此外,AlexNet还采用了一些增强训练效果的技巧,如局部响应归一化和随机失活等。
- 过拟合:根本原因是特征维度过多,模型假设过于复杂,参数过多,训练数据过少,噪声过多,导致拟合的函数完美的预测训练集,但对新数据的测试集预测结果差。过度的拟合了训练数据,而没有考虑到泛化能力。
- dropout可以理解为它变相地减少了网络训练的参数
上图包含了GPU通信的部分。这是由当时GPU内存的限制引起的,作者使用两块GPU进行计算,因此分为了上下两部分。但是,以目前GPU的处理能力,单GPU足够了,因此其结构图可以如下所示:
经卷积后的矩阵尺寸大小计算公式为:
N = (W - F + 2P)/ S + 1
- 输入图片大小W*W
- Filter大小F*F
- 步长S
- padding的像素数P
padding [1,2] :特征矩阵左侧补1列零,右侧补2列零,上方补1行零,下方补2行零
import torch.nn as nn
import torch
class AlexNet(nn.Module):
def __init__(self, num_classes=1000, init_weights=False):
super(AlexNet, self).__init__()
self.features = nn.Sequential(
# 数据集比较小且为了加快训练速度,所以把卷积核的个数96变为原论文的一半48,准确率基本一样
nn.Conv2d(3, 48, kernel_size=11, stride=4, padding=2), # input[3, 224, 224] output[48, 55, 55]
nn.ReLU(inplace=True),
nn.MaxPool2d(kernel_size=3, stride=2), # output[48, 27, 27]
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),
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),
)
# 初始化权重
if init_weights:
self._initialize_weights()
def forward(self, x):
x = self.features(x)
x = torch.flatten(x, start_dim=1)
x = self.classifier(x)
return x
# 初始化权重函数
def _initialize_weights(self):
for m in self.modules():
# 判断该层结构是否是卷积层
if isinstance(m, nn.Conv2d):
nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
if m.bias is not None:
nn.init.constant_(m.bias, 0)
# 判断该层结构是否是全连接层
elif isinstance(m, nn.Linear):
nn.init.normal_(m.weight, 0, 0.01)
nn.init.constant_(m.bias, 0)
使用nn.ZeroPad2d((1,2,1,2)):左侧补1列,右侧补2列,上方补1行,下方补2行
import os
import sys
import json
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 tqdm import tqdm
from model import AlexNet
def main():
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
print("using {} device.".format(device))
data_transform = {
"train": transforms.Compose([transforms.RandomResizedCrop(224), # 随机裁剪
transforms.RandomHorizontalFlip(), # 随机翻转
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
image_path = os.path.join(data_root, "data_set", "flower_data") # flower data set path
assert os.path.exists(image_path), "{} path does not exist.".format(image_path)
train_dataset = datasets.ImageFolder(root=os.path.join(image_path, "train"),
transform=data_transform["train"])
train_num = len(train_dataset)
# {'daisy':0, 'dandelion':1, 'roses':2, 'sunflower':3, 'tulips':4}
# 获取分类名称对应的索引
flower_list = train_dataset.class_to_idx
# 调换键和值的顺序
cla_dict = dict((val, key) for key, val in flower_list.items())
# write dict into json file
# 将cla_dict编码成json的格式
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
nw = min([os.cpu_count(), batch_size if batch_size > 1 else 0, 8]) # number of workers
print('Using {} dataloader workers every process'.format(nw))
train_loader = torch.utils.data.DataLoader(train_dataset,
batch_size=batch_size, shuffle=True,
num_workers=nw)
validate_dataset = datasets.ImageFolder(root=os.path.join(image_path, "val"),
transform=data_transform["val"])
val_num = len(validate_dataset)
validate_loader = torch.utils.data.DataLoader(validate_dataset,
batch_size=4, shuffle=False,
num_workers=nw)
print("using {} images for training, {} images for validation.".format(train_num,
val_num))
# test_data_iter = iter(validate_loader)
# test_image, test_label = test_data_iter.__next__()
#
# 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)
loss_function = nn.CrossEntropyLoss()
# pata = list(net.parameters()) # 查看模型的参数
optimizer = optim.Adam(net.parameters(), lr=0.0002)
epochs = 10
save_path = './AlexNet.pth'
best_acc = 0.0 # 最佳准确率
train_steps = len(train_loader)
for epoch in range(epochs):
# train
net.train()
running_loss = 0.0
train_bar = tqdm(train_loader, file=sys.stdout)
for step, data in enumerate(train_bar):
images, labels = data
optimizer.zero_grad()
outputs = net(images.to(device))
loss = loss_function(outputs, labels.to(device))
loss.backward()
optimizer.step()
# print statistics
running_loss += loss.item()
train_bar.desc = "train epoch[{}/{}] loss:{:.3f}".format(epoch + 1,
epochs,
loss)
# validate
net.eval()
acc = 0.0 # accumulate accurate number / epoch
with torch.no_grad():
val_bar = tqdm(validate_loader, file=sys.stdout)
for val_data in val_bar:
val_images, val_labels = val_data
outputs = net(val_images.to(device))
predict_y = torch.max(outputs, dim=1)[1]
acc += torch.eq(predict_y, val_labels.to(device)).sum().item()
val_accurate = acc / val_num
print('[epoch %d] train_loss: %.3f val_accuracy: %.3f' %
(epoch + 1, running_loss / train_steps, val_accurate))
if val_accurate > best_acc:
best_acc = val_accurate
torch.save(net.state_dict(), save_path)
print('Finished Training')
if __name__ == '__main__':
main()
json.dumps(cla_dict, indent=4)
tqdm(train_loader, file=sys.stdout)
Tqdm是python进度条库,可以在Python长循环中添加一个进度提示信息。用户只需要封装任意的迭代器,是一个快速、扩展性强的进度条工具库。
tqdm用在dataloader上其实是对每个batch和batch总数做的进度条
import os
import json
import torch
from PIL import Image
from torchvision import transforms
import matplotlib.pyplot as plt
from model import AlexNet
def main():
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
data_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_path = "../tulip.jpg"
assert os.path.exists(img_path), "file: '{}' dose not exist.".format(img_path)
img = Image.open(img_path)
plt.imshow(img)
# [N, C, H, W]
img = data_transform(img)
# expand batch dimension
img = torch.unsqueeze(img, dim=0)
# read class_indict
json_path = './class_indices.json'
assert os.path.exists(json_path), "file: '{}' dose not exist.".format(json_path)
with open(json_path, "r") as f:
class_indict = json.load(f)
# create model
model = AlexNet(num_classes=5).to(device)
# load model weights
weights_path = "./AlexNet.pth"
assert os.path.exists(weights_path), "file: '{}' dose not exist.".format(weights_path)
model.load_state_dict(torch.load(weights_path))
model.eval()
with torch.no_grad():
# predict class
output = torch.squeeze(model(img.to(device))).cpu()
predict = torch.softmax(output, dim=0)
predict_cla = torch.argmax(predict).numpy()
print_res = "class: {} prob: {:.3}".format(class_indict[str(predict_cla)],
predict[predict_cla].numpy())
plt.title(print_res)
for i in range(len(predict)):
print("class: {:10} prob: {:.3}".format(class_indict[str(i)],
predict[i].numpy()))
plt.show()
if __name__ == '__main__':
main()