致谢：霹雳吧啦Wz：https://space.bilibili.com/18161609
目录
致谢：霹雳吧啦Wz：https://space.bilibili.com/18161609
1 本次要点
1.1 Python库语法
- python中定义函数，参数分为一般参数，默认参数，非关键字参数和关键字参数
- 非关键字参数（或称可变参数）*args
- 定义：可变参数就是传入的参数个数是可变的，可以是0个，1个，2个，……很多个。
- 作用：就是可以一次给函数传很多的参数
- 特征：*args
- 关键字参数**kw
- 定义：关键字参数允许你传入0个或任意个含参数名的参数，这些关键字参数在函数内部自动组装为一个dict。在调用函数时，可以只传入必选参数。
- 作用：扩展函数的功能
- 特征：**kw
- 非关键字参数（或称可变参数）*args
1.2 深度学习理论
- 感受野：在卷积神经网络中，决定某一层输出结果中一个元素所对应的输入层的区域大小，被称作 感受野(receptive field)。
- imageNet所有图片的RGB均值：[123.68, 116.78, 103.94]。如果使用ImageNet的预训练模型，那么后续训练时图片要减去此均值
- 使用ImageNet预训练模型的标准化方法：transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])。
- 不使用预训练模型：transforms.Normalize([0.5, 0.5, 0.5], [0.5, 0.5, 0.5])
2 网络简介
2.1 历史意义
- VGG在2014年由牛津大学著名研究组VGG (Visual Geometry Group) 提出，斩获该年ImageNet竞赛中 Localization Task (定位任务) 第一名 和 Classification Task (分类任务) 第二名。
2.2 网络亮点
- 通过堆叠（中间没有跟池化层）多个3x3的卷积核来替代大尺度卷积核（目的：减少网络参数量）（2层3*3卷积代替1层5*5卷积，3层3*3卷积代替1层7*7卷积）
2.3 网络架构
3 代码结构
- mode.py
- train.py
- predict.py
3.1 mode.py
import torch.nn as nn
import torch
class VGG(nn.modules):
def __init__(self, features, class_num=1000, init_weights=False):
super(VGG, self).__init__()
self.features = features
self.classifier = nn.Sequential(
nn.Dropout(p=0.5),
nn.Linear(512*7*7, 2048),
nn.ReLU(True),
nn.Dropout(p=0.5),
nn.Linear(2048, 2048),
nn.ReLU(True),
nn.Linear(2048, class_num)
)
if init_weights:
self._initialize_weights()
def forward(self, x):
# N * 3 * 224 * 224
x = self.features(x)
# N * 512 * 7 * 7
x = torch.flatten(x, start_dim=1)
# N * 512 * 7 * 7
x = self.classifier(x)
return x
def _initialize_weights(self):
for m in self.modules():
if isinstance(m, nn.Conv2d):
# nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
nn.init.xavier_normal_(m.weight)
if m.bias is not None:
nn.init.constant_(m.bias, 0)
elif isinstance(m, nn.Linear):
nn.init.xavier_uniform_(m.weight)
# nn.init.normal_(m.weight, 0, 0.01)
nn.init.constant_(m.bias, 0)
def make_features(cfg:list): #传入一个配置变量，list类型
layers = []
in_channels = 3
for v in cfg:
if v == 'M':
layers += [nn.MaxPool2d(kernel_size=2, stride=2)]
else:
conv2d = nn.Conv2d(in_channels, v, kernel_size=3, padding=1)
layers += [conv2d, nn.ReLU(inplace=True)]
in_channels = v
return nn.Sequential(*layers) # “*”：通过非关键字参数形式传入进去。
# 数字代表卷积核个数。M代表池化层。
cfgs = {
'vgg11': [64, 'M', 128, 'M', 256, 256, 'M', 512, 512, 'M', 512, 512, 'M'],
'vgg13': [64, 64, 'M', 128, 128, 'M', 256, 256, 'M', 512, 512, 'M', 512, 512, 'M'],
'vgg16': [64, 64, 'M', 128, 128, 'M', 256, 256, 256, 'M', 512, 512, 512, 'M', 512, 512, 512, 'M'],
'vgg19': [64, 64, 'M', 128, 128, 'M', 256, 256, 256, 256, 'M', 512, 512, 512, 512, 'M', 512, 512, 512, 512, 'M'],
}
# 此函数功能：实例化VGG类
#**kwargs可变长度的字典变量，这个字典变量可能就包含分类个数、是否初始化等。
#**kwargs意思是该函数可以接受任意多个输入变量。
def vgg(model_name="vgg16", **kwargs):
try:
cfg = cfgs[model_name]
except:
print("Warning: model number {} not in cfgs dict!".format(model_name)
exit(-1)
model = VGG(make_features(cfg), **kwargs)
return model
3.2 train.py
import torch.nn as nn
from torchvision import transforms, datasets
import json
import os
import torch.optim as optim
from model import vgg
import torch
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),
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)),
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}
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
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=batch_size, shuffle=False,
num_workers=nw)
print("using {} images for training, {} images fot validation.".format(train_num,
val_num))
# test_data_iter = iter(validate_loader)
# test_image, test_label = test_data_iter.next()
model_name = "vgg16"
net = vgg(model_name=model_name, num_classes=5, init_weights=True)
net.to(device)
loss_function = nn.CrossEntropyLoss()
optimizer = optim.Adam(net.parameters(), lr=0.0001)
best_acc = 0.0
save_path = './{}Net.pth'.format(model_name)
for epoch in range(30):
# train
net.train()
running_loss = 0.0
for step, data in enumerate(train_loader, start=0):
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()
# print train process
rate = (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()
# validate
net.eval()
acc = 0.0 # accumulate accurate number / epoch
with torch.no_grad():
for val_data in validate_loader:
val_images, val_labels = val_data
optimizer.zero_grad()
outputs = 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_num
if val_accurate > best_acc:
best_acc = val_accurate
torch.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')
if __name__ == '__main__':
main()3.3 predict.py
import torch
from model import vgg
from PIL import Image
from torchvision import transforms
import matplotlib.pyplot as plt
import json
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 = Image.open("../tulip.jpg")
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 = vgg(model_name="vgg16", num_classes=5)
# load model weights
model_weight_path = "./vgg16Net.pth"
model.load_state_dict(torch.load(model_weight_path))
model.eval()
with torch.no_grad():
# predict class
output = torch.squeeze(model(img))
predict = torch.softmax(output, dim=0)
predict_cla = torch.argmax(predict).numpy()
print(class_indict[str(predict_cla)])
plt.show()
6647
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
