本篇博客是学习B站霹雳吧啦Wz教学视频的总结
本节所用到的程序和教学视频链接:
网络结构
-
1.提出inception 结构
-
初始版本
- 先前层得到的特征矩阵同时输入到3个卷积层和一个池化层中进行处理
- 然后按照深度进行拼接,得到输出特征矩阵,其中四个框得到的结果其宽和高必须相同
-
进阶版本
- 与初级版本相比,进阶版除了 1 × 1 1\times1 1×1的卷积层外,其他三个都与一个 1 × 1 1\times 1 1×1的卷积核进行串联,这三个 1 × 1 1 \times 1 1×1起到了一个降维的功能
-
-
2.辅助分类器
* AveragePool 平均池化下采样操作,池化核是5,步长是3
* Conv 卷积层 卷积核是1,步长是1
* FC 全连接层
程序
程序结构
model.py
import torch.nn as nn
import torch
import torch.nn.functional as F
class GoogLeNet(nn.Module):
def __init__(self, num_classes=1000, aux_logits=True, init_weights=False):
super(GoogLeNet, self).__init__()
self.aux_logits = aux_logits
self.conv1 = BasicConv2d(3, 64, kernel_size=7, stride=2, padding=3)
self.maxpool1 = nn.MaxPool2d(3, stride=2, ceil_mode=True)
self.conv2 = BasicConv2d(64, 64, kernel_size=1)
self.conv3 = BasicConv2d(64, 192, kernel_size=3, padding=1)
self.maxpool2 = nn.MaxPool2d(3, stride=2, ceil_mode=True)
self.inception3a = Inception(192, 64, 96, 128, 16, 32, 32)
self.inception3b = Inception(256, 128, 128, 192, 32, 96, 64)
self.maxpool3 = nn.MaxPool2d(3, stride=2, ceil_mode=True)
self.inception4a = Inception(480, 192, 96, 208, 16, 48, 64)
self.inception4b = Inception(512, 160, 112, 224, 24, 64, 64)
self.inception4c = Inception(512, 128, 128, 256, 24, 64, 64)
self.inception4d = Inception(512, 112, 144, 288, 32, 64, 64)
self.inception4e = Inception(528, 256, 160, 320, 32, 128, 128)
self.maxpool4 = nn.MaxPool2d(3, stride=2, ceil_mode=True)
self.inception5a = Inception(832, 256, 160, 320, 32, 128, 128)
self.inception5b = Inception(832, 384, 192, 384, 48, 128, 128)
if self.aux_logits:
self.aux1 = InceptionAux(512, num_classes)
self.aux2 = InceptionAux(528, num_classes)
self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
self.dropout = nn.Dropout(0.4)
self.fc = nn.Linear(1024, num_classes)
if init_weights:
self._initialize_weights()
def forward(self, x):
# N x 3 x 224 x 224
x = self.conv1(x)
# N x 64 x 112 x 112
x = self.maxpool1(x)
# N x 64 x 56 x 56
x = self.conv2(x)
# N x 64 x 56 x 56
x = self.conv3(x)
# N x 192 x 56 x 56
x = self.maxpool2(x)
# N x 192 x 28 x 28
x = self.inception3a(x)
# N x 256 x 28 x 28
x = self.inception3b(x)
# N x 480 x 28 x 28
x = self.maxpool3(x)
# N x 480 x 14 x 14
x = self.inception4a(x)
# N x 512 x 14 x 14
if self.training and self.aux_logits: # eval model lose this layer
aux1 = self.aux1(x)
x = self.inception4b(x)
# N x 512 x 14 x 14
x = self.inception4c(x)
# N x 512 x 14 x 14
x = self.inception4d(x)
# N x 528 x 14 x 14
if self.training and self.aux_logits: # eval model lose this layer
aux2 = self.aux2(x)
x = self.inception4e(x)
# N x 832 x 14 x 14
x = self.maxpool4(x)
# N x 832 x 7 x 7
x = self.inception5a(x)
# N x 832 x 7 x 7
x = self.inception5b(x)
# N x 1024 x 7 x 7
x = self.avgpool(x)
# N x 1024 x 1 x 1
x = torch.flatten(x, 1)
# N x 1024
x = self.dropout(x)
x = self.fc(x)
# N x 1000 (num_classes)
if self.training and self.aux_logits: # eval model lose this layer
return x, aux2, aux1
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')
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)
nn.init.constant_(m.bias, 0)
class Inception(nn.Module):
def __init__(self, in_channels, ch1x1, ch3x3red, ch3x3, ch5x5red, ch5x5, pool_proj):
super(Inception, self).__init__()
self.branch1 = BasicConv2d(in_channels, ch1x1, kernel_size=1)
self.branch2 = nn.Sequential(
BasicConv2d(in_channels, ch3x3red, kernel_size=1),
BasicConv2d(ch3x3red, ch3x3, kernel_size=3, padding=1) # 保证输出大小等于输入大小
)
self.branch3 = nn.Sequential(
BasicConv2d(in_channels, ch5x5red, kernel_size=1),
BasicConv2d(ch5x5red, ch5x5, kernel_size=5, padding=2) # 保证输出大小等于输入大小
)
self.branch4 = nn.Sequential(
nn.MaxPool2d(kernel_size=3, stride=1, padding=1),
BasicConv2d(in_channels, pool_proj, kernel_size=1)
)
def forward(self, x):
branch1 = self.branch1(x)
branch2 = self.branch2(x)
branch3 = self.branch3(x)
branch4 = self.branch4(x)
outputs = [branch1, branch2, branch3, branch4]
return torch.cat(outputs, 1)
class InceptionAux(nn.Module):
def __init__(self, in_channels, num_classes):
super(InceptionAux, self).__init__()
self.averagePool = nn.AvgPool2d(kernel_size=5, stride=3)
self.conv = BasicConv2d(in_channels, 128, kernel_size=1) # output[batch, 128, 4, 4]
self.fc1 = nn.Linear(2048, 1024)
self.fc2 = nn.Linear(1024, num_classes)
def forward(self, x):
# aux1: N x 512 x 14 x 14, aux2: N x 528 x 14 x 14
x = self.averagePool(x)
# aux1: N x 512 x 4 x 4, aux2: N x 528 x 4 x 4
x = self.conv(x)
# N x 128 x 4 x 4
x = torch.flatten(x, 1)
x = F.dropout(x, 0.5, training=self.training)
# N x 2048
x = F.relu(self.fc1(x), inplace=True)
x = F.dropout(x, 0.5, training=self.training)
# N x 1024
x = self.fc2(x)
# N x num_classes
return x
class BasicConv2d(nn.Module):
def __init__(self, in_channels, out_channels, **kwargs):
super(BasicConv2d, self).__init__()
self.conv = nn.Conv2d(in_channels, out_channels, **kwargs)
self.relu = nn.ReLU(inplace=True)
def forward(self, x):
x = self.conv(x)
x = self.relu(x)
return x
- BasicConv2d 类需要提供in_channels和out_channels,以及其他参数如:(stride,padding),该类将Conv2d和ReLu合并
- Inception类就是GoogLeNet网络的特性,该类实现了inception进阶版的结构,需要提供七个结构的参数
- torch.cat 可以实现拼接,即将数组中的不同元素按照指定的维度拼接在一起,在 上述程序中,dim=1是在 深度方向进行拼接,为确保拼接的顺利进行,需要4个输出结果的高和宽相同
- x=F.dropout(x, 0.5, training=self.training) self.training 让该句只在网络处在训练模式下运行
- self.maxpool1=nn.MaxPool2d(3,stride=2,ceil_mode=True) ceil_mode是向下取整
- self.avgpool = nn.AdaptiveAvgPool2d((1,1)) 自适应平均池化,给定输出的长和宽,会将任意大小的输入池化为事先设定的长和宽
train.py
import os
import json
import torch
import torch.nn as nn
from torchvision import transforms, datasets
import torch.optim as optim
from tqdm import tqdm
from model import GoogLeNet
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 for validation.".format(train_num,
val_num))
# test_data_iter = iter(validate_loader)
# test_image, test_label = test_data_iter.next()
# net = torchvision.models.googlenet(num_classes=5)
# model_dict = net.state_dict()
# pretrain_model = torch.load("googlenet.pth")
# del_list = ["aux1.fc2.weight", "aux1.fc2.bias",
# "aux2.fc2.weight", "aux2.fc2.bias",
# "fc.weight", "fc.bias"]
# pretrain_dict = {k: v for k, v in pretrain_model.items() if k not in del_list}
# model_dict.update(pretrain_dict)
# net.load_state_dict(model_dict)
net = GoogLeNet(num_classes=5, aux_logits=True, init_weights=True)
net.to(device)
loss_function = nn.CrossEntropyLoss()
optimizer = optim.Adam(net.parameters(), lr=0.0003)
epochs = 30
best_acc = 0.0
save_path = './googleNet.pth'
train_steps = len(train_loader)
for epoch in range(epochs):
# train
net.train()
running_loss = 0.0
train_bar = tqdm(train_loader)
for step, data in enumerate(train_bar):
images, labels = data
optimizer.zero_grad()
logits, aux_logits2, aux_logits1 = net(images.to(device))
loss0 = loss_function(logits, labels.to(device))
loss1 = loss_function(aux_logits1, labels.to(device))
loss2 = loss_function(aux_logits2, labels.to(device))
loss = loss0 + loss1 * 0.3 + loss2 * 0.3
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)
for val_data in val_bar:
val_images, val_labels = val_data
outputs = net(val_images.to(device)) # eval model only have last output layer
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()
- logits, aux_logits2, aux_logits1 = net(images.to(device)),网络实例化过程中aux_logits=True,意味需要辅助辅助分类器,所以会得到三个结果
predict.py
import os
import json
import torch
from PIL import Image
from torchvision import transforms
import matplotlib.pyplot as plt
from model import GoogLeNet
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)
json_file = open(json_path, "r")
class_indict = json.load(json_file)
# create model
model = GoogLeNet(num_classes=5, aux_logits=False).to(device)
# load model weights
weights_path = "./googleNet.pth"
assert os.path.exists(weights_path), "file: '{}' dose not exist.".format(weights_path)
missing_keys, unexpected_keys = model.load_state_dict(torch.load(weights_path, map_location=device),
strict=False)
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)
print(print_res)
plt.show()
if __name__ == '__main__':
main()
- model = GoogLeNet(num_classes=5, aux_logits=False).to(device) 网络在使用的过程中是不需要辅助分类器的,所以aux_logits=False
- missing_keys, unexpected_keys = model.load_state_dict(torch.load(weights_path,map_location=device),strict=False)
- 我们不需要辅助分类器,但是训练结果保存了辅助分类器的相关参数,我们需要对参数进行取舍
- strict=False 就是为了应对这一情况设置的参数,False:网络只提取需要的参数
- torch.load(weights_path,map_location=device) map_location=device将参数初始化到device上