1、model.py
import torch.nn as nn
import torch
# 【1】定义18/34层的残差结构;这个模块不仅需要有实线残差功能,还要有虚线的功能
class BasicBlock(nn.Module):
# 18/34层的残差结构,他的第一层与第二层的卷积核的个数是一样的
expansion = 1 # 对应的残差结构主分支上所采用的卷积核的个数有没有发生变化。
# downsample所对应的就是虚线的残差结构---shortcut,1*1的卷积层;out_channel主分支上卷积核的个数(输出深度)
# in_channel 输入的深度
# conv3_x---conv5_x的第一层残差结构,都是虚线残差结构--》每一层都起到降维的作用
def __init__(self, in_channel, out_channel, stride=1, downsample=None):
super(BasicBlock, self).__init__()
# stride是传入的参数,默认=1,时对应的是实线残差结构,=2时对应虚线残差结构---》h w 变为一半; bias=False不使用偏置参数,因为BN
# 输出的深度=in_channel(传入的),out_channel(传入的)
self.conv1 = nn.Conv2d(in_channels=in_channel, out_channels=out_channel,
kernel_size=3, stride=stride, padding=1, bias=False)
self.bn1 = nn.BatchNorm2d(out_channel)
self.relu = nn.ReLU()
# 无论是实线还是虚线残差结构,第二层卷积中stride=1
# 输入是conv1的输出out_channel,卷积核的个数是out_channel
self.conv2 = nn.Conv2d(in_channels=out_channel, out_channels=out_channel,
kernel_size=3, stride=1, padding=1, bias=False)
self.bn2 = nn.BatchNorm2d(out_channel)
self.downsample = downsample # 默认=none
# 【2】定义前向传播
def forward(self, x):
identity = x # identity捷径分支上的输出值
# 如果有输入下采样函数(not None),则对应的是虚线的残差结构x输入--》得到捷径分支的输出
if self.downsample is not None:
identity = self.downsample(x)
# 主线的输入
out = self.conv1(x)
out = self.bn1(out)
out = self.relu(out)
out = self.conv2(out)
out = self.bn2(out)
# 主分支与捷径分支相加
out += identity
out = self.relu(out)
return out
#【3】定义50/101/152层的残差结构
class Bottleneck(nn.Module):
expansion = 4 #conv2_x--conv5_x中,第三层的卷积核的个数是前两层的4倍
def __init__(self, in_channel, out_channel, stride=1, downsample=None):
super(Bottleneck, self).__init__()
# 卷积核的个数out_channel(输入的)指的是残差结构中第一,第二层的卷积核的个数
self.conv1 = nn.Conv2d(in_channels=in_channel, out_channels=out_channel,
kernel_size=1, stride=1, bias=False) # squeeze channels
self.bn1 = nn.BatchNorm2d(out_channel)
# -----------------------------------------
# 卷积层第二层,实现残差结构中stride=1,虚线残差中stride=2,stride=stride是传入参数,默认为1
self.conv2 = nn.Conv2d(in_channels=out_channel, out_channels=out_channel,
kernel_size=3, stride=stride, bias=False, padding=1)
self.bn2 = nn.BatchNorm2d(out_channel)
# -----------------------------------------
# out_channels=out_channel*self.expansion 卷积核的个数是上一层卷积核的4倍
self.conv3 = nn.Conv2d(in_channels=out_channel, out_channels=out_channel*self.expansion,
kernel_size=1, stride=1, bias=False) # unsqueeze channels
self.bn3 = nn.BatchNorm2d(out_channel*self.expansion)
self.relu = nn.ReLU(inplace=True)
self.downsample = downsample
# 【4】定义前向传播
def forward(self, x):
identity = x
if self.downsample is not None:
identity = self.downsample(x)
out = self.conv1(x)
out = self.bn1(out)
out = self.relu(out)
out = self.conv2(out)
out = self.bn2(out)
out = self.relu(out)
out = self.conv3(out)
out = self.bn3(out)
out += identity
out = self.relu(out)
return out
# 【5】整个框架的部分
class ResNet(nn.Module):
# block 所对应的就是残差结构, blocks_num 所使用残差结构的数目 是一个列表结构, include_top=True方便以后在resnet上搭建更加复杂的网络
def __init__(self, block, blocks_num, num_classes=1000, include_top=True):
super(ResNet, self).__init__()
self.include_top = include_top
self.in_channel = 64
# 是通过第一层的池化的深度,--》所有层残差结构在maxpool后输出都为64
# 对应表格7*7卷积层,第一层使用的卷积核的个数是64个=self.in_channel
self.conv1 = nn.Conv2d(3, self.in_channel, kernel_size=7, stride=2,
padding=3, bias=False)
self.bn1 = nn.BatchNorm2d(self.in_channel)
self.relu = nn.ReLU(inplace=True)
self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
# conv2_x---conv5_x;是通过self._make_layer函数生成的;64 128 256 等都是conv2_x---conv5_x第一层卷积核的 个数
self.layer1 = self._make_layer(block, 64, blocks_num[0])
self.layer2 = self._make_layer(block, 128, blocks_num[1], stride=2)
self.layer3 = self._make_layer(block, 256, blocks_num[2], stride=2)
self.layer4 = self._make_layer(block, 512, blocks_num[3], stride=2)
if self.include_top:
self.avgpool = nn.AdaptiveAvgPool2d((1, 1)) # output size = (1, 1)
self.fc = nn.Linear(512 * block.expansion, num_classes)
for m in self.modules():
if isinstance(m, nn.Conv2d):
nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
# block(BasicBlock/Bottleneck) , channel 残差结构中第一层卷积核个数, block_num 该层(conv2_X)一共有多少个残差结构
# 34层中 conv_2x是3个, stride=1
#
# stride从第二层开始就变成2,所以都会生层虚线残差结构
def _make_layer(self, block, channel, block_num, stride=1):
downsample = None
# 对于第1层stride默认为1,in_channel=64(定义的)是否与channel * block.expansion相等。
# 对于layer1是不满足的,64=64*1 ;所以对于18/34层会直接跳过这个语句;
# 对于50/101/152是满足,则会进入语句生成downsample---》在conv2_x所对应的一系列残差结构的第一层其实也是虚线的残差结构,
# 但是只需要调整特征矩阵的深度,h w 则不需要调整。
# 对于conv3_x---conv5_x对应的第一层虚线残差结构,不仅要调整深度,还要将h w 变为原来一半
if stride != 1 or self.in_channel != channel * block.expansion:
downsample = nn.Sequential(
# 捷径分支*4
nn.Conv2d(self.in_channel, channel * block.expansion, kernel_size=1, stride=stride, bias=False),
nn.BatchNorm2d(channel * block.expansion))
layers = []
# 将第一层的残差结构添加进layers,channel残差结构所对应分支上的第一个卷积层的卷积核的个数
# downsample=downsample 对于18/34层的网络由于他是=none,所对应的就是一个实线的残差结构
# 对于50/101/152层而言它的downsample是我们定义好的深度*4,h w不变---》所对应的就是虚线残差结构
# 对于layer1来说stride=1
layers.append(block(self.in_channel, channel, downsample=downsample, stride=stride))
self.in_channel = channel * block.expansion
# 遍历实线残差结构,无论是18/152的残差结构中第二层卷积开始都是实线结构
# 1 从1开始,因为第一层已经搭建好了, block_num
for _ in range(1, block_num):
layers.append(block(self.in_channel, channel))
# 把列表转换成非关键字参数传进去
return nn.Sequential(*layers)
# 【6】总体的前向传播
def forward(self, x):
x = self.conv1(x)
x = self.bn1(x)
x = self.relu(x)
x = self.maxpool(x)
x = self.layer1(x)
x = self.layer2(x)
x = self.layer3(x)
x = self.layer4(x)
if self.include_top:
x = self.avgpool(x)
x = torch.flatten(x, 1)
x = self.fc(x)
return x
def resnet34(num_classes=1000, include_top=True):
return ResNet(BasicBlock, [3, 4, 6, 3], num_classes=num_classes, include_top=include_top)
def resnet101(num_classes=1000, include_top=True):
return ResNet(Bottleneck, [3, 4, 23, 3], num_classes=num_classes, include_top=include_top)
2、train.py
import torch
import torch.nn as nn
from torchvision import transforms, datasets
import json
import matplotlib.pyplot as plt
import os
import torch.optim as optim
from model import resnet34, resnet101
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
print(device)
data_transform = {
"train": transforms.Compose([transforms.RandomResizedCrop(224),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])]),
"val": transforms.Compose([transforms.Resize(256),
transforms.CenterCrop(224),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])])}
data_root = os.path.abspath(os.path.join(os.getcwd(), "../..")) # get data root path
image_path = data_root + "/data_set/gabage_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 = 16
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=False,
num_workers=0)
# 【1】net = GoogLeNet(num_classes=5, aux_logits=True, init_weights=True)
# net.to(device)
# 【2】 net = AlexNet(num_classes=12, init_weights=True)
# 网络指定到规定的设备中
# net.to(device)
net = resnet34(num_classes=12)
net.to(device)
# {net = resnet34()
# # # net.load_state_dict(torch.load;load pretrain weights
# model_weight_path = "./resnet34-333f7ec4.pth"
# missing_keys, unexpected_keys = net.load_state_dict(torch.load(model_weight_path), strict=False)
# # # for param in net.parameters():
# # # param.requires_grad = False
# # # change fc layer structure
# inchannel = net.fc.in_features
# net.fc = nn.Linear(inchannel, 5)
# net.to(device)}
loss_function = nn.CrossEntropyLoss()
optimizer = optim.Adam(net.parameters(), lr=0.0001)
best_acc = 0.0
save_path = './resNet34.pth'
for epoch in range(200):
# train
net.train()
running_loss = 0.0
for step, data in enumerate(train_loader, start=0):
images, labels = data
optimizer.zero_grad()
logits = net(images.to(device))
loss = loss_function(logits, 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}%[{}->{}]{:.4f}".format(int(rate*100), a, b, loss), end="")
print()
# validate
net.eval()
acc = 0.0 # accumulate accurate number / epoch
with torch.no_grad():
for data_test in validate_loader:
test_images, test_labels = data_test
outputs = net(test_images.to(device)) # eval model only have last output layer
# loss = loss_function(outputs, test_labels)
predict_y = torch.max(outputs, dim=1)[1]
acc += (predict_y == test_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')
3、predict.py
import torch
from model import resnet34
from PIL import Image
from torchvision import transforms
import matplotlib.pyplot as plt
import json
# 要进行和训练过程一样的预处理
data_transform = transforms.Compose(
[transforms.Resize(256),
transforms.CenterCrop(224),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])])
# 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 = resnet34(num_classes=5)
# load model weights
model_weight_path = "./resNet34.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)], predict[predict_cla].numpy())
plt.show()