import torch
from torch import optim, nn
import visdom
import torchvision
from torch.utils.data import DataLoader
from DIYdata_loader import DIYData_loader
from GoogLeNet import GoogLeNet
batchsz = 20
picture_resize = 224
lr = 1e-3
epochs = 10
device = torch.device('cuda')
torch.manual_seed(1234)
train_db = DIYData_loader('D:\python pycharm learning\清华大佬课程\青光眼GooLeNet\青光眼分类', picture_resize, mode='train')
val_db = DIYData_loader('D:\python pycharm learning\清华大佬课程\青光眼GooLeNet\青光眼分类', picture_resize, mode='val')
test_db = DIYData_loader('D:\python pycharm learning\清华大佬课程\青光眼GooLeNet\青光眼分类', picture_resize, mode='test')
train_loader = DataLoader(train_db, batch_size=batchsz, shuffle=True,
num_workers=4)
val_loader = DataLoader(val_db, batch_size=batchsz, num_workers=2)
test_loader = DataLoader(test_db, batch_size=batchsz, num_workers=2)
viz = visdom.Visdom()
def evalute(model, loader):
model.eval()
correct = 0
total = len(loader.dataset)
for x, y in loader:
x, y = x.to(device), y.to(device)
with torch.no_grad():
logits = model(x)
pred = logits.argmax(dim=1)
correct += torch.eq(pred, y).sum().float().item()
return correct / total
def main():
model = GoogLeNet(3).to(device)
optimizer = optim.Adam(model.parameters(),lr=lr)
criteon = nn.CrossEntropyLoss()
best_acc,best_epoch =0, 0
global_step = 0
viz.line([0],[-1], win='loss',opts = dict(title='loss'))
viz.line([0],[-1], win='val_acc', opts=dict(title='val_acc'))
for epoch in range(epochs):
for step, (x,y) in enumerate(train_loader):
#x:[b,3,224,224],y :[b]
x,y = x.to(device),y.to(device)
model.train()
logits = model(x)
loss = criteon(logits,y)
optimizer.zero_grad()
loss.backward()
optimizer.step()
viz.line([loss.item()], [global_step], win='loss', update = 'append')
global_step+=1
if epoch %1 ==0:
val_acc = evalute(model,val_loader)
if val_acc > best_acc:
best_epoch =epoch
best_acc =val_acc
torch.save(model.state_dict(),'best.mdl')
viz.line([val_acc], [global_step], win='val_acc', update='append')
print('best acc:',best_acc,'best epoch:',best_epoch)
model.load_state_dict(torch.load('best.mdl'))
print('loaded from ckpt!')
test_acc = evalute(model,test_loader)
print('test acc:', test_acc)
if __name__=='__main__':
main()
# 数据集共有364张图:Glaucoma:32,Normal:225,Suspect Glaucoma:107
import torch
import os, glob
import random, csv
from torch.utils.data import Dataset, DataLoader
from PIL import Image
from torchvision import transforms
# 自定义数据加载类
class DIYData_loader(Dataset):
def __init__(self, root, resize, mode): # root:文件所在目录,resize:图像分辨率调整一致,mode:当前类何功能
super(DIYData_loader, self).__init__()
self.root = root
self.resize = resize
self.name2label = {} # 对每个加载的文件进行编码:'bulbasaur': 0, 'charmander': 1, 'mewtwo': 2, 'pikachu': 3, 'squirtle': 4
for name in sorted(os.listdir((os.path.join(root)))): # 对指定root中的文件进行排序
if not os.path.isdir(os.path.join(root, name)):
continue
self.name2label[name] = len(self.name2label.keys()) # keys返回列表当中的value,len计算列表长度
#print(self.name2label) # 根据文件顺序,以idx:文件名,vlaue:0,1,2,3,4,生成列表
# images labels
self.images, self.labels = self.load_csv('images.csv') # load_csv要么先创建images.csv,要么直接读取images.csv,
#print('data_len:',len(self.images))
if mode == 'train': # train dataset 60% of ALL DATA
self.images = self.images[:int(0.6 * len(self.images))]
self.labels = self.labels[:int(0.6 * len(self.labels))]
elif mode == 'validation': # val dataset 60%-80% of ALL DATA
self.images = self.images[int(0.6 * len(self.images)):int(0.8 * len(self.images))]
self.labels = self.labels[int(0.6 * len(self.labels)):int(0.8 * len(self.labels))]
else: # test dataset 80%-100% of ALL DATA
self.images = self.images[int(0.8 * len(self.images)):int(len(self.images))]
self.labels = self.labels[int(0.8 * len(self.labels)):int(len(self.labels))]
# images[0]: D:\python pycharm learning\清华大佬课程\fisrt\pokemon\mewtwo\00000081.png
# #labels[0]:2
# images 还是图片的地址列表,需要__getitem__继续转换
# image,label 不能把所有图片全部加载到内存,可能会爆内存
def load_csv(self, filename): # 生成,读取filename文件
# filename 不存在:生成filename
if not os.path.exists(os.path.join(self.root, filename)):
images = []
for name in self.name2label.keys():
# .../pokemen/mewtwo/00001.png 加载进images列表
# 实际上是加载每张图片的地址
images += glob.glob(os.path.join(self.root, name, '*.png'))
images += glob.glob(os.path.join(self.root, name, '*.jpg'))
images += glob.glob(os.path.join(self.root, name, '*.jpeg'))
#print(len(images), images[0])
random.shuffle(images)
with open(os.path.join(self.root, filename), mode='w', newline='') as f:
writer = csv.writer(f)
for img in images: # .....\bulbasaur\00000000.png
name = img.split(os.sep)[-2] # 指:bulbasaur 图片真实类别
label = self.name2label[name] # 在name2label列表根据name找出对应的value:0,1...
# .....\bulbasaur\00000000.png , 0
writer.writerow([img, label])
print('writen into csv file:', filename)
# filename 存在:直接读取filename
images, labels = [], []
with open(os.path.join(self.root, filename)) as f:
reader = csv.reader(f)
for row in reader:
# '...pokemon\bulbasaur\00000000.png', 0
img, label = row
label = int(label)
images.append(img)
labels.append(label)
assert len(images) == len(labels)
return images, labels
def __len__(self):
return len(self.images)
def denormalize(self, x_hat): # 对已经进行规范化处理的totensor,去除规范化
mean = [0.485, 0.456, 0.406]
std = [0.229, 0.224, 0.225]
# x_hat = (x-mean)/std
# x = x_hat*std +mean
# x:[c,h,w]
# mean:[3]=>[3,1,1]
mean = torch.tensor(mean).unsqueeze(1).unsqueeze(1)
std = torch.tensor(std).unsqueeze(1).unsqueeze(1)
x = x_hat * std + mean
return x
def __getitem__(self, idx):
pass
# idx~[0~len(images)]
# self.iamges,self.labels
# images[0]: D:\python pycharm learning\清华大佬课程\fisrt\pokemon\mewtwo\00000081.png
# #labels[0]:2
img, label = self.images[idx], self.labels[idx]
tf = transforms.Compose([
lambda x: Image.open(x).convert('RGB'), # string image => image data
transforms.Resize((int(self.resize * 1.25), int(self.resize * 1.25))), # 压缩到稍大
transforms.RandomRotation(20), # 图片旋转,增加图片的复杂度,但是又不会使网络太复杂
transforms.CenterCrop(self.resize), # 可能会有其他的底存在
transforms.ToTensor(),
#transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
transforms.Normalize(mean=[0, 0, 0], std=[1, 1, 1])
# R mean:0.854,std:0.229
])
img = tf(img)
label = torch.tensor(label)
# Pokemon类根据一个索引每次返回一个img(三位张量),一个label(0维张量)
return img, label # img,label打包成元组返回
def main():
import visdom # 启动 python -m visdom.server,http://localhost:8097
import time
viz = visdom.Visdom()
db = DIYData_loader('D:\python pycharm learning\清华大佬课程\second\青光眼分类', 224, 'train')
# x,y = next(iter(db))
# print('sample:',x.shape,y.shape,y)
# viz.images(db.denormalize(x), win='sample_x', opts=dict(title='sample_x'))
# DataLoader加载器按batch_size打乱所有依次在内存当中按批次顺序加载每次批次,
# 每个批次内含batch个Pokemon类返回的对象(元组,列表,字符串)
loader = DataLoader(db, batch_size=20, shuffle=True)
for x, y in loader:
print('x_shape:',x.shape)
viz.images(db.denormalize(x), nrow=8, win='batch', opts=dict(title='batch'))
viz.text(str(y.numpy()), win='label', opts=dict(title='batch-y'))
time.sleep(10)
break
if __name__ == '__main__':
main()
# model.py
import torch.nn as nn
import torch
import torch.nn.functional as F
class GoogLeNet(nn.Module):
def __init__(self, num_classes=5, aux_logits=False, 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 5 (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)
# inception结构
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)
# 辅助分类器
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, 512)
self.fc3 = nn.Linear(512, 256)
self.fc4 = nn.Linear(256, 64)
self.fc5 = nn.Linear(64, 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 = F.relu(self.fc2(x))
x = F.dropout(x, 0.5, training=self.training)
# N x 512
x = F.relu(self.fc3(x))
x = F.dropout(x, 0.5, training=self.training)
# N x 256
x = F.relu(self.fc4(x))
x = F.dropout(x, 0.5, training=self.training)
# N x 64
x = self.fc5(x)
x = F.dropout(x, 0.5, training=self.training)
# 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
def main():
device = torch.device("cuda")
blk = GoogLeNet(3)
blk = blk.to(device)
tmp = torch.randn(64, 3, 224, 224)
tmp = tmp.to(device)
out = blk(tmp)
print('GoogLeNet:', out.shape)
if __name__ == '__main__':
main()
运行结果: