image.png
因为本人GPU显存不够就可怜的2G 实在hold不住ResNet 的参数量只好将 残差模块只弄两个卷积核，而且batch_size也修改为1只进行代码测试 - 。 -，听说COLAB上有免费的16G GPU使用下次在运行，由于GPU会进行并行运算这个计算出的显存与实际使用的显存也有点差距。
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
import pickle
# 数据加载
def load(file):
with open(file, 'rb') as fo:
dict = pickle.load(fo, encoding='bytes')
return dict
fil_1 = 'E:\Download\DigitalImage\cifar-10-batches-py\data_batch_1'
fil_2 = 'E:\Download\DigitalImage\cifar-10-batches-py\data_batch_2'
fil_3 = 'E:\Download\DigitalImage\cifar-10-batches-py\data_batch_3'
fil_4 = 'E:\Download\DigitalImage\cifar-10-batches-py\data_batch_4'
fil_5 = 'E:\Download\DigitalImage\cifar-10-batches-py\data_batch_5'
fil_6 = 'E:\Download\DigitalImage\cifar-10-batches-py\\test_batch_1'
path = [fil_1,fil_2,fil_3,fil_4,fil_5,fil_6]
train_data = []
test_data = []
for i in range(len(path)):
if i != len(path)-1:
datas = load(path[i])
a = datas[b'data'].reshape(10000,3,32,32)
train_data.append((torch.FloatTensor(a),torch.LongTensor(datas[b'labels'])))
print()
else:
datas = load(path[i])
test_data = [(torch.FloatTensor(datas[b'data'].reshape(10000,3,32,32)),torch.LongTensor(datas[b'labels']))]
# 残差块定义
class ResBlock(nn.Module):
def __init__(self,in_channel,out_channel,stri):
super(ResBlock,self).__init__()
self.cov1 = nn.Conv2d(in_channel,out_channel,kernel_size = 3,stride = stri,padding = 1)
self.bn1 = nn.BatchNorm2d(out_channel)
self.cov2 = nn.Conv2d(out_channel,out_channel,kernel_size = 3,stride = 1,padding = 1)
self.bn2 = nn.BatchNorm2d(out_channel)
# 恒等映射保证和输出维度一致
self.identity = nn.Sequential(
nn.Conv2d(in_channel,out_channel,kernel_size = 1,stride =stri,padding = 0),
nn.BatchNorm2d(out_channel)
)
def forward(self,x):
out = F.relu(self.cov1(x))
out = self.bn1(out)
out = F.relu(self.cov2(out))
out = self.bn2(out)
#out = F.relu(self.cov2(out))
#out = self.bn2(out)
#out = F.relu(self.cov2(out))
#out = self.bn2(out)
#print(self.identity(x).shape,out.shape)
out = self.identity(x) + out
out = F.relu(out)
return out
#测试代码输入伪图片
x = torch.randn(2,3,32,32)
a = ResBlock(3,64,2)
print(a(x).shape)
torch.Size([2, 64, 16, 16])
# 残差块网络连接
class Flatten(nn.Module):
def __init__(self):
super(Flatten,self).__init__()
def forward(self,input):
return input.view(input.size(0),-1)
class Resnet18(nn.Module):
def __init__(self):
super(Resnet18,self).__init__()
self.model = nn.Sequential(
nn.Conv2d(3,64,kernel_size = 3,stride = 1,padding = 1),
nn.BatchNorm2d(64),
ResBlock(64,128,stri = 2),
ResBlock(128,256,stri = 2),
ResBlock(256,512,stri = 2),
ResBlock(512,1024,stri = 2),
nn.AvgPool2d(2),
Flatten(),
nn.Linear(1024,10)
)
def forward(self,x):
return self.model(x)
#测试代码
x = torch.randn(2,3,32,32)
c = Resnet18()
print(c(x).shape)
torch.Size([2, 10])
epochs = 10
device = torch.device('cuda:0')
ResNet18 = Resnet18().to(device)
optimizer = optim.SGD(ResNet18.parameters(),lr = 0.01)
loss_fun = nn.CrossEntropyLoss().to(device)
def Run():
for epoch in range(epochs):
ResNet18.train()
for index,(data,label) in enumerate(train_data):
for i in range(100):
datas = data[i:(i+1),:,:,:].to(device)
#print(datas.shape)
labels = label[i:(i+1)].to(device)
#print(labels.shape)
logits = ResNet18(datas)
loss = loss_fun(logits,labels)
optimizer.zero_grad()
loss.backward()
optimizer.step()
print('epoch:{}\t batch:{}\t loss:{}'.format(epoch,index,loss.item()))
ResNet18.eval()
loss = 0
correct = 0
AVGloss = 0
for index,(data,label) in enumerate(test_data):
for i in range(100):
datas = data[i:i+1,:,:,:].to(device)
labels = label[i:i+1].to(device)
logits = ResNet18(datas)
loss += loss_fun(logits,labels)
predict = logits.argmax(dim=1)
correct += predict.eq(labels).float().sum().item()
loss /= 100.
print('epochs:{} \t accuracy:{}%\t test_date_AVGloss:{} '.format(epoch,100.*correct/100,loss.item()))
Run()
epoch:0 batch:0 loss:1.193771243095398
epoch:0 batch:1 loss:0.6211187839508057
epoch:0 batch:2 loss:2.3206470012664795
epoch:0 batch:3 loss:1.0057952404022217
epoch:0 batch:4 loss:1.6052329540252686
epochs:0 accuracy:7.0% test_date_AVGloss:4.08225154876709
epoch:1 batch:0 loss:1.168436050415039
epoch:1 batch:1 loss:0.6469242572784424
epoch:1 batch:2 loss:1.9090821743011475
epoch:1 batch:3 loss:0.8259971141815186
epoch:1 batch:4 loss:1.482107400894165
epochs:1 accuracy:7.0% test_date_AVGloss:4.174167633056641
epoch:2 batch:0 loss:1.1068801879882812
epoch:2 batch:1 loss:0.5857620239257812
epoch:2 batch:2 loss:1.4080276489257812
epoch:2 batch:3 loss:0.6490111351013184
epoch:2 batch:4 loss:1.3858662843704224
epochs:2 accuracy:7.0% test_date_AVGloss:4.06494140625
epoch:3 batch:0 loss:0.7395391464233398
epoch:3 batch:1 loss:0.5753352642059326
epoch:3 batch:2 loss:1.252335786819458
epoch:3 batch:3 loss:0.41171860694885254
epoch:3 batch:4 loss:1.258840560913086
epochs:3 accuracy:10.0% test_date_AVGloss:3.6299731731414795
epoch:4 batch:0 loss:0.5887634754180908
epoch:4 batch:1 loss:0.5793724060058594
epoch:4 batch:2 loss:1.1198831796646118
epoch:4 batch:3 loss:0.300403356552124
epoch:4 batch:4 loss:0.7450690269470215
epochs:4 accuracy:14.0% test_date_AVGloss:3.8890163898468018
epoch:5 batch:0 loss:0.24598288536071777
epoch:5 batch:1 loss:0.16252756118774414
epoch:5 batch:2 loss:0.6145534515380859
epoch:5 batch:3 loss:0.1928553581237793
epoch:5 batch:4 loss:0.20372629165649414
epochs:5 accuracy:18.0% test_date_AVGloss:3.09653377532959
epoch:6 batch:0 loss:0.07158946990966797
epoch:6 batch:1 loss:0.2547154426574707
epoch:6 batch:2 loss:0.2163069248199463
epoch:6 batch:3 loss:0.1844019889831543
epoch:6 batch:4 loss:0.12868928909301758
epochs:6 accuracy:23.0% test_date_AVGloss:2.7130041122436523
epoch:7 batch:0 loss:0.04795646667480469
epoch:7 batch:1 loss:0.053249359130859375
epoch:7 batch:2 loss:0.02186727523803711
epoch:7 batch:3 loss:0.032016754150390625
epoch:7 batch:4 loss:0.02663278579711914
epochs:7 accuracy:23.0% test_date_AVGloss:2.557596445083618
epoch:8 batch:0 loss:0.03522920608520508
epoch:8 batch:1 loss:0.03684282302856445
epoch:8 batch:2 loss:0.014127731323242188
epoch:8 batch:3 loss:0.018548965454101562
epoch:8 batch:4 loss:0.019474029541015625
epochs:8 accuracy:21.0% test_date_AVGloss:2.537302255630493
epoch:9 batch:0 loss:0.01775217056274414
epoch:9 batch:1 loss:0.023839473724365234
epoch:9 batch:2 loss:0.011283397674560547
epoch:9 batch:3 loss:0.014598846435546875
epoch:9 batch:4 loss:0.014908790588378906
epochs:9 accuracy:25.0% test_date_AVGloss:2.5501718521118164
print(len(test_data))
1
# 参数字节数
byte = (9*(3*64+64*64+64*128+128*128+128*256+256*256+256*512+512*512+512*1024+1024*1024)+1024*10)*4
# SGD
sgd_byte = byte
# 保存梯度字节数
print(byte)
grad = byte
# 输入输出显存
put = (3*32*32+32*32*64+64*16*16+128*8*8+256*4*4+512*2*2+1024)*4
print((byte*3+put)/1000000)
75397888
226.595072
