PyTorch搭建ResNet模型（在CIFAR10数据集上准确率达到了90%）_pointnet pytorch复现准确率高于90

PyTorch搭建ResNet模型

https://zhuanlan.zhihu.com/p/101332297

为了减少时间成本，本文只复现了ResNet-18模型，诸如ResNet-34、ResNet-50、ResNet-101、ResNet-152等更深层的神经网络模型，可以在ResNet-18的基础上修改而来。ResNet由于在顺序结构神经网络中引入了残差块（Residual Block），因此得名Residual Networks（ResNet）。

Residual Block：


ResNet-18与ResNet-50：

ResNet-34：

# import packages
import torch
import torchvision
1
2
3

# Device configuration.
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
1
2

# Transform configuration and data augmentation.
transform_train = torchvision.transforms.Compose([torchvision.transforms.Pad(4),
                                                 torchvision.transforms.RandomHorizontalFlip(),
                                                 torchvision.transforms.RandomCrop(32),
                                                 torchvision.transforms.ToTensor(),
                                                 torchvision.transforms.Normalize([0.5, 0.5, 0.5], [0.5, 0.5, 0.5])])
transform_test = torchvision.transforms.Compose([torchvision.transforms.ToTensor(),
                                                torchvision.transforms.Normalize([0.5, 0.5, 0.5], [0.5, 0.5, 0.5])])
1
2
3
4
5
6
7
8

# Hyper-parameters
num_classes = 10
batch_size = 100
learning_rate = 0.001
num_epochs = 80
1
2
3
4
5

# Load downloaded dataset.
train_dataset = torchvision.datasets.CIFAR10('data/CIFAR/', download=False, train=True, transform=transform_train)
test_dataset = torchvision.datasets.CIFAR10('data/CIFAR/', download=False, train=False, transform=transform_test)
1
2
3

# Data Loader.
train_loader = torch.utils.data.DataLoader(dataset=train_dataset, batch_size=batch_size, shuffle=True)
test_loader = torch.utils.data.DataLoader(dataset=test_dataset, batch_size=batch_size, shuffle=False)
1
2
3

# Define 3x3 convolution.
def conv3x3(in_channels, out_channels, stride=1):
    return torch.nn.Conv2d(in_channels, out_channels, kernel_size=3, stride=stride, padding=1, bias=False)
1
2
3

# Define Residual block
class ResidualBlock(torch.nn.Module):
    def __init__(self, in_channels, out_channels, stride=1, downsample=None):
        super(ResidualBlock, self).__init__()
        self.conv1 = conv3x3(in_channels, out_channels, stride)
        self.bn1 = torch.nn.BatchNorm2d(out_channels)
        self.relu = torch.nn.ReLU(inplace=True)
        self.conv2 = conv3x3(out_channels, out_channels)
        self.bn2 = torch.nn.BatchNorm2d(out_channels)
        self.downsample = downsample
        
    def forward(self, x):
        residual = x
        out = self.conv1(x)
        out = self.bn1(out)
        out = self.relu(out)
        out = self.conv2(out)
        out = self.bn2(out)
        if self.downsample :
            residual = self.downsample(x)
        out += residual
        out = self.relu(out)
        return out
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23

# Define ResNet-18
class ResNet(torch.nn.Module):
    def __init__(self, block, layers, num_classes):
        super(ResNet, self).__init__()
        self.in_channels = 16
        self.conv = conv3x3(3, 16)
        self.bn = torch.nn.BatchNorm2d(16)
        self.relu = torch.nn.ReLU(inplace=True)
        self.layer1 = self._make_layers(block, 16, layers[0])
        self.layer2 = self._make_layers(block, 32, layers[1], 2)
        self.layer3 = self._make_layers(block, 64, layers[2], 2)
        self.layer4 = self._make_layers(block, 128, layers[3], 2)
        self.avg_pool = torch.nn.AdaptiveAvgPool2d((1, 1))
        self.fc = torch.nn.Linear(128, num_classes)
        
    def _make_layers(self, block, out_channels, blocks, stride=1):
        downsample = None
        if (stride != 1) or (self.in_channels != out_channels):
            downsample = torch.nn.Sequential(
                conv3x3(self.in_channels, out_channels, stride=stride),
                torch.nn.BatchNorm2d(out_channels))
        layers = []
        layers.append(block(self.in_channels, out_channels, stride, downsample))
        self.in_channels = out_channels
        for i in range(1, blocks):
            layers.append(block(out_channels, out_channels))
        return torch.nn.Sequential(*layers)
    
    def forward(self, x):
        out = self.conv(x)
        out = self.bn(out)
        out = self.relu(out)
        out = self.layer1(out)
        out = self.layer2(out)
        out = self.layer3(out)
        out = self.layer4(out)
        out = self.avg_pool(out)
        out = out.view(out.size(0), -1)
        out = self.fc(out)
        return out
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40

# Make model.
model = ResNet(ResidualBlock, [2, 2, 2, 2], num_classes).to(device)
1
2

# Loss ans optimizer
criterion = torch.nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)
1
2
3

# For updating learning rate.
def update_lr(optimizer, lr):
    for param_group in optimizer.param_groups:
        param_group['lr'] = lr
1
2
3
4

# Train the model.
total_step = len(train_loader)
curr_lr = learning_rate
for epoch in range(num_epochs):
    for i, (images, labels) in enumerate(train_loader):
        images = images.to(device)
        labels = labels.to(device)
        
        # Forward pass.
        outputs = model(images)
        loss = criterion(outputs, labels)
        
        # Backward and optimize
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()
        
        if (i+1) % 100 == 0:
            print ('Epoch [{}/{}], Step [{}/{}], Loss: {:.4f}'.format(epoch+1, num_epochs, i+1, total_step, loss.item()))
    # Decay learning rate.
    if (epoch+1) % 20 == 0:
        curr_lr /= 3
        update_lr(optimizer, curr_lr)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23

Epoch [1/80], Step [100/500], Loss: 1.6278
Epoch [1/80], Step [200/500], Loss: 1.3368
Epoch [1/80], Step [300/500], Loss: 1.3774
Epoch [1/80], Step [400/500], Loss: 1.2487
Epoch [1/80], Step [500/500], Loss: 1.0083
Epoch [2/80], Step [100/500], Loss: 1.1344
Epoch [2/80], Step [200/500], Loss: 0.8391
Epoch [2/80], Step [300/500], Loss: 1.1451
Epoch [2/80], Step [400/500], Loss: 1.1581
Epoch [2/80], Step [500/500], Loss: 1.0138
Epoch [3/80], Step [100/500], Loss: 0.8204
Epoch [3/80], Step [200/500], Loss: 0.9306
Epoch [3/80], Step [300/500], Loss: 0.6666
Epoch [3/80], Step [400/500], Loss: 0.9254
Epoch [3/80], Step [500/500], Loss: 0.7068
Epoch [4/80], Step [100/500], Loss: 0.7309
Epoch [4/80], Step [200/500], Loss: 0.6603
Epoch [4/80], Step [300/500], Loss: 0.5715
Epoch [4/80], Step [400/500], Loss: 0.6693
Epoch [4/80], Step [500/500], Loss: 0.6240
Epoch [5/80], Step [100/500], Loss: 0.6171
Epoch [5/80], Step [200/500], Loss: 0.7757
Epoch [5/80], Step [300/500], Loss: 0.5394
Epoch [5/80], Step [400/500], Loss: 0.4437
Epoch [5/80], Step [500/500], Loss: 0.5371
Epoch [6/80], Step [100/500], Loss: 0.5737
Epoch [6/80], Step [200/500], Loss: 0.7505
Epoch [6/80], Step [300/500], Loss: 0.4102
Epoch [6/80], Step [400/500], Loss: 0.3542
Epoch [6/80], Step [500/500], Loss: 0.5393
Epoch [7/80], Step [100/500], Loss: 0.4987
Epoch [7/80], Step [200/500], Loss: 0.4006
Epoch [7/80], Step [300/500], Loss: 0.4238
Epoch [7/80], Step [400/500], Loss: 0.4722
Epoch [7/80], Step [500/500], Loss: 0.4706
Epoch [8/80], Step [100/500], Loss: 0.5829
Epoch [8/80], Step [200/500], Loss: 0.5226
Epoch [8/80], Step [300/500], Loss: 0.4381
Epoch [8/80], Step [400/500], Loss: 0.4344
Epoch [8/80], Step [500/500], Loss: 0.4641
Epoch [9/80], Step [100/500], Loss: 0.5033
Epoch [9/80], Step [200/500], Loss: 0.4500
Epoch [9/80], Step [300/500], Loss: 0.4019
Epoch [9/80], Step [400/500], Loss: 0.4249
Epoch [9/80], Step [500/500], Loss: 0.5130
Epoch [10/80], Step [100/500], Loss: 0.4057
Epoch [10/80], Step [200/500], Loss: 0.4189
Epoch [10/80], Step [300/500], Loss: 0.4459
Epoch [10/80], Step [400/500], Loss: 0.4157
Epoch [10/80], Step [500/500], Loss: 0.3352
Epoch [11/80], Step [100/500], Loss: 0.4696
Epoch [11/80], Step [200/500], Loss: 0.3871
Epoch [11/80], Step [300/500], Loss: 0.3810
Epoch [11/80], Step [400/500], Loss: 0.4613
Epoch [11/80], Step [500/500], Loss: 0.3651
Epoch [12/80], Step [100/500], Loss: 0.3487
Epoch [12/80], Step [200/500], Loss: 0.3225
Epoch [12/80], Step [300/500], Loss: 0.3127
Epoch [12/80], Step [400/500], Loss: 0.4051
Epoch [12/80], Step [500/500], Loss: 0.3588
Epoch [13/80], Step [100/500], Loss: 0.5568
Epoch [13/80], Step [200/500], Loss: 0.3759
Epoch [13/80], Step [300/500], Loss: 0.2941
Epoch [13/80], Step [400/500], Loss: 0.5200
Epoch [13/80], Step [500/500], Loss: 0.3995
Epoch [14/80], Step [100/500], Loss: 0.4985
Epoch [14/80], Step [200/500], Loss: 0.4564
Epoch [14/80], Step [300/500], Loss: 0.2351
Epoch [14/80], Step [400/500], Loss: 0.4535
Epoch [14/80], Step [500/500], Loss: 0.5108
Epoch [15/80], Step [100/500], Loss: 0.3881
Epoch [15/80], Step [200/500], Loss: 0.4429
Epoch [15/80], Step [300/500], Loss: 0.2841
Epoch [15/80], Step [400/500], Loss: 0.4210
Epoch [15/80], Step [500/500], Loss: 0.2653
Epoch [16/80], Step [100/500], Loss: 0.4307
Epoch [16/80], Step [200/500], Loss: 0.2401
Epoch [16/80], Step [300/500], Loss: 0.1996
Epoch [16/80], Step [400/500], Loss: 0.2240
Epoch [16/80], Step [500/500], Loss: 0.2821
Epoch [17/80], Step [100/500], Loss: 0.2849
Epoch [17/80], Step [200/500], Loss: 0.2965
Epoch [17/80], Step [300/500], Loss: 0.3777
Epoch [17/80], Step [400/500], Loss: 0.4469
Epoch [17/80], Step [500/500], Loss: 0.2752
Epoch [18/80], Step [100/500], Loss: 0.2665
Epoch [18/80], Step [200/500], Loss: 0.3726
Epoch [18/80], Step [300/500], Loss: 0.1999
Epoch [18/80], Step [400/500], Loss: 0.2555
Epoch [18/80], Step [500/500], Loss: 0.2895
Epoch [19/80], Step [100/500], Loss: 0.1635
Epoch [19/80], Step [200/500], Loss: 0.1796
Epoch [19/80], Step [300/500], Loss: 0.4037
Epoch [19/80], Step [400/500], Loss: 0.2623
Epoch [19/80], Step [500/500], Loss: 0.1818
Epoch [20/80], Step [100/500], Loss: 0.2265
Epoch [20/80], Step [200/500], Loss: 0.4131
Epoch [20/80], Step [300/500], Loss: 0.2777
Epoch [20/80], Step [400/500], Loss: 0.3146
Epoch [20/80], Step [500/500], Loss: 0.3028
Epoch [21/80], Step [100/500], Loss: 0.3265
Epoch [21/80], Step [200/500], Loss: 0.2229
Epoch [21/80], Step [300/500], Loss: 0.2388
Epoch [21/80], Step [400/500], Loss: 0.2601
Epoch [21/80], Step [500/500], Loss: 0.1227
Epoch [22/80], Step [100/500], Loss: 0.2175
Epoch [22/80], Step [200/500], Loss: 0.2641
Epoch [22/80], Step [300/500], Loss: 0.1847
Epoch [22/80], Step [400/500], Loss: 0.1926
Epoch [22/80], Step [500/500], Loss: 0.2075
Epoch [23/80], Step [100/500], Loss: 0.1859
Epoch [23/80], Step [200/500], Loss: 0.1570
Epoch [23/80], Step [300/500], Loss: 0.2750
Epoch [23/80], Step [400/500], Loss: 0.0908
Epoch [23/80], Step [500/500], Loss: 0.1936
Epoch [24/80], Step [100/500], Loss: 0.1485
Epoch [24/80], Step [200/500], Loss: 0.1572
Epoch [24/80], Step [300/500], Loss: 0.1881
Epoch [24/80], Step [400/500], Loss: 0.1262
Epoch [24/80], Step [500/500], Loss: 0.3006
Epoch [25/80], Step [100/500], Loss: 0.2768
Epoch [25/80], Step [200/500], Loss: 0.0902
Epoch [25/80], Step [300/500], Loss: 0.2313
Epoch [25/80], Step [400/500], Loss: 0.1361
Epoch [25/80], Step [500/500], Loss: 0.2736
Epoch [26/80], Step [100/500], Loss: 0.1499
Epoch [26/80], Step [200/500], Loss: 0.1687
Epoch [26/80], Step [300/500], Loss: 0.1190
Epoch [26/80], Step [400/500], Loss: 0.1117
Epoch [26/80], Step [500/500], Loss: 0.1268
Epoch [27/80], Step [100/500], Loss: 0.1518
Epoch [27/80], Step [200/500], Loss: 0.1603
Epoch [27/80], Step [300/500], Loss: 0.1415
Epoch [27/80], Step [400/500], Loss: 0.2641
Epoch [27/80], Step [500/500], Loss: 0.0748
Epoch [28/80], Step [100/500], Loss: 0.2301
Epoch [28/80], Step [200/500], Loss: 0.2718
Epoch [28/80], Step [300/500], Loss: 0.2650
Epoch [28/80], Step [400/500], Loss: 0.0754
Epoch [28/80], Step [500/500], Loss: 0.1454
Epoch [29/80], Step [100/500], Loss: 0.1373
Epoch [29/80], Step [200/500], Loss: 0.1285
Epoch [29/80], Step [300/500], Loss: 0.1345
Epoch [29/80], Step [400/500], Loss: 0.1153
Epoch [29/80], Step [500/500], Loss: 0.2338
Epoch [30/80], Step [100/500], Loss: 0.1643
Epoch [30/80], Step [200/500], Loss: 0.0779
Epoch [30/80], Step [300/500], Loss: 0.1455
Epoch [30/80], Step [400/500], Loss: 0.1288
Epoch [30/80], Step [500/500], Loss: 0.2127
Epoch [31/80], Step [100/500], Loss: 0.2214
Epoch [31/80], Step [200/500], Loss: 0.1338
Epoch [31/80], Step [300/500], Loss: 0.1166
Epoch [31/80], Step [400/500], Loss: 0.0748
Epoch [31/80], Step [500/500], Loss: 0.2321
Epoch [32/80], Step [100/500], Loss: 0.1146
Epoch [32/80], Step [200/500], Loss: 0.1730
Epoch [32/80], Step [300/500], Loss: 0.1165
Epoch [32/80], Step [400/500], Loss: 0.2201
Epoch [32/80], Step [500/500], Loss: 0.0860
Epoch [33/80], Step [100/500], Loss: 0.1171
Epoch [33/80], Step [200/500], Loss: 0.1427
Epoch [33/80], Step [300/500], Loss: 0.1329
Epoch [33/80], Step [400/500], Loss: 0.1102
Epoch [33/80], Step [500/500], Loss: 0.1330
Epoch [34/80], Step [100/500], Loss: 0.1335
Epoch [34/80], Step [200/500], Loss: 0.1465
Epoch [34/80], Step [300/500], Loss: 0.1598
Epoch [34/80], Step [400/500], Loss: 0.0849
Epoch [34/80], Step [500/500], Loss: 0.0847
Epoch [35/80], Step [100/500], Loss: 0.2173
Epoch [35/80], Step [200/500], Loss: 0.1172
Epoch [35/80], Step [300/500], Loss: 0.1516
Epoch [35/80], Step [400/500], Loss: 0.1212
Epoch [35/80], Step [500/500], Loss: 0.0644
Epoch [36/80], Step [100/500], Loss: 0.0651
Epoch [36/80], Step [200/500], Loss: 0.1346
Epoch [36/80], Step [300/500], Loss: 0.0986
Epoch [36/80], Step [400/500], Loss: 0.1141
Epoch [36/80], Step [500/500], Loss: 0.1344
Epoch [37/80], Step [100/500], Loss: 0.1834
Epoch [37/80], Step [200/500], Loss: 0.1162
Epoch [37/80], Step [300/500], Loss: 0.1637
Epoch [37/80], Step [400/500], Loss: 0.0949
Epoch [37/80], Step [500/500], Loss: 0.1504
Epoch [38/80], Step [100/500], Loss: 0.1251
Epoch [38/80], Step [200/500], Loss: 0.1133
Epoch [38/80], Step [300/500], Loss: 0.1080
Epoch [38/80], Step [400/500], Loss: 0.0686
Epoch [38/80], Step [500/500], Loss: 0.1099
Epoch [39/80], Step [100/500], Loss: 0.0616
Epoch [39/80], Step [200/500], Loss: 0.1919
Epoch [39/80], Step [300/500], Loss: 0.1736
Epoch [39/80], Step [400/500], Loss: 0.1276
Epoch [39/80], Step [500/500], Loss: 0.0810
Epoch [40/80], Step [100/500], Loss: 0.1305
Epoch [40/80], Step [200/500], Loss: 0.1893
Epoch [40/80], Step [300/500], Loss: 0.0975
Epoch [40/80], Step [400/500], Loss: 0.0918
Epoch [40/80], Step [500/500], Loss: 0.0549
Epoch [41/80], Step [100/500], Loss: 0.0390
Epoch [41/80], Step [200/500], Loss: 0.0826
Epoch [41/80], Step [300/500], Loss: 0.0812
Epoch [41/80], Step [400/500], Loss: 0.1012
Epoch [41/80], Step [500/500], Loss: 0.0991
Epoch [42/80], Step [100/500], Loss: 0.1419
Epoch [42/80], Step [200/500], Loss: 0.1208
Epoch [42/80], Step [300/500], Loss: 0.0862
Epoch [42/80], Step [400/500], Loss: 0.0817
Epoch [42/80], Step [500/500], Loss: 0.0749
Epoch [43/80], Step [100/500], Loss: 0.0834
Epoch [43/80], Step [200/500], Loss: 0.0713
Epoch [43/80], Step [300/500], Loss: 0.0794
Epoch [43/80], Step [400/500], Loss: 0.1317
Epoch [43/80], Step [500/500], Loss: 0.0561
Epoch [44/80], Step [100/500], Loss: 0.1528
Epoch [44/80], Step [200/500], Loss: 0.0989
Epoch [44/80], Step [300/500], Loss: 0.1040
Epoch [44/80], Step [400/500], Loss: 0.0633
Epoch [44/80], Step [500/500], Loss: 0.0580
Epoch [45/80], Step [100/500], Loss: 0.0817
Epoch [45/80], Step [200/500], Loss: 0.0723
Epoch [45/80], Step [300/500], Loss: 0.0435
Epoch [45/80], Step [400/500], Loss: 0.1233
Epoch [45/80], Step [500/500], Loss: 0.0652
Epoch [46/80], Step [100/500], Loss: 0.0720
Epoch [46/80], Step [200/500], Loss: 0.0727
Epoch [46/80], Step [300/500], Loss: 0.0731
Epoch [46/80], Step [400/500], Loss: 0.1015
Epoch [46/80], Step [500/500], Loss: 0.1100
Epoch [47/80], Step [100/500], Loss: 0.1373
Epoch [47/80], Step [200/500], Loss: 0.0711
Epoch [47/80], Step [300/500], Loss: 0.0612
Epoch [47/80], Step [400/500], Loss: 0.1126
Epoch [47/80], Step [500/500], Loss: 0.0481
Epoch [48/80], Step [100/500], Loss: 0.0284
Epoch [48/80], Step [200/500], Loss: 0.0472
Epoch [48/80], Step [300/500], Loss: 0.0857
Epoch [48/80], Step [400/500], Loss: 0.0402
Epoch [48/80], Step [500/500], Loss: 0.0856
Epoch [49/80], Step [100/500], Loss: 0.0678
Epoch [49/80], Step [200/500], Loss: 0.0627
Epoch [49/80], Step [300/500], Loss: 0.0598
Epoch [49/80], Step [400/500], Loss: 0.0643
Epoch [49/80], Step [500/500], Loss: 0.0256
Epoch [50/80], Step [100/500], Loss: 0.0903
Epoch [50/80], Step [200/500], Loss: 0.0344
Epoch [50/80], Step [300/500], Loss: 0.0522
Epoch [50/80], Step [400/500], Loss: 0.0502
Epoch [50/80], Step [500/500], Loss: 0.0344
Epoch [51/80], Step [100/500], Loss: 0.0654
Epoch [51/80], Step [200/500], Loss: 0.0376
Epoch [51/80], Step [300/500], Loss: 0.0347
Epoch [51/80], Step [400/500], Loss: 0.0391
Epoch [51/80], Step [500/500], Loss: 0.0918
Epoch [52/80], Step [100/500], Loss: 0.0627
Epoch [52/80], Step [200/500], Loss: 0.0631
Epoch [52/80], Step [300/500], Loss: 0.1437
Epoch [52/80], Step [400/500], Loss: 0.1198
Epoch [52/80], Step [500/500], Loss: 0.0595
Epoch [53/80], Step [100/500], Loss: 0.0501
Epoch [53/80], Step [200/500], Loss: 0.0416
Epoch [53/80], Step [300/500], Loss: 0.0831
Epoch [53/80], Step [400/500], Loss: 0.0350
Epoch [53/80], Step [500/500], Loss: 0.0257
Epoch [54/80], Step [100/500], Loss: 0.0628
Epoch [54/80], Step [200/500], Loss: 0.0533
Epoch [54/80], Step [300/500], Loss: 0.0226
Epoch [54/80], Step [400/500], Loss: 0.0379
Epoch [54/80], Step [500/500], Loss: 0.0605
Epoch [55/80], Step [100/500], Loss: 0.1083
Epoch [55/80], Step [200/500], Loss: 0.1897
Epoch [55/80], Step [300/500], Loss: 0.0573
Epoch [55/80], Step [400/500], Loss: 0.0658
Epoch [55/80], Step [500/500], Loss: 0.0485
Epoch [56/80], Step [100/500], Loss: 0.0430
Epoch [56/80], Step [200/500], Loss: 0.0346
Epoch [56/80], Step [300/500], Loss: 0.0393
Epoch [56/80], Step [400/500], Loss: 0.0278
Epoch [56/80], Step [500/500], Loss: 0.0634
Epoch [57/80], Step [100/500], Loss: 0.0588
Epoch [57/80], Step [200/500], Loss: 0.0300
Epoch [57/80], Step [300/500], Loss: 0.0223
Epoch [57/80], Step [400/500], Loss: 0.1497
Epoch [57/80], Step [500/500], Loss: 0.0777
Epoch [58/80], Step [100/500], Loss: 0.0809
Epoch [58/80], Step [200/500], Loss: 0.0934
Epoch [58/80], Step [300/500], Loss: 0.0982
Epoch [58/80], Step [400/500], Loss: 0.1587
Epoch [58/80], Step [500/500], Loss: 0.0417
Epoch [59/80], Step [100/500], Loss: 0.0371
Epoch [59/80], Step [200/500], Loss: 0.1052
Epoch [59/80], Step [300/500], Loss: 0.0455
Epoch [59/80], Step [400/500], Loss: 0.0274
Epoch [59/80], Step [500/500], Loss: 0.0616
Epoch [60/80], Step [100/500], Loss: 0.1352
Epoch [60/80], Step [200/500], Loss: 0.0750
Epoch [60/80], Step [300/500], Loss: 0.0705
Epoch [60/80], Step [400/500], Loss: 0.0296
Epoch [60/80], Step [500/500], Loss: 0.0380
Epoch [61/80], Step [100/500], Loss: 0.0438
Epoch [61/80], Step [200/500], Loss: 0.0599
Epoch [61/80], Step [300/500], Loss: 0.0504
Epoch [61/80], Step [400/500], Loss: 0.0469
Epoch [61/80], Step [500/500], Loss: 0.0534
Epoch [62/80], Step [100/500], Loss: 0.0200
Epoch [62/80], Step [200/500], Loss: 0.0518
Epoch [62/80], Step [300/500], Loss: 0.0660
Epoch [62/80], Step [400/500], Loss: 0.0473
Epoch [62/80], Step [500/500], Loss: 0.0292
Epoch [63/80], Step [100/500], Loss: 0.0576
Epoch [63/80], Step [200/500], Loss: 0.0643
Epoch [63/80], Step [300/500], Loss: 0.0856
Epoch [63/80], Step [400/500], Loss: 0.0674
Epoch [63/80], Step [500/500], Loss: 0.0834
Epoch [64/80], Step [100/500], Loss: 0.0638
Epoch [64/80], Step [200/500], Loss: 0.0802
Epoch [64/80], Step [300/500], Loss: 0.0700
Epoch [64/80], Step [400/500], Loss: 0.0195
Epoch [64/80], Step [500/500], Loss: 0.0488
Epoch [65/80], Step [100/500], Loss: 0.0358
Epoch [65/80], Step [200/500], Loss: 0.0692
Epoch [65/80], Step [300/500], Loss: 0.0298
Epoch [65/80], Step [400/500], Loss: 0.0233
Epoch [65/80], Step [500/500], Loss: 0.0875
Epoch [66/80], Step [100/500], Loss: 0.0298
Epoch [66/80], Step [200/500], Loss: 0.0509
Epoch [66/80], Step [300/500], Loss: 0.0227
Epoch [66/80], Step [400/500], Loss: 0.1122
Epoch [66/80], Step [500/500], Loss: 0.0954
Epoch [67/80], Step [100/500], Loss: 0.0623
Epoch [67/80], Step [200/500], Loss: 0.0213
Epoch [67/80], Step [300/500], Loss: 0.0553
Epoch [67/80], Step [400/500], Loss: 0.0296
Epoch [67/80], Step [500/500], Loss: 0.0715
Epoch [68/80], Step [100/500], Loss: 0.0543
Epoch [68/80], Step [200/500], Loss: 0.0407
Epoch [68/80], Step [300/500], Loss: 0.0370
Epoch [68/80], Step [400/500], Loss: 0.0279
Epoch [68/80], Step [500/500], Loss: 0.0512
Epoch [69/80], Step [100/500], Loss: 0.0297
Epoch [69/80], Step [200/500], Loss: 0.0583
Epoch [69/80], Step [300/500], Loss: 0.0760
Epoch [69/80], Step [400/500], Loss: 0.0403
Epoch [69/80], Step [500/500], Loss: 0.0189
Epoch [70/80], Step [100/500], Loss: 0.1321
Epoch [70/80], Step [200/500], Loss: 0.0988
Epoch [70/80], Step [300/500], Loss: 0.0440
Epoch [70/80], Step [400/500], Loss: 0.0250
Epoch [70/80], Step [500/500], Loss: 0.0671
Epoch [71/80], Step [100/500], Loss: 0.0293
Epoch [71/80], Step [200/500], Loss: 0.0672
Epoch [71/80], Step [300/500], Loss: 0.0317
Epoch [71/80], Step [400/500], Loss: 0.0436
Epoch [71/80], Step [500/500], Loss: 0.0260
Epoch [72/80], Step [100/500], Loss: 0.0429
Epoch [72/80], Step [200/500], Loss: 0.0222
Epoch [72/80], Step [300/500], Loss: 0.0480
Epoch [72/80], Step [400/500], Loss: 0.0367
Epoch [72/80], Step [500/500], Loss: 0.0134
Epoch [73/80], Step [100/500], Loss: 0.0628
Epoch [73/80], Step [200/500], Loss: 0.0403
Epoch [73/80], Step [300/500], Loss: 0.0436
Epoch [73/80], Step [400/500], Loss: 0.1032
Epoch [73/80], Step [500/500], Loss: 0.0663
Epoch [74/80], Step [100/500], Loss: 0.0192
Epoch [74/80], Step [200/500], Loss: 0.0254
Epoch [74/80], Step [300/500], Loss: 0.0436
Epoch [74/80], Step [400/500], Loss: 0.1073
Epoch [74/80], Step [500/500], Loss: 0.0539
Epoch [75/80], Step [100/500], Loss: 0.0437
Epoch [75/80], Step [200/500], Loss: 0.0813
Epoch [75/80], Step [300/500], Loss: 0.0821
Epoch [75/80], Step [400/500], Loss: 0.0847
Epoch [75/80], Step [500/500], Loss: 0.0428
Epoch [76/80], Step [100/500], Loss: 0.0912
Epoch [76/80], Step [200/500], Loss: 0.0295
Epoch [76/80], Step [300/500], Loss: 0.0700
Epoch [76/80], Step [400/500], Loss: 0.0480
Epoch [76/80], Step [500/500], Loss: 0.0358
Epoch [77/80], Step [100/500], Loss: 0.0178
Epoch [77/80], Step [200/500], Loss: 0.0154
Epoch [77/80], Step [300/500], Loss: 0.0662
Epoch [77/80], Step [400/500], Loss: 0.0258
Epoch [77/80], Step [500/500], Loss: 0.0811
Epoch [78/80], Step [100/500], Loss: 0.0542
Epoch [78/80], Step [200/500], Loss: 0.0643
Epoch [78/80], Step [300/500], Loss: 0.0575
Epoch [78/80], Step [400/500], Loss: 0.0371
Epoch [78/80], Step [500/500], Loss: 0.0512
Epoch [79/80], Step [100/500], Loss: 0.0240
Epoch [79/80], Step [200/500], Loss: 0.0133
Epoch [79/80], Step [300/500], Loss: 0.0532
Epoch [79/80], Step [400/500], Loss: 0.0760
Epoch [79/80], Step [500/500], Loss: 0.0356
Epoch [80/80], Step [100/500], Loss: 0.0728
Epoch [80/80], Step [200/500], Loss: 0.0553
Epoch [80/80], Step [300/500], Loss: 0.0228
Epoch [80/80], Step [400/500], Loss: 0.0324
Epoch [80/80], Step [500/500], Loss: 0.0701
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400

# Test the model.
model.eval()
with torch.no_grad():
    correct = 0
    total = 0
    for images, labels in test_loader:
        images = images.to(device)
        labels = labels.to(device)
        outputs = model(images)
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).sum().item()
        
    print('Accuracy of the model on the test images: {} %'.format(100 * correct / total))
1
2
3
4
5
6
7
8
9
10
11
12
13
14

Accuracy of the model on the test images: 89.89 %
1

# Save the model
torch.save(model.state_dict(), 'ResNet.ckpt')
1
2

1