diff --git a/imagenet.py b/imagenet.py
index f0c5c0a..edede9e 100644
--- a/imagenet.py
+++ b/imagenet.py
@@ -329,11 +329,11 @@ def test(val_loader, model, criterion, epoch, use_cuda):
     bar.finish()
     return (losses.avg, top1.avg, top5.avg)
 
-def save_checkpoint(state, is_best, checkpoint='checkpoint', filename='checkpoint.pth.tar'):
+def save_checkpoint(state, is_best, checkpoint='checkpoint', filename='checkpoint.pth'):
     filepath = os.path.join(checkpoint, filename)
     torch.save(state, filepath)
     if is_best:
-        shutil.copyfile(filepath, os.path.join(checkpoint, 'model_best.pth.tar'))
+        shutil.copyfile(filepath, os.path.join(checkpoint, 'model_best.pth'))
 
 def adjust_learning_rate(optimizer, epoch):
     global state
diff --git a/models/imagenet/__init__.py b/models/imagenet/__init__.py
index 9ad77bf..cffa6e7 100644
--- a/models/imagenet/__init__.py
+++ b/models/imagenet/__init__.py
@@ -9,3 +9,4 @@
 from .resnext_ibn_a import *
 from .se_resnet import *
 from .se_resnet_ibn_a import *
+from .se_resnet_ibn_b import *
diff --git a/models/imagenet/se_resnet_ibn_b.py b/models/imagenet/se_resnet_ibn_b.py
new file mode 100644
index 0000000..7bcf619
--- /dev/null
+++ b/models/imagenet/se_resnet_ibn_b.py
@@ -0,0 +1,190 @@
+from .se_module import SELayer
+import torch.nn as nn
+import torch
+import math
+
+__all__ = ['se_resnet50_ibn_b', 'se_resnet101_ibn_b', 'se_resnet152_ibn_b']
+
+def conv3x3(in_planes, out_planes, stride=1):
+    return nn.Conv2d(in_planes, out_planes, kernel_size=3, stride=stride, padding=1, bias=False)
+
+
+class SEBasicBlock(nn.Module):
+    expansion = 1
+
+    def __init__(self, inplanes, planes, stride=1, downsample=None, reduction=16, IN=False):
+        super(SEBasicBlock, self).__init__()
+        self.conv1 = conv3x3(inplanes, planes, stride)
+        self.bn1 = nn.BatchNorm2d(planes)
+        self.relu = nn.ReLU(inplace=True)
+        self.conv2 = conv3x3(planes, planes, 1)
+        self.bn2 = nn.BatchNorm2d(planes)
+        self.IN = None
+        if IN:
+            self.IN = nn.InstanceNorm2d(planes * 4, affine=True)
+        self.se = SELayer(planes, reduction)
+        self.downsample = downsample
+        self.stride = stride
+
+    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)
+        out = self.se(out)
+
+        if self.downsample is not None:
+            residual = self.downsample(x)
+
+        out += residual
+        if self.IN is not None:
+            out = self.IN(out)
+        out = self.relu(out)
+
+        return out
+
+
+class SEBottleneck(nn.Module):
+    expansion = 4
+
+    def __init__(self, inplanes, planes, stride=1, downsample=None, reduction=16, IN=False):
+        super(SEBottleneck, self).__init__()
+        self.conv1 = nn.Conv2d(inplanes, planes, kernel_size=1, bias=False)
+        self.bn1 = nn.BatchNorm2d(planes)
+        self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=stride,
+                               padding=1, bias=False)
+        self.bn2 = nn.BatchNorm2d(planes)
+        self.conv3 = nn.Conv2d(planes, planes * 4, kernel_size=1, bias=False)
+        self.bn3 = nn.BatchNorm2d(planes * 4)
+        self.IN = None
+        if IN:
+            self.IN = nn.InstanceNorm2d(planes * 4, affine=True)
+        self.relu = nn.ReLU(inplace=True)
+        self.se = SELayer(planes * 4, reduction)
+        self.downsample = downsample
+        self.stride = stride
+        
+    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)
+        out = self.relu(out)
+
+        out = self.conv3(out)
+        out = self.bn3(out)
+        out = self.se(out)
+
+        if self.downsample is not None:
+            residual = self.downsample(x)
+
+        out += residual
+        if self.IN is not None:
+            out = self.IN(out)
+        out = self.relu(out)
+
+        return out
+
+class ResNet(nn.Module):
+
+    def __init__(self, block, layers, num_classes=1000):
+        self.inplanes = 64
+        super(ResNet, self).__init__()
+        self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3,
+                               bias=False)
+        self.bn1 = nn.InstanceNorm2d(64, affine=True)
+        self.relu = nn.ReLU(inplace=True)
+        self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
+        self.layer1 = self._make_layer(block, 64, layers[0], stride=1, IN=True) 
+        self.layer2 = self._make_layer(block, 128, layers[1], stride=2, IN=True)
+        self.layer3 = self._make_layer(block, 256, layers[2], stride=2)
+        self.layer4 = self._make_layer(block, 512, layers[3], stride=2)
+        self.avgpool = nn.AvgPool2d(7)
+        self.fc = nn.Linear(512 * block.expansion, num_classes)
+        
+        self.conv1.weight.data.normal_(0, math.sqrt(2. / (7 * 7 * 64)))
+        for m in self.modules():
+            if isinstance(m, nn.Conv2d):
+                n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
+                m.weight.data.normal_(0, math.sqrt(2. / n))
+            elif isinstance(m, nn.BatchNorm2d):
+                m.weight.data.fill_(1)
+                m.bias.data.zero_()
+            elif isinstance(m, nn.InstanceNorm2d):
+                m.weight.data.fill_(1)
+                m.bias.data.zero_()
+
+    def _make_layer(self, block, planes, blocks, stride=1, IN=False):
+        downsample = None
+        if stride != 1 or self.inplanes != planes * block.expansion:
+            downsample = nn.Sequential(
+                nn.Conv2d(self.inplanes, planes * block.expansion,
+                          kernel_size=1, stride=stride, bias=False),
+                nn.BatchNorm2d(planes * block.expansion),
+            )
+
+        layers = []
+        layers.append(block(self.inplanes, planes, stride, downsample))
+        self.inplanes = planes * block.expansion
+        for i in range(1, blocks-1):
+            layers.append(block(self.inplanes, planes))
+        layers.append(block(self.inplanes, planes, IN=IN))
+
+        return nn.Sequential(*layers)
+
+    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)
+
+        x = self.avgpool(x)
+        x = x.view(x.size(0), -1)
+        x = self.fc(x)
+
+        return x
+
+
+def se_resnet50_ibn_b(num_classes=1000):
+    """Constructs a ResNet-50 model.
+
+    Args:
+        pretrained (bool): If True, returns a model pre-trained on ImageNet
+    """
+    model = ResNet(SEBottleneck, [3, 4, 6, 3], num_classes=num_classes)
+    model.avgpool = nn.AdaptiveAvgPool2d(1)
+    return model
+
+
+def se_resnet101_ibn_b(num_classes=1000):
+    """Constructs a ResNet-101 model.
+
+    Args:
+        pretrained (bool): If True, returns a model pre-trained on ImageNet
+    """
+    model = ResNet(SEBottleneck, [3, 4, 23, 3], num_classes=num_classes)
+    model.avgpool = nn.AdaptiveAvgPool2d(1)
+    return model
+
+
+def se_resnet152_ibn_b(num_classes):
+    """Constructs a ResNet-152 model.
+
+    Args:
+        pretrained (bool): If True, returns a model pre-trained on ImageNet
+    """
+    model = ResNet(SEBottleneck, [3, 8, 36, 3], num_classes=num_classes)
+    model.avgpool = nn.AdaptiveAvgPool2d(1)
+    return model
diff --git a/test.sh b/test.sh
index 7f43b35..052feb8 100755
--- a/test.sh
+++ b/test.sh
@@ -5,7 +5,7 @@ data_path=/pathToYourImageNetDataset/
 python -u imagenet.py \
     -a $model \
     --test-batch 100 \
-    --model_weight pretrained/${model}.pth.tar \
+    --model_weight pretrained/${model}.pth \
     -e \
     -j 16 \
     --data $data_path \