Downloads/preact_resnet.py Downloads/resnet18k.py
import torch.nn as nn
import torch.nn.functional as F

class PreActBlock(nn.Module):
    '''Pre-activation version of the BasicBlock.'''
    expansion = 1

    def __init__(self, in_planes, planes, stride=1):                                                                                                                                        
        super(PreActBlock, self).__init__()
        self.bn1 = nn.BatchNorm2d(in_planes)
        self.conv1 = nn.Conv2d(in_planes, planes, kernel_size=3, stride=stride, padding=1, bias=False)
        self.bn2 = nn.BatchNorm2d(planes)
        self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=1, padding=1, bias=False)

+--  8 lines: if stride != 1 or in_planes != self.expansion*planes:-------------------------------------------------------------------------------------------------------------------------
        out = self.conv1(out)
        out = self.conv2(F.relu(self.bn2(out)))
        out += shortcut
        return out

class PreActResNet(nn.Module):
    def __init__(self, block, num_blocks, num_classes=10):                                                                                                                                  
        super(PreActResNet, self).__init__()
        self.in_planes = 64                                                                                                                                                                 
--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------

        self.conv1 = nn.Conv2d(3, 64, kernel_size=3, stride=1, padding=1, bias=False)                                                                                                       
        self.layer1 = self._make_layer(block, 64, num_blocks[0], stride=1)                                                                                                                  
        self.layer2 = self._make_layer(block, 128, num_blocks[1], stride=2)                                                                                                                 
        self.layer3 = self._make_layer(block, 256, num_blocks[2], stride=2)                                                                                                                 
        self.layer4 = self._make_layer(block, 512, num_blocks[3], stride=2)                                                                                                                 
        self.linear = nn.Linear(512*block.expansion, num_classes)                                                                                                                           

    def _make_layer(self, block, planes, num_blocks, stride):
--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
        strides = [stride] + [1]*(num_blocks-1)
        layers = []
        for stride in strides:
            layers.append(block(self.in_planes, planes, stride))
            self.in_planes = planes * block.expansion
        return nn.Sequential(*layers)
+-- 11 lines: def forward(self, x):---------------------------------------------------------------------------------------------------------------------------------------------------------
import torch.nn as nn
import torch.nn.functional as F

class PreActBlock(nn.Module):
    '''Pre-activation version of the BasicBlock.'''
    expansion = 1

    def __init__(self, in_planes, planes, stride=1, **kwargs):                                                                                                                              
        super(PreActBlock, self).__init__()
        self.bn1 = nn.BatchNorm2d(in_planes)
        self.conv1 = nn.Conv2d(in_planes, planes, kernel_size=3, stride=stride, padding=1, bias=False)
        self.bn2 = nn.BatchNorm2d(planes)
        self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=1, padding=1, bias=False)

+--  8 lines: if stride != 1 or in_planes != self.expansion*planes:-------------------------------------------------------------------------------------------------------------------------
        out = self.conv1(out)
        out = self.conv2(F.relu(self.bn2(out)))
        out += shortcut
        return out

class PreActResNet(nn.Module):
    def __init__(self, block, num_blocks, num_classes=10, init_channels=64):                                                                                                                
        super(PreActResNet, self).__init__()
        self.in_planes = init_channels                                                                                                                                                      
        c = init_channels                                                                                                                                                                   

        self.conv1 = nn.Conv2d(3, c, kernel_size=3, stride=1, padding=1, bias=False)                                                                                                        
        self.layer1 = self._make_layer(block, c, num_blocks[0], stride=1)                                                                                                                   
        self.layer2 = self._make_layer(block, 2*c, num_blocks[1], stride=2)                                                                                                                 
        self.layer3 = self._make_layer(block, 4*c, num_blocks[2], stride=2)                                                                                                                 
        self.layer4 = self._make_layer(block, 8*c, num_blocks[3], stride=2)                                                                                                                 
        self.linear = nn.Linear(8*c*block.expansion, num_classes)                                                                                                                           

    def _make_layer(self, block, planes, num_blocks, stride):
        # eg: [2, 1, 1, ..., 1]. Only the first one downsamples.                                                                                                                            
        strides = [stride] + [1]*(num_blocks-1)
        layers = []
        for stride in strides:
            layers.append(block(self.in_planes, planes, stride))
            self.in_planes = planes * block.expansion
        return nn.Sequential(*layers)
+-- 11 lines: def forward(self, x):---------------------------------------------------------------------------------------------------------------------------------------------------------