以下是 ResRep 的 PyTorch 版本的源代码：
```python
import torch
import torch.nn as nn
import torch.nn.functional as F
class ResidualBlock(nn.Module):
def __init__(self, in_channels, out_channels, stride=1):
super(ResidualBlock, self).__init__()
self.conv1 = nn.Conv2d(in_channels, out_channels, kernel_size=3, stride=stride, padding=1, bias=False)
self.bn1 = nn.BatchNorm2d(out_channels)
self.conv2 = nn.Conv2d(out_channels, out_channels, kernel_size=3, stride=1, padding=1, bias=False)
self.bn2 = nn.BatchNorm2d(out_channels)
self.shortcut = nn.Sequential()
if stride != 1 or in_channels != out_channels:
self.shortcut = nn.Sequential(
nn.Conv2d(in_channels, out_channels, kernel_size=1, stride=stride, bias=False),
nn.BatchNorm2d(out_channels)
)
def forward(self, x):
out = F.relu(self.bn1(self.conv1(x)))
out = self.bn2(self.conv2(out))
out += self.shortcut(x)
out = F.relu(out)
return out
class ResNet(nn.Module):
def __init__(self, block, num_blocks, num_classes=10):
super(ResNet, self).__init__()
self.in_channels = 64
self.conv1 = nn.Conv2d(3, 64, kernel_size=3, stride=1, padding=1, bias=False)
self.bn1 = nn.BatchNorm2d(64)
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.avg_pool = nn.AdaptiveAvgPool2d((1, 1))
self.fc = nn.Linear(512, num_classes)
def make_layer(self, block, out_channels, num_blocks, stride):
layers = []
layers.append(block(self.in_channels, out_channels, stride))
self.in_channels = out_channels
for i in range(num_blocks - 1):
layers.append(block(out_channels, out_channels, stride=1))
return nn.Sequential(*layers)
def forward(self, x):
out = F.relu(self.bn1(self.conv1(x)))
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
def ResRep18():
return ResNet(ResidualBlock, [2, 2, 2, 2])
def ResRep34():
return ResNet(ResidualBlock, [3, 4, 6, 3])
def ResRep50():
return ResNet(BottleneckBlock, [3, 4, 6, 3])
def ResRep101():
return ResNet(BottleneckBlock, [3, 4, 23, 3])
def ResRep152():
return ResNet(BottleneckBlock, [3, 8, 36, 3])
```
这里定义了 ResidualBlock 类和 ResNet 类，其中 ResNet 由多个 ResidualBlock 组成。可以通过调用 ResRep18()、ResRep34()、ResRep50()、ResRep101() 和 ResRep152() 函数来获取不同深度的 ResNet 模型。
《ResRep: Lossless CNN Pruning via Decoupling Remembering and Forgetting》提出了一种在CNN中无损剪枝的方法，通过在卷积层后加入1x1卷积的修剪层，解耦训练与修剪过程，避免影响模型准确性。通过在修剪层施加惩罚项，促进通道的稀疏性，并在训练后删除接近零的通道，最终实现等价的修剪模型。
最低0.47元/天 解锁文章
扫一扫
396
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
