023-216095/Cherry
/README.md
import torch
from torch import nn
from collections import OrderedDict
from cherry.core import Module
from cherry.layers import Flatten, Linear, ReLU, Sigmoid, Tanh, Softmax, Dropout, BatchNorm2d, MaxPool2d
class ResNet(Module):
def __init__(self, num_classes, block, layers, num_channels=64):
super(ResNet, self).__init__()
self.in_channels = num_channels
self.layers = layers
self.conv1 = nn.Conv2d(3, num_channels, kernel_size=3, stride=1, padding=1, bias=False)
self.bn1 = BatchNorm2d(num_channels)
self.relu = ReLU(inplace=True)
self.layer1 = self._make_layer(block, 64, layers[0])
self.layer2 = self._make_layer(block, 128, layers[1], stride=2)
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)
for m in self.modules():
if isinstance(m, nn.Conv2d):
nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
elif isinstance(m, (nn.BatchNorm2d, nn.GroupNorm)):
nn.init.constant_(m.weight, 1)
nn.init.constant_(m.bias, 0)
def _make_layer(self, block, planes, blocks, stride=1):
downsample = None
if stride != 1 or self.in_channels != planes * block.expansion:
downsample = nn.Sequential(
nn.Conv2d(self.in_channels, planes * block.expansion, kernel_size=1, stride=stride, bias=False),
BatchNorm2d(planes * block.expansion)
)
layers = []
layers.append(block(self.in_channels, planes, stride, downsample))
self.in_channels = planes * block.expansion
for _ in range(1, blocks):
layers.append(block(self.in_channels, planes))
return nn.Sequential(*layers)
def forward(self, x):
x = self.conv1(x)
x = self.bn1(x)
x = self.relu(x)
x = self.layer1(x)
x = self.layer2(x)
x = self.layer3(x)
x = self.layer4(x)
x = self.avgpool(x)
x = torch.flatten(x, 1)
x = self.fc(x)
return x
class BasicBlock(nn.Module):
expansion = 1
def __init__(self, in_channels, planes, stride=1, downsample=None):
super(BasicBlock, self).__init__()
self.conv1 = nn.Conv2d(in_channels, planes, kernel_size=3, stride=stride, padding=1, bias=False)
self.bn1 = BatchNorm2d(planes)
self.relu = ReLU(inplace=True)
self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=1, padding=1, bias=False)
self.bn2 = BatchNorm2d(planes)
self.downsample = downsample
self.stride = stride
def forward(self, x):
identity = x
out = self.conv1(x)
out = self.bn1(out)
out = self.relu(out)
out = self.conv2(out)
out = self.bn2(out)
if self.downsample is not None:
identity = self.downsample(x)
out += identity
out = self.relu(out)
return out
class ResNet18(ResNet):
def __init__(self, num_classes):
super(ResNet18, self).__init__(num_classes, BasicBlock, [2, 2, 2, 2])
class ResNet34(ResNet):
def __init__(self, num_classes):
super(ResNet34, self).__init__(num_classes, BasicBlock, [3, 4, 6, 3])
class ResNet50(ResNet):
def __init__(self, num_classes):
super(ResNet50, self).__init__(num_classes, Bottleneck, [3, 4, 6, 3])
class ResNet101(ResNet):
def __init__(self, num_classes):
super(ResNet101, self).__init__(num_classes, Bottleneck, [3, 4, 23, 3])
class ResNet152(ResNet):
def __init__(self, num_classes):
super(ResNet152, self).__init__(num_classes, Bottleneck, [3, 8, 36, 3])
class ResNet18(nn.Module):
def __init__(self, num_classes):
super(ResNet18, self).__init__()
self.conv1 = nn.Conv2d(3, 64, kernel_size=3, stride=1, padding=1, bias=False)
self.bn1 = BatchNorm2d(64)
self.relu = ReLU(inplace=True)
self.layer1 = self._make_layer(64, 2, BasicBlock, stride=1)
self.layer2