import paddle
import paddle.nn as nn
import math
class OctaveConv(nn.Layer):
 def __init__(self, in_channels, out_channels, kernel_size, alpha_in=0.5, alpha_out=0.5, stride=1, padding=0, dilation=1,
                 groups=1, bias=False):
 super(OctaveConv, self).__init__()
 self.downsample = nn.AvgPool2D(kernel_size=(2, 2), stride=2)
 self.upsample = nn.Upsample(scale_factor=2, mode='nearest')
 assert stride == 1 or stride == 2, "Stride should be 1 or 2."
 self.stride = stride
 self.is_dw = groups == in_channels
 assert 0 <= alpha_in <= 1 and 0 <= alpha_out <= 1, "Alphas should be in the interval from 0 to 1."
 self.alpha_in, self.alpha_out = alpha_in, alpha_out
 self.conv_l2l = None if alpha_in == 0 or alpha_out == 0 else  nn.Conv2D(int(alpha_in * in_channels), int(alpha_out * out_channels),
 kernel_size, 1, padding, dilation, math.ceil(alpha_in * groups))
 self.conv_l2h = None if alpha_in == 0 or alpha_out == 1 or self.is_dw else  nn.Conv2D(int(alpha_in * in_channels), out_channels - int(alpha_out * out_channels),
 kernel_size, 1, padding, dilation, groups)
 self.conv_h2l = None if alpha_in == 1 or alpha_out == 0 or self.is_dw else  nn.Conv2D(in_channels - int(alpha_in * in_channels), int(alpha_out * out_channels),
 kernel_size, 1, padding, dilation, groups)
 self.conv_h2h = None if alpha_in == 1 or alpha_out == 1 else  nn.Conv2D(in_channels - int(alpha_in * in_channels), out_channels - int(alpha_out * out_channels),
 kernel_size, 1, padding, dilation, math.ceil(groups - alpha_in * groups))
 def forward(self, x):
 x_h, x_l = x if type(x) is tuple else (x, None)
 x_h = self.downsample(x_h) if self.stride == 2 else x_h
        x_h2h = self.conv_h2h(x_h)
        x_h2l = self.conv_h2l(self.downsample(x_h)) if self.alpha_out > 0 and not self.is_dw else None
 if x_l is not None:
            x_l2l = self.downsample(x_l) if self.stride == 2 else x_l
            x_l2l = self.conv_l2l(x_l2l) if self.alpha_out > 0 else None
 if self.is_dw:
 return x_h2h, x_l2l
 else:
                x_l2h = self.conv_l2h(x_l)
                x_l2h = self.upsample(x_l2h) if self.stride == 1 else x_l2h
 x_h = x_l2h + x_h2h
 x_l = x_h2l + x_l2l if x_h2l is not None and x_l2l is not None else None
 return x_h, x_l
 else:
 return x_h2h, x_h2l
class Conv_BN(nn.Layer):
 def __init__(self, in_channels, out_channels, kernel_size, alpha_in=0.5, alpha_out=0.5, stride=1, padding=0, dilation=1,
                 groups=1, bias=False, norm_layer=nn.BatchNorm2D):
 super(Conv_BN, self).__init__()
 self.conv = OctaveConv(in_channels, out_channels, kernel_size, alpha_in, alpha_out, stride, padding, dilation,
                               groups, bias)
 self.bn_h = None if alpha_out == 1 else norm_layer(int(out_channels * (1 - alpha_out)))
 self.bn_l = None if alpha_out == 0 else norm_layer(int(out_channels * alpha_out))
 def forward(self, x):
 x_h, x_l = self.conv(x)
 x_h = self.bn_h(x_h)
 x_l = self.bn_l(x_l) if x_l is not None else None
 return x_h, x_l
class Conv_BN_ACT(nn.Layer):
 def __init__(self, in_channels=3, out_channels=32, kernel_size=3, alpha_in=0.5, alpha_out=0.5, stride=1, padding=0, dilation=1,
                 groups=1, bias=False, norm_layer=nn.BatchNorm2D, activation_layer=nn.ReLU):
 super(Conv_BN_ACT, self).__init__()
 self.conv = OctaveConv(in_channels, out_channels, kernel_size, alpha_in, alpha_out, stride, padding, dilation,
                               groups, bias)
 self.bn_h = None if alpha_out == 1 else norm_layer(int(out_channels * (1 - alpha_out)))
 self.bn_l = None if alpha_out == 0 else norm_layer(int(out_channels * alpha_out))
 self.act = activation_layer()
 def forward(self, x):
 x_h, x_l = self.conv(x)
 x_h = self.act(self.bn_h(x_h))
 x_l = self.act(self.bn_l(x_l)) if x_l is not None else None
 return x_h, x_l

# Oct-Mobilnetv1
import paddle.nn as nn
__all__ = ['oct_mobilenet']
def conv_bn(inp, oup, stride):
 return nn.Sequential(
 nn.Conv2D(inp, oup, 3, stride, 1),
 nn.BatchNorm2D(oup),
 nn.ReLU()
 )
def conv_dw(inp, oup, stride, alpha_in=0.5, alpha_out=0.5):
 return nn.Sequential(
 Conv_BN_ACT(inp, inp, kernel_size=3, stride=stride, padding=1, groups=inp,   alpha_in=alpha_in, alpha_out=alpha_in if alpha_out != alpha_in else alpha_out),
 Conv_BN_ACT(inp, oup, kernel_size=1, alpha_in=alpha_in, alpha_out=alpha_out)
 )
class OctMobileNet(nn.Layer):
 def __init__(self, num_classes=1000):
 super(OctMobileNet, self).__init__()
 self.features = nn.Sequential(
 conv_bn( 3, 32, 2),
 conv_dw( 32, 64, 1, 0, 0.5),
 conv_dw( 64, 128, 2),
 conv_dw(128, 128, 1),
 conv_dw(128, 256, 2), 
 conv_dw(256, 256, 1),
 conv_dw(256, 512, 2),
 conv_dw(512, 512, 1),
 conv_dw(512, 512, 1),
 conv_dw(512, 512, 1),
 conv_dw(512, 512, 1),
 conv_dw(512, 512, 1, 0.5, 0),
 conv_dw(512, 1024, 2, 0, 0),
 conv_dw(1024, 1024, 1, 0, 0),
 )
 self.avgpool = nn.AdaptiveAvgPool2D((1, 1))
 self.fc = nn.Linear(1024, num_classes)
 def forward(self, x):
 x_h, x_l = self.features(x)
        x = self.avgpool(x_h)
        x = x.reshape([-1, 1024])
        x = self.fc(x)
 return x
def oct_mobilenet(**kwargs):
 """
    Constructs a Octave MobileNet V1 model
    """
 return OctMobileNet(**kwargs)

import paddle.nn as nn
__all__ = ['OctResNet', 'oct_resnet50', 'oct_resnet101', 'oct_resnet152', 'oct_resnet200']
class Bottleneck(nn.Layer):
    expansion = 4
 def __init__(self, inplanes, planes, stride=1, downsample=None, groups=1,
 base_width=64, alpha_in=0.5, alpha_out=0.5, norm_layer=None, output=False):
 super(Bottleneck, self).__init__()
 if norm_layer is None:
 norm_layer = nn.BatchNorm2D
        width = int(planes * (base_width / 64.)) * groups
 # Both self.conv2 and self.downsample layers downsample the input when stride != 1
 self.conv1 = Conv_BN_ACT(inplanes, width, kernel_size=1, alpha_in=alpha_in, alpha_out=alpha_out, norm_layer=norm_layer)
 self.conv2 = Conv_BN_ACT(width, width, kernel_size=3, stride=stride, padding=1, groups=groups, norm_layer=norm_layer,
 alpha_in=0 if output else 0.5, alpha_out=0 if output else 0.5)
 self.conv3 = Conv_BN(width, planes * self.expansion, kernel_size=1, norm_layer=norm_layer,
 alpha_in=0 if output else 0.5, alpha_out=0 if output else 0.5)
 self.relu = nn.ReLU()
 self.downsample = downsample
 self.stride = stride
 def forward(self, x):
 identity_h = x[0] if type(x) is tuple else x
 identity_l = x[1] if type(x) is tuple else None
 x_h, x_l = self.conv1(x)
 x_h, x_l = self.conv2((x_h, x_l))
 x_h, x_l = self.conv3((x_h, x_l))
 if self.downsample is not None:
 identity_h, identity_l = self.downsample(x)
 x_h += identity_h
 x_l = x_l + identity_l if identity_l is not None else None
 x_h = self.relu(x_h)
 x_l = self.relu(x_l) if x_l is not None else None
 return x_h, x_l
class OctResNet(nn.Layer):
 def __init__(self, block, layers, num_classes=1000, zero_init_residual=False,
                 groups=1, width_per_group=64, norm_layer=None):
 super(OctResNet, self).__init__()
 if norm_layer is None:
 norm_layer = nn.BatchNorm2D
 self.inplanes = 64
 self.groups = groups
 self.base_width = width_per_group
 self.conv1 = nn.Conv2D(3, self.inplanes, kernel_size=7, stride=2, padding=3,
 )
        self.bn1 = norm_layer(self.inplanes)
 self.relu = nn.ReLU()
 self.maxpool = nn.MaxPool2D(kernel_size=3, stride=2, padding=1)
 self.layer1 = self._make_layer(block, 64, layers[0], norm_layer=norm_layer, alpha_in=0)
 self.layer2 = self._make_layer(block, 128, layers[1], stride=2, norm_layer=norm_layer)
 self.layer3 = self._make_layer(block, 256, layers[2], stride=2, norm_layer=norm_layer)
 self.layer4 = self._make_layer(block, 512, layers[3], stride=2, norm_layer=norm_layer, alpha_out=0, output=True)
 self.avgpool = nn.AdaptiveAvgPool2D((1, 1))
 self.fc = nn.Linear(512 * block.expansion, num_classes)
 def _make_layer(self, block, planes, blocks, stride=1, alpha_in=0.5, alpha_out=0.5, norm_layer=None, output=False):
 if norm_layer is None:
 norm_layer = nn.BatchNorm2D
 downsample = None
 if stride != 1 or self.inplanes != planes * block.expansion:
 downsample = nn.Sequential(
 Conv_BN(self.inplanes, planes * block.expansion, kernel_size=1, stride=stride, alpha_in=alpha_in, alpha_out=alpha_out)
 )
        layers = []
 layers.append(block(self.inplanes, planes, stride, downsample, self.groups,
 self.base_width, alpha_in, alpha_out, norm_layer, output))
 self.inplanes = planes * block.expansion
 for _ in range(1, blocks):
 layers.append(block(self.inplanes, planes, groups=self.groups,
 base_width=self.base_width, norm_layer=norm_layer,
 alpha_in=0 if output else 0.5, alpha_out=0 if output else 0.5, output=output))
 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_h, x_l = self.layer1(x)
 x_h, x_l = self.layer2((x_h,x_l))
 x_h, x_l = self.layer3((x_h,x_l))
 x_h, x_l = self.layer4((x_h,x_l))
        x = self.avgpool(x_h)
        x = x.reshape([x.shape[0], -1])
        x = self.fc(x)
 return x
def oct_resnet50(pretrained=False, **kwargs):
 """Constructs a Octave ResNet-50 model.
 Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
    """
    model = OctResNet(Bottleneck, [3, 4, 6, 3], **kwargs)
 return model
def oct_resnet101(pretrained=False, **kwargs):
 """Constructs a Octave ResNet-101 model.
 Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
    """
    model = OctResNet(Bottleneck, [3, 4, 23, 3], **kwargs)
 return model
def oct_resnet152(pretrained=False, **kwargs):
 """Constructs a Octave ResNet-152 model.
 Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
    """
    model = OctResNet(Bottleneck, [3, 8, 36, 3], **kwargs)
 return model
def oct_resnet200(pretrained=False, **kwargs):
 """Constructs a Octave ResNet-200 model.
 Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
    """
    model = OctResNet(Bottleneck, [3, 24, 36, 3], **kwargs)
 return model

Octmobilnet_model = oct_mobilenet(num_classes=10)
# inputs = paddle.randn((1, 2, 224, 224))
# print(model(inputs))
paddle.summary(Octmobilnet_model,(16,3,224,224))

import paddle
from paddle.metric import Accuracy
from paddle.vision.transforms import Compose, Normalize, Resize, Transpose, ToTensor
callback = paddle.callbacks.VisualDL(log_dir='visualdl_log_dir_octmobilenet')
normalize = Normalize(mean=[0.5, 0.5, 0.5],
                    std=[0.5, 0.5, 0.5],
 data_format='HWC')
transform = Compose([ToTensor(), Normalize(), Resize(size=(224,224))])
cifar10_train = paddle.vision.datasets.Cifar10(mode='train',
                                               transform=transform)
cifar10_test = paddle.vision.datasets.Cifar10(mode='test',
                                              transform=transform)
# 构建训练集数据加载器
train_loader = paddle.io.DataLoader(cifar10_train, batch_size=768, shuffle=True, drop_last=True)
# 构建测试集数据加载器
test_loader = paddle.io.DataLoader(cifar10_test, batch_size=768, shuffle=True, drop_last=True)
Octmobilnet_model = paddle.Model(oct_mobilenet(num_classes=10))
optim = paddle.optimizer.Adam(learning_rate=0.001, parameters=Octmobilnet_model.parameters())
Octmobilnet_model.prepare(
 optim,
 paddle.nn.CrossEntropyLoss(),
 Accuracy()
 )
Octmobilnet_model.fit(train_data=train_loader,
 eval_data=test_loader,
        epochs=12,
        callbacks=callback,
        verbose=1
 )

from paddle.vision.models import MobileNetV1
mobile_model = MobileNetV1(num_classes=10)
# inputs = paddle.randn((1, 2, 224, 224))
# print(model(inputs))
paddle.summary(mobile_model,(16,3,224,224))

import paddle
from paddle.metric import Accuracy
from paddle.vision.transforms import Compose, Normalize, Resize, Transpose, ToTensor
callback = paddle.callbacks.VisualDL(log_dir='visualdl_log_dir_mobilenet')
normalize = Normalize(mean=[0.5, 0.5, 0.5],
                    std=[0.5, 0.5, 0.5],
 data_format='HWC')
transform = Compose([ToTensor(), Normalize(), Resize(size=(224,224))])
cifar10_train = paddle.vision.datasets.Cifar10(mode='train',
                                               transform=transform)
cifar10_test = paddle.vision.datasets.Cifar10(mode='test',
                                              transform=transform)
# 构建训练集数据加载器
train_loader = paddle.io.DataLoader(cifar10_train, batch_size=768, shuffle=True, drop_last=True)
# 构建测试集数据加载器
test_loader = paddle.io.DataLoader(cifar10_test, batch_size=768, shuffle=True, drop_last=True)
mobile_model = paddle.Model(MobileNetV1(num_classes=10))
optim = paddle.optimizer.Adam(learning_rate=0.001, parameters=mobile_model.parameters())
mobile_model.prepare(
 optim,
 paddle.nn.CrossEntropyLoss(),
 Accuracy()
 )
mobile_model.fit(train_data=train_loader,
 eval_data=test_loader,
        epochs=12,
        callbacks=callback,
        verbose=1
 )

octresnet50_model = oct_resnet50(num_classes=10)
paddle.summary(octresnet50_model,(16,3,224,224))

import paddle
from paddle.metric import Accuracy
from paddle.vision.transforms import Compose, Normalize, Resize, Transpose, ToTensor
callback = paddle.callbacks.VisualDL(log_dir='visualdl_log_dir_octresnet')
normalize = Normalize(mean=[0.5, 0.5, 0.5],
                    std=[0.5, 0.5, 0.5],
 data_format='HWC')
transform = Compose([ToTensor(), Normalize(), Resize(size=(224,224))])
cifar10_train = paddle.vision.datasets.Cifar10(mode='train',
                                               transform=transform)
cifar10_test = paddle.vision.datasets.Cifar10(mode='test',
                                              transform=transform)
# 构建训练集数据加载器
train_loader = paddle.io.DataLoader(cifar10_train, batch_size=256, shuffle=True, drop_last=True)
# 构建测试集数据加载器
test_loader = paddle.io.DataLoader(cifar10_test, batch_size=256, shuffle=True, drop_last=True)
oct_resnet50 = paddle.Model(oct_resnet50(num_classes=10))
optim = paddle.optimizer.Adam(learning_rate=0.001, parameters=oct_resnet50.parameters())
oct_resnet50.prepare(
 optim,
 paddle.nn.CrossEntropyLoss(),
 Accuracy()
 )
oct_resnet50.fit(train_data=train_loader,
 eval_data=test_loader,
        epochs=12,
        callbacks=callback,
        verbose=1
 )

import paddle
# build model
resmodel = resnet50(num_classes=10)
paddle.summary(resmodel,(16,3,224,224))

import paddle
from paddle.metric import Accuracy
from paddle.vision.transforms import Compose, Normalize, Resize, Transpose, ToTensor
from paddle.vision.models import resnet50
callback = paddle.callbacks.VisualDL(log_dir='visualdl_log_dir_resnet')
normalize = Normalize(mean=[0.5, 0.5, 0.5],
                    std=[0.5, 0.5, 0.5],
 data_format='HWC')
transform = Compose([ToTensor(), Normalize(), Resize(size=(224,224))])
cifar10_train = paddle.vision.datasets.Cifar10(mode='train',
                                               transform=transform)
cifar10_test = paddle.vision.datasets.Cifar10(mode='test',
                                              transform=transform)
# 构建训练集数据加载器
train_loader = paddle.io.DataLoader(cifar10_train, batch_size=256, shuffle=True, drop_last=True)
# 构建测试集数据加载器
test_loader = paddle.io.DataLoader(cifar10_test, batch_size=256, shuffle=True, drop_last=True)
res_model = paddle.Model(resnet50(num_classes=10))
optim = paddle.optimizer.Adam(learning_rate=0.001, parameters=res_model.parameters())
res_model.prepare(
 optim,
 paddle.nn.CrossEntropyLoss(),
 Accuracy()
 )
res_model.fit(train_data=train_loader,
 eval_data=test_loader,
        epochs=12,
        callbacks=callback,
        verbose=1
 )