EPSANet：多尺度通道注意力机制

本文复现了EPSANet，其核心是高效金字塔注意力分割模块（EPSA）。该模块通过SPC获取多尺度特征图，经SE提取注意力、Softmax校准后加权输出。文中给出模块及网络完整代码，构建了EPSANet50等模型，并在Cifar10上与ResNet-50对比，显示其性能更优，泛化性强，适用于多种下游任务。

前言

Hi guy！我们这下又见面了，这次是来复现 EPSANet

关于注意力机制，实际上最近我比较关注enhance一类的文章，这篇论文也可以算是划分到enhance一类，先上性能图

不得不说这个图做的还怪好看，可视化效果也蛮直观，性能还可以

不仅是图像分类，而且在下游任务比如目标检测分割上，也展现了良好的性能

高效金字塔注意力分割模块（EPSA）

EPSA模块可以有效地提取更细粒度的多尺度空间信息，同时可以建立更长距离的通道依赖关系

其中 SPC module 如下

PSA模块主要分四个步骤实现：

输出得到一个多尺度特征信息注意力加权之后的特征图。该特征图多尺度信息表示能力更丰富。

import paddleimport paddle.nn as nnimport mathdef conv(in_planes, out_planes, kernel_size=3, stride=1, padding=1, dilation=1, groups=1):    """standard convolution with padding"""    return nn.Conv2D(in_planes, out_planes, kernel_size=kernel_size, stride=stride,                     padding=padding, dilation=dilation, groups=groups, bias_attr=False)def conv1x1(in_planes, out_planes, stride=1):    """1x1 convolution"""    return nn.Conv2D(in_planes, out_planes, kernel_size=1, stride=stride, bias_attr=False)class SEWeightModule(nn.Layer):    def __init__(self, channels, reduction=16):        super(SEWeightModule, self).__init__()        self.avg_pool = nn.AdaptiveAvgPool2D(1)        self.fc1 = nn.Conv2D(channels, channels//reduction, kernel_size=1, padding=0)        self.relu = nn.ReLU()        self.fc2 = nn.Conv2D(channels//reduction, channels, kernel_size=1, padding=0)        self.sigmoid = nn.Sigmoid()    def forward(self, x):        out = self.avg_pool(x)        out = self.fc1(out)        out = self.relu(out)        out = self.fc2(out)        weight = self.sigmoid(out)        return weightclass PSAModule(nn.Layer):    def __init__(self, inplans, planes, conv_kernels=[3, 5, 7, 9], stride=1, conv_groups=[1, 4, 8, 16]):        super(PSAModule, self).__init__()        self.conv_1 = conv(inplans, planes//4, kernel_size=conv_kernels[0], padding=conv_kernels[0]//2,                            stride=stride, groups=conv_groups[0])        self.conv_2 = conv(inplans, planes//4, kernel_size=conv_kernels[1], padding=conv_kernels[1]//2,                            stride=stride, groups=conv_groups[1])        self.conv_3 = conv(inplans, planes//4, kernel_size=conv_kernels[2], padding=conv_kernels[2]//2,                            stride=stride, groups=conv_groups[2])        self.conv_4 = conv(inplans, planes//4, kernel_size=conv_kernels[3], padding=conv_kernels[3]//2,                            stride=stride, groups=conv_groups[3])        self.se = SEWeightModule(planes // 4)        self.split_channel = planes // 4        self.softmax = nn.Softmax(axis=1)    def forward(self, x):        # stage 1        batch_size = x.shape[0]        x1 = self.conv_1(x)        x2 = self.conv_2(x)        x3 = self.conv_3(x)        x4 = self.conv_4(x)        feats = paddle.concat((x1, x2, x3, x4), axis=1)        feats = feats.reshape([batch_size, 4, self.split_channel, feats.shape[2], feats.shape[3]])                # stage 2        x1_se = self.se(x1)        x2_se = self.se(x2)        x3_se = self.se(x3)        x4_se = self.se(x4)        x_se = paddle.concat((x1_se, x2_se, x3_se, x4_se), axis=1)        attention_vectors = x_se.reshape([batch_size, 4, self.split_channel, 1, 1])        attention_vectors = self.softmax(attention_vectors) # stage 3        # stage 4        feats_weight = feats * attention_vectors        for i in range(4):            x_se_weight_fp = feats_weight[:, i, :, :]            if i == 0:                out = x_se_weight_fp            else:                out = paddle.concat((x_se_weight_fp, out), axis=1)        return out

/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/layers/utils.py:26: DeprecationWarning: `np.int` is a deprecated alias for the builtin `int`. To silence this warning, use `int` by itself. Doing this will not modify any behavior and is safe. When replacing `np.int`, you may wish to use e.g. `np.int64` or `np.int32` to specify the precision. If you wish to review your current use, check the release note link for additional information.Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations  def convert_to_list(value, n, name, dtype=np.int):

# 验证 PSA psa = PSAModule(64, 64)x = paddle.randn([32, 64, 112, 112])y = psa(x)print(y)

EPSANet

现在搭建一个EPSANet，它基于EPSA Block，从下图可以看出EPSA Block用PSA模块代替了ResNet Block的Conv 3x3卷积

与ResNet-50对比

class EPSABlock(nn.Layer):    expansion = 4    def __init__(self, inplanes, planes, stride=1, downsample=None, norm_layer=None, conv_kernels=[3, 5, 7, 9],                 conv_groups=[1, 4, 8, 16]):        super(EPSABlock, self).__init__()        if norm_layer is None:            norm_layer = nn.BatchNorm2D        self.conv1 = conv1x1(inplanes, planes)        self.bn1 = norm_layer(planes)        self.conv2 = PSAModule(planes, planes, stride=stride, conv_kernels=conv_kernels, conv_groups=conv_groups)        self.bn2 = norm_layer(planes)        self.conv3 = conv1x1(planes, planes * self.expansion)        self.bn3 = norm_layer(planes * self.expansion)        self.relu = nn.ReLU()        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)        out = self.relu(out)        out = self.conv3(out)        out = self.bn3(out)        if self.downsample is not None:            identity = self.downsample(x)        out += identity        out = self.relu(out)        return outclass EPSANet(nn.Layer):    def __init__(self, block, layers, num_classes=1000):        super(EPSANet, self).__init__()        self.inplanes = 64        self.conv1 = nn.Conv2D(3, 64, kernel_size=7, stride=2, padding=3, bias_attr=False)        self.bn1 = nn.BatchNorm2D(64)        self.relu = nn.ReLU()        self.maxpool = nn.MaxPool2D(kernel_size=3, stride=2, padding=1)        self.layer1 = self._make_layers(block, 64, layers[0], stride=1)        self.layer2 = self._make_layers(block, 128, layers[1], stride=2)        self.layer3 = self._make_layers(block, 256, layers[2], stride=2)        self.layer4 = self._make_layers(block, 512, layers[3], stride=2)        self.avgpool = nn.AdaptiveAvgPool2D((1, 1))        self.fc = nn.Linear(512 * block.expansion, num_classes)                        for m in self.sublayers():            if isinstance(m, nn.Conv2D):                n = m.weight.shape[2] * m.weight.shape[3] * m.weight.shape[0]                normal_ = nn.initializer.Normal(std=math.sqrt(2. / n))                normal_(m.weight)    def _make_layers(self, block, planes, num_blocks, stride=1):        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_attr=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, num_blocks):            layers.append(block(self.inplanes, planes))        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.reshape([x.shape[0], -1])        x = self.fc(x)        return x

模型定义

def epsanet50(**kwarg):    model = EPSANet(EPSABlock, [3, 4, 6, 3], **kwarg)    return modeldef epsanet101():    model = EPSANet(EPSABlock, [3, 4, 23, 3], **kwarg)    return model

查看模型

paddle.Model(epsanet50()).summary((1,3,224,224))

--------------------------------------------------------------------------------    Layer (type)         Input Shape          Output Shape         Param #    ================================================================================     Conv2D-13        [[1, 3, 224, 224]]   [1, 64, 112, 112]        9,408        BatchNorm2D-1     [[1, 64, 112, 112]]   [1, 64, 112, 112]         256             ReLU-3        [[1, 64, 112, 112]]   [1, 64, 112, 112]          0           MaxPool2D-1      [[1, 64, 112, 112]]    [1, 64, 56, 56]           0            Conv2D-15        [[1, 64, 56, 56]]     [1, 64, 56, 56]         4,096        BatchNorm2D-3      [[1, 64, 56, 56]]     [1, 64, 56, 56]          256             ReLU-5         [[1, 256, 56, 56]]    [1, 256, 56, 56]          0            Conv2D-16        [[1, 64, 56, 56]]     [1, 16, 56, 56]         9,216          Conv2D-17        [[1, 64, 56, 56]]     [1, 16, 56, 56]         6,400          Conv2D-18        [[1, 64, 56, 56]]     [1, 16, 56, 56]         6,272          Conv2D-19        [[1, 64, 56, 56]]     [1, 16, 56, 56]         5,184     AdaptiveAvgPool2D-3   [[1, 16, 56, 56]]      [1, 16, 1, 1]            0            Conv2D-20         [[1, 16, 1, 1]]        [1, 1, 1, 1]           17              ReLU-4           [[1, 1, 1, 1]]        [1, 1, 1, 1]            0            Conv2D-21          [[1, 1, 1, 1]]       [1, 16, 1, 1]           32            Sigmoid-3         [[1, 16, 1, 1]]       [1, 16, 1, 1]            0         SEWeightModule-3    [[1, 16, 56, 56]]      [1, 16, 1, 1]            0            Softmax-3        [[1, 4, 16, 1, 1]]    [1, 4, 16, 1, 1]          0           PSAModule-3       [[1, 64, 56, 56]]     [1, 64, 56, 56]           0          BatchNorm2D-4      [[1, 64, 56, 56]]     [1, 64, 56, 56]          256           Conv2D-22        [[1, 64, 56, 56]]     [1, 256, 56, 56]       16,384        BatchNorm2D-5      [[1, 256, 56, 56]]    [1, 256, 56, 56]        1,024          Conv2D-14        [[1, 64, 56, 56]]     [1, 256, 56, 56]       16,384        BatchNorm2D-2      [[1, 256, 56, 56]]    [1, 256, 56, 56]        1,024         EPSABlock-1       [[1, 64, 56, 56]]     [1, 256, 56, 56]          0            Conv2D-23        [[1, 256, 56, 56]]    [1, 64, 56, 56]        16,384        BatchNorm2D-6      [[1, 64, 56, 56]]     [1, 64, 56, 56]          256             ReLU-7         [[1, 256, 56, 56]]    [1, 256, 56, 56]          0            Conv2D-24        [[1, 64, 56, 56]]     [1, 16, 56, 56]         9,216          Conv2D-25        [[1, 64, 56, 56]]     [1, 16, 56, 56]         6,400          Conv2D-26        [[1, 64, 56, 56]]     [1, 16, 56, 56]         6,272          Conv2D-27        [[1, 64, 56, 56]]     [1, 16, 56, 56]         5,184     AdaptiveAvgPool2D-4   [[1, 16, 56, 56]]      [1, 16, 1, 1]            0            Conv2D-28         [[1, 16, 1, 1]]        [1, 1, 1, 1]           17              ReLU-6           [[1, 1, 1, 1]]        [1, 1, 1, 1]            0            Conv2D-29          [[1, 1, 1, 1]]       [1, 16, 1, 1]           32            Sigmoid-4         [[1, 16, 1, 1]]       [1, 16, 1, 1]            0         SEWeightModule-4    [[1, 16, 56, 56]]      [1, 16, 1, 1]            0            Softmax-4        [[1, 4, 16, 1, 1]]    [1, 4, 16, 1, 1]          0           PSAModule-4       [[1, 64, 56, 56]]     [1, 64, 56, 56]           0          BatchNorm2D-7      [[1, 64, 56, 56]]     [1, 64, 56, 56]          256           Conv2D-30        [[1, 64, 56, 56]]     [1, 256, 56, 56]       16,384        BatchNorm2D-8      [[1, 256, 56, 56]]    [1, 256, 56, 56]        1,024         EPSABlock-2       [[1, 256, 56, 56]]    [1, 256, 56, 56]          0            Conv2D-31        [[1, 256, 56, 56]]    [1, 64, 56, 56]        16,384        BatchNorm2D-9      [[1, 64, 56, 56]]     [1, 64, 56, 56]          256             ReLU-9         [[1, 256, 56, 56]]    [1, 256, 56, 56]          0            Conv2D-32        [[1, 64, 56, 56]]     [1, 16, 56, 56]         9,216          Conv2D-33        [[1, 64, 56, 56]]     [1, 16, 56, 56]         6,400          Conv2D-34        [[1, 64, 56, 56]]     [1, 16, 56, 56]         6,272          Conv2D-35        [[1, 64, 56, 56]]     [1, 16, 56, 56]         5,184     AdaptiveAvgPool2D-5   [[1, 16, 56, 56]]      [1, 16, 1, 1]            0            Conv2D-36         [[1, 16, 1, 1]]        [1, 1, 1, 1]           17              ReLU-8           [[1, 1, 1, 1]]        [1, 1, 1, 1]            0            Conv2D-37          [[1, 1, 1, 1]]       [1, 16, 1, 1]           32            Sigmoid-5         [[1, 16, 1, 1]]       [1, 16, 1, 1]            0         SEWeightModule-5    [[1, 16, 56, 56]]      [1, 16, 1, 1]            0            Softmax-5        [[1, 4, 16, 1, 1]]    [1, 4, 16, 1, 1]          0           PSAModule-5       [[1, 64, 56, 56]]     [1, 64, 56, 56]           0          BatchNorm2D-10     [[1, 64, 56, 56]]     [1, 64, 56, 56]          256           Conv2D-38        [[1, 64, 56, 56]]     [1, 256, 56, 56]       16,384        BatchNorm2D-11     [[1, 256, 56, 56]]    [1, 256, 56, 56]        1,024         EPSABlock-3       [[1, 256, 56, 56]]    [1, 256, 56, 56]          0            Conv2D-40        [[1, 256, 56, 56]]    [1, 128, 56, 56]       32,768        BatchNorm2D-13     [[1, 128, 56, 56]]    [1, 128, 56, 56]         512            ReLU-11         [[1, 512, 28, 28]]    [1, 512, 28, 28]          0            Conv2D-41        [[1, 128, 56, 56]]    [1, 32, 28, 28]        36,864          Conv2D-42        [[1, 128, 56, 56]]    [1, 32, 28, 28]        25,600          Conv2D-43        [[1, 128, 56, 56]]    [1, 32, 28, 28]        25,088          Conv2D-44        [[1, 128, 56, 56]]    [1, 32, 28, 28]        20,736     AdaptiveAvgPool2D-6   [[1, 32, 28, 28]]      [1, 32, 1, 1]            0            Conv2D-45         [[1, 32, 1, 1]]        [1, 2, 1, 1]           66             ReLU-10           [[1, 2, 1, 1]]        [1, 2, 1, 1]            0            Conv2D-46          [[1, 2, 1, 1]]       [1, 32, 1, 1]           96            Sigmoid-6         [[1, 32, 1, 1]]       [1, 32, 1, 1]            0         SEWeightModule-6    [[1, 32, 28, 28]]      [1, 32, 1, 1]            0            Softmax-6        [[1, 4, 32, 1, 1]]    [1, 4, 32, 1, 1]          0           PSAModule-6       [[1, 128, 56, 56]]    [1, 128, 28, 28]          0          BatchNorm2D-14     [[1, 128, 28, 28]]    [1, 128, 28, 28]         512           Conv2D-47        [[1, 128, 28, 28]]    [1, 512, 28, 28]       65,536        BatchNorm2D-15     [[1, 512, 28, 28]]    [1, 512, 28, 28]        2,048          Conv2D-39        [[1, 256, 56, 56]]    [1, 512, 28, 28]       131,072       BatchNorm2D-12     [[1, 512, 28, 28]]    [1, 512, 28, 28]        2,048         EPSABlock-4       [[1, 256, 56, 56]]    [1, 512, 28, 28]          0            Conv2D-48        [[1, 512, 28, 28]]    [1, 128, 28, 28]       65,536        BatchNorm2D-16     [[1, 128, 28, 28]]    [1, 128, 28, 28]         512            ReLU-13         [[1, 512, 28, 28]]    [1, 512, 28, 28]          0            Conv2D-49        [[1, 128, 28, 28]]    [1, 32, 28, 28]        36,864          Conv2D-50        [[1, 128, 28, 28]]    [1, 32, 28, 28]        25,600          Conv2D-51        [[1, 128, 28, 28]]    [1, 32, 28, 28]        25,088          Conv2D-52        [[1, 128, 28, 28]]    [1, 32, 28, 28]        20,736     AdaptiveAvgPool2D-7   [[1, 32, 28, 28]]      [1, 32, 1, 1]            0            Conv2D-53         [[1, 32, 1, 1]]        [1, 2, 1, 1]           66             ReLU-12           [[1, 2, 1, 1]]        [1, 2, 1, 1]            0            Conv2D-54          [[1, 2, 1, 1]]       [1, 32, 1, 1]           96            Sigmoid-7         [[1, 32, 1, 1]]       [1, 32, 1, 1]            0         SEWeightModule-7    [[1, 32, 28, 28]]      [1, 32, 1, 1]            0            Softmax-7        [[1, 4, 32, 1, 1]]    [1, 4, 32, 1, 1]          0           PSAModule-7       [[1, 128, 28, 28]]    [1, 128, 28, 28]          0          BatchNorm2D-17     [[1, 128, 28, 28]]    [1, 128, 28, 28]         512           Conv2D-55        [[1, 128, 28, 28]]    [1, 512, 28, 28]       65,536        BatchNorm2D-18     [[1, 512, 28, 28]]    [1, 512, 28, 28]        2,048         EPSABlock-5       [[1, 512, 28, 28]]    [1, 512, 28, 28]          0            Conv2D-56        [[1, 512, 28, 28]]    [1, 128, 28, 28]       65,536        BatchNorm2D-19     [[1, 128, 28, 28]]    [1, 128, 28, 28]         512            ReLU-15         [[1, 512, 28, 28]]    [1, 512, 28, 28]          0            Conv2D-57        [[1, 128, 28, 28]]    [1, 32, 28, 28]        36,864          Conv2D-58        [[1, 128, 28, 28]]    [1, 32, 28, 28]        25,600          Conv2D-59        [[1, 128, 28, 28]]    [1, 32, 28, 28]        25,088          Conv2D-60        [[1, 128, 28, 28]]    [1, 32, 28, 28]        20,736     AdaptiveAvgPool2D-8   [[1, 32, 28, 28]]      [1, 32, 1, 1]            0            Conv2D-61         [[1, 32, 1, 1]]        [1, 2, 1, 1]           66             ReLU-14           [[1, 2, 1, 1]]        [1, 2, 1, 1]            0            Conv2D-62          [[1, 2, 1, 1]]       [1, 32, 1, 1]           96            Sigmoid-8         [[1, 32, 1, 1]]       [1, 32, 1, 1]            0         SEWeightModule-8    [[1, 32, 28, 28]]      [1, 32, 1, 1]            0            Softmax-8        [[1, 4, 32, 1, 1]]    [1, 4, 32, 1, 1]          0           PSAModule-8       [[1, 128, 28, 28]]    [1, 128, 28, 28]          0          BatchNorm2D-20     [[1, 128, 28, 28]]    [1, 128, 28, 28]         512           Conv2D-63        [[1, 128, 28, 28]]    [1, 512, 28, 28]       65,536        BatchNorm2D-21     [[1, 512, 28, 28]]    [1, 512, 28, 28]        2,048         EPSABlock-6       [[1, 512, 28, 28]]    [1, 512, 28, 28]          0            Conv2D-64        [[1, 512, 28, 28]]    [1, 128, 28, 28]       65,536        BatchNorm2D-22     [[1, 128, 28, 28]]    [1, 128, 28, 28]         512            ReLU-17         [[1, 512, 28, 28]]    [1, 512, 28, 28]          0            Conv2D-65        [[1, 128, 28, 28]]    [1, 32, 28, 28]        36,864          Conv2D-66        [[1, 128, 28, 28]]    [1, 32, 28, 28]        25,600          Conv2D-67        [[1, 128, 28, 28]]    [1, 32, 28, 28]        25,088          Conv2D-68        [[1, 128, 28, 28]]    [1, 32, 28, 28]        20,736     AdaptiveAvgPool2D-9   [[1, 32, 28, 28]]      [1, 32, 1, 1]            0            Conv2D-69         [[1, 32, 1, 1]]        [1, 2, 1, 1]           66             ReLU-16           [[1, 2, 1, 1]]        [1, 2, 1, 1]            0            Conv2D-70          [[1, 2, 1, 1]]       [1, 32, 1, 1]           96            Sigmoid-9         [[1, 32, 1, 1]]       [1, 32, 1, 1]            0         SEWeightModule-9    [[1, 32, 28, 28]]      [1, 32, 1, 1]            0            Softmax-9        [[1, 4, 32, 1, 1]]    [1, 4, 32, 1, 1]          0           PSAModule-9       [[1, 128, 28, 28]]    [1, 128, 28, 28]          0          BatchNorm2D-23     [[1, 128, 28, 28]]    [1, 128, 28, 28]         512           Conv2D-71        [[1, 128, 28, 28]]    [1, 512, 28, 28]       65,536        BatchNorm2D-24     [[1, 512, 28, 28]]    [1, 512, 28, 28]        2,048         EPSABlock-7       [[1, 512, 28, 28]]    [1, 512, 28, 28]          0            Conv2D-73        [[1, 512, 28, 28]]    [1, 256, 28, 28]       131,072       BatchNorm2D-26     [[1, 256, 28, 28]]    [1, 256, 28, 28]        1,024           ReLU-19        [[1, 1024, 14, 14]]   [1, 1024, 14, 14]          0            Conv2D-74        [[1, 256, 28, 28]]    [1, 64, 14, 14]        147,456         Conv2D-75        [[1, 256, 28, 28]]    [1, 64, 14, 14]        102,400         Conv2D-76        [[1, 256, 28, 28]]    [1, 64, 14, 14]        100,352         Conv2D-77        [[1, 256, 28, 28]]    [1, 64, 14, 14]        82,944     AdaptiveAvgPool2D-10  [[1, 64, 14, 14]]      [1, 64, 1, 1]            0            Conv2D-78         [[1, 64, 1, 1]]        [1, 4, 1, 1]           260            ReLU-18           [[1, 4, 1, 1]]        [1, 4, 1, 1]            0            Conv2D-79          [[1, 4, 1, 1]]       [1, 64, 1, 1]           320           Sigmoid-10        [[1, 64, 1, 1]]       [1, 64, 1, 1]            0        SEWeightModule-10    [[1, 64, 14, 14]]      [1, 64, 1, 1]            0            Softmax-10       [[1, 4, 64, 1, 1]]    [1, 4, 64, 1, 1]          0           PSAModule-10      [[1, 256, 28, 28]]    [1, 256, 14, 14]          0          BatchNorm2D-27     [[1, 256, 14, 14]]    [1, 256, 14, 14]        1,024          Conv2D-80        [[1, 256, 14, 14]]   [1, 1024, 14, 14]       262,144       BatchNorm2D-28    [[1, 1024, 14, 14]]   [1, 1024, 14, 14]        4,096          Conv2D-72        [[1, 512, 28, 28]]   [1, 1024, 14, 14]       524,288       BatchNorm2D-25    [[1, 1024, 14, 14]]   [1, 1024, 14, 14]        4,096         EPSABlock-8       [[1, 512, 28, 28]]   [1, 1024, 14, 14]          0            Conv2D-81       [[1, 1024, 14, 14]]    [1, 256, 14, 14]       262,144       BatchNorm2D-29     [[1, 256, 14, 14]]    [1, 256, 14, 14]        1,024           ReLU-21        [[1, 1024, 14, 14]]   [1, 1024, 14, 14]          0            Conv2D-82        [[1, 256, 14, 14]]    [1, 64, 14, 14]        147,456         Conv2D-83        [[1, 256, 14, 14]]    [1, 64, 14, 14]        102,400         Conv2D-84        [[1, 256, 14, 14]]    [1, 64, 14, 14]        100,352         Conv2D-85        [[1, 256, 14, 14]]    [1, 64, 14, 14]        82,944     AdaptiveAvgPool2D-11  [[1, 64, 14, 14]]      [1, 64, 1, 1]            0            Conv2D-86         [[1, 64, 1, 1]]        [1, 4, 1, 1]           260            ReLU-20           [[1, 4, 1, 1]]        [1, 4, 1, 1]            0            Conv2D-87          [[1, 4, 1, 1]]       [1, 64, 1, 1]           320           Sigmoid-11        [[1, 64, 1, 1]]       [1, 64, 1, 1]            0        SEWeightModule-11    [[1, 64, 14, 14]]      [1, 64, 1, 1]            0            Softmax-11       [[1, 4, 64, 1, 1]]    [1, 4, 64, 1, 1]          0           PSAModule-11      [[1, 256, 14, 14]]    [1, 256, 14, 14]          0          BatchNorm2D-30     [[1, 256, 14, 14]]    [1, 256, 14, 14]        1,024          Conv2D-88        [[1, 256, 14, 14]]   [1, 1024, 14, 14]       262,144       BatchNorm2D-31    [[1, 1024, 14, 14]]   [1, 1024, 14, 14]        4,096         EPSABlock-9      [[1, 1024, 14, 14]]   [1, 1024, 14, 14]          0            Conv2D-89       [[1, 1024, 14, 14]]    [1, 256, 14, 14]       262,144       BatchNorm2D-32     [[1, 256, 14, 14]]    [1, 256, 14, 14]        1,024           ReLU-23        [[1, 1024, 14, 14]]   [1, 1024, 14, 14]          0            Conv2D-90        [[1, 256, 14, 14]]    [1, 64, 14, 14]        147,456         Conv2D-91        [[1, 256, 14, 14]]    [1, 64, 14, 14]        102,400         Conv2D-92        [[1, 256, 14, 14]]    [1, 64, 14, 14]        100,352         Conv2D-93        [[1, 256, 14, 14]]    [1, 64, 14, 14]        82,944     AdaptiveAvgPool2D-12  [[1, 64, 14, 14]]      [1, 64, 1, 1]            0            Conv2D-94         [[1, 64, 1, 1]]        [1, 4, 1, 1]           260            ReLU-22           [[1, 4, 1, 1]]        [1, 4, 1, 1]            0            Conv2D-95          [[1, 4, 1, 1]]       [1, 64, 1, 1]           320           Sigmoid-12        [[1, 64, 1, 1]]       [1, 64, 1, 1]            0        SEWeightModule-12    [[1, 64, 14, 14]]      [1, 64, 1, 1]            0            Softmax-12       [[1, 4, 64, 1, 1]]    [1, 4, 64, 1, 1]          0           PSAModule-12      [[1, 256, 14, 14]]    [1, 256, 14, 14]          0          BatchNorm2D-33     [[1, 256, 14, 14]]    [1, 256, 14, 14]        1,024          Conv2D-96        [[1, 256, 14, 14]]   [1, 1024, 14, 14]       262,144       BatchNorm2D-34    [[1, 1024, 14, 14]]   [1, 1024, 14, 14]        4,096         EPSABlock-10     [[1, 1024, 14, 14]]   [1, 1024, 14, 14]          0            Conv2D-97       [[1, 1024, 14, 14]]    [1, 256, 14, 14]       262,144       BatchNorm2D-35     [[1, 256, 14, 14]]    [1, 256, 14, 14]        1,024           ReLU-25        [[1, 1024, 14, 14]]   [1, 1024, 14, 14]          0            Conv2D-98        [[1, 256, 14, 14]]    [1, 64, 14, 14]        147,456         Conv2D-99        [[1, 256, 14, 14]]    [1, 64, 14, 14]        102,400         Conv2D-100       [[1, 256, 14, 14]]    [1, 64, 14, 14]        100,352         Conv2D-101       [[1, 256, 14, 14]]    [1, 64, 14, 14]        82,944     AdaptiveAvgPool2D-13  [[1, 64, 14, 14]]      [1, 64, 1, 1]            0            Conv2D-102        [[1, 64, 1, 1]]        [1, 4, 1, 1]           260            ReLU-24           [[1, 4, 1, 1]]        [1, 4, 1, 1]            0            Conv2D-103         [[1, 4, 1, 1]]       [1, 64, 1, 1]           320           Sigmoid-13        [[1, 64, 1, 1]]       [1, 64, 1, 1]            0        SEWeightModule-13    [[1, 64, 14, 14]]      [1, 64, 1, 1]            0            Softmax-13       [[1, 4, 64, 1, 1]]    [1, 4, 64, 1, 1]          0           PSAModule-13      [[1, 256, 14, 14]]    [1, 256, 14, 14]          0          BatchNorm2D-36     [[1, 256, 14, 14]]    [1, 256, 14, 14]        1,024          Conv2D-104       [[1, 256, 14, 14]]   [1, 1024, 14, 14]       262,144       BatchNorm2D-37    [[1, 1024, 14, 14]]   [1, 1024, 14, 14]        4,096         EPSABlock-11     [[1, 1024, 14, 14]]   [1, 1024, 14, 14]          0            Conv2D-105      [[1, 1024, 14, 14]]    [1, 256, 14, 14]       262,144       BatchNorm2D-38     [[1, 256, 14, 14]]    [1, 256, 14, 14]        1,024           ReLU-27        [[1, 1024, 14, 14]]   [1, 1024, 14, 14]          0            Conv2D-106       [[1, 256, 14, 14]]    [1, 64, 14, 14]        147,456         Conv2D-107       [[1, 256, 14, 14]]    [1, 64, 14, 14]        102,400         Conv2D-108       [[1, 256, 14, 14]]    [1, 64, 14, 14]        100,352         Conv2D-109       [[1, 256, 14, 14]]    [1, 64, 14, 14]        82,944     AdaptiveAvgPool2D-14  [[1, 64, 14, 14]]      [1, 64, 1, 1]            0            Conv2D-110        [[1, 64, 1, 1]]        [1, 4, 1, 1]           260            ReLU-26           [[1, 4, 1, 1]]        [1, 4, 1, 1]            0            Conv2D-111         [[1, 4, 1, 1]]       [1, 64, 1, 1]           320           Sigmoid-14        [[1, 64, 1, 1]]       [1, 64, 1, 1]            0        SEWeightModule-14    [[1, 64, 14, 14]]      [1, 64, 1, 1]            0            Softmax-14       [[1, 4, 64, 1, 1]]    [1, 4, 64, 1, 1]          0           PSAModule-14      [[1, 256, 14, 14]]    [1, 256, 14, 14]          0          BatchNorm2D-39     [[1, 256, 14, 14]]    [1, 256, 14, 14]        1,024          Conv2D-112       [[1, 256, 14, 14]]   [1, 1024, 14, 14]       262,144       BatchNorm2D-40    [[1, 1024, 14, 14]]   [1, 1024, 14, 14]        4,096         EPSABlock-12     [[1, 1024, 14, 14]]   [1, 1024, 14, 14]          0            Conv2D-113      [[1, 1024, 14, 14]]    [1, 256, 14, 14]       262,144       BatchNorm2D-41     [[1, 256, 14, 14]]    [1, 256, 14, 14]        1,024           ReLU-29        [[1, 1024, 14, 14]]   [1, 1024, 14, 14]          0            Conv2D-114       [[1, 256, 14, 14]]    [1, 64, 14, 14]        147,456         Conv2D-115       [[1, 256, 14, 14]]    [1, 64, 14, 14]        102,400         Conv2D-116       [[1, 256, 14, 14]]    [1, 64, 14, 14]        100,352         Conv2D-117       [[1, 256, 14, 14]]    [1, 64, 14, 14]        82,944     AdaptiveAvgPool2D-15  [[1, 64, 14, 14]]      [1, 64, 1, 1]            0            Conv2D-118        [[1, 64, 1, 1]]        [1, 4, 1, 1]           260            ReLU-28           [[1, 4, 1, 1]]        [1, 4, 1, 1]            0            Conv2D-119         [[1, 4, 1, 1]]       [1, 64, 1, 1]           320           Sigmoid-15        [[1, 64, 1, 1]]       [1, 64, 1, 1]            0        SEWeightModule-15    [[1, 64, 14, 14]]      [1, 64, 1, 1]            0            Softmax-15       [[1, 4, 64, 1, 1]]    [1, 4, 64, 1, 1]          0           PSAModule-15      [[1, 256, 14, 14]]    [1, 256, 14, 14]          0          BatchNorm2D-42     [[1, 256, 14, 14]]    [1, 256, 14, 14]        1,024          Conv2D-120       [[1, 256, 14, 14]]   [1, 1024, 14, 14]       262,144       BatchNorm2D-43    [[1, 1024, 14, 14]]   [1, 1024, 14, 14]        4,096         EPSABlock-13     [[1, 1024, 14, 14]]   [1, 1024, 14, 14]          0            Conv2D-122      [[1, 1024, 14, 14]]    [1, 512, 14, 14]       524,288       BatchNorm2D-45     [[1, 512, 14, 14]]    [1, 512, 14, 14]        2,048           ReLU-31         [[1, 2048, 7, 7]]     [1, 2048, 7, 7]           0            Conv2D-123       [[1, 512, 14, 14]]     [1, 128, 7, 7]        589,824         Conv2D-124       [[1, 512, 14, 14]]     [1, 128, 7, 7]        409,600         Conv2D-125       [[1, 512, 14, 14]]     [1, 128, 7, 7]        401,408         Conv2D-126       [[1, 512, 14, 14]]     [1, 128, 7, 7]        331,776    AdaptiveAvgPool2D-16   [[1, 128, 7, 7]]      [1, 128, 1, 1]           0            Conv2D-127        [[1, 128, 1, 1]]       [1, 8, 1, 1]          1,032           ReLU-30           [[1, 8, 1, 1]]        [1, 8, 1, 1]            0            Conv2D-128         [[1, 8, 1, 1]]       [1, 128, 1, 1]         1,152          Sigmoid-16        [[1, 128, 1, 1]]      [1, 128, 1, 1]           0        SEWeightModule-16     [[1, 128, 7, 7]]      [1, 128, 1, 1]           0            Softmax-16      [[1, 4, 128, 1, 1]]   [1, 4, 128, 1, 1]          0           PSAModule-16      [[1, 512, 14, 14]]     [1, 512, 7, 7]           0          BatchNorm2D-46      [[1, 512, 7, 7]]      [1, 512, 7, 7]         2,048          Conv2D-129        [[1, 512, 7, 7]]     [1, 2048, 7, 7]       1,048,576      BatchNorm2D-47     [[1, 2048, 7, 7]]     [1, 2048, 7, 7]         8,192          Conv2D-121      [[1, 1024, 14, 14]]    [1, 2048, 7, 7]       2,097,152      BatchNorm2D-44     [[1, 2048, 7, 7]]     [1, 2048, 7, 7]         8,192         EPSABlock-14     [[1, 1024, 14, 14]]    [1, 2048, 7, 7]           0            Conv2D-130       [[1, 2048, 7, 7]]      [1, 512, 7, 7]       1,048,576      BatchNorm2D-48      [[1, 512, 7, 7]]      [1, 512, 7, 7]         2,048           ReLU-33         [[1, 2048, 7, 7]]     [1, 2048, 7, 7]           0            Conv2D-131        [[1, 512, 7, 7]]      [1, 128, 7, 7]        589,824         Conv2D-132        [[1, 512, 7, 7]]      [1, 128, 7, 7]        409,600         Conv2D-133        [[1, 512, 7, 7]]      [1, 128, 7, 7]        401,408         Conv2D-134        [[1, 512, 7, 7]]      [1, 128, 7, 7]        331,776    AdaptiveAvgPool2D-17   [[1, 128, 7, 7]]      [1, 128, 1, 1]           0            Conv2D-135        [[1, 128, 1, 1]]       [1, 8, 1, 1]          1,032           ReLU-32           [[1, 8, 1, 1]]        [1, 8, 1, 1]            0            Conv2D-136         [[1, 8, 1, 1]]       [1, 128, 1, 1]         1,152          Sigmoid-17        [[1, 128, 1, 1]]      [1, 128, 1, 1]           0        SEWeightModule-17     [[1, 128, 7, 7]]      [1, 128, 1, 1]           0            Softmax-17      [[1, 4, 128, 1, 1]]   [1, 4, 128, 1, 1]          0           PSAModule-17       [[1, 512, 7, 7]]      [1, 512, 7, 7]           0          BatchNorm2D-49      [[1, 512, 7, 7]]      [1, 512, 7, 7]         2,048          Conv2D-137        [[1, 512, 7, 7]]     [1, 2048, 7, 7]       1,048,576      BatchNorm2D-50     [[1, 2048, 7, 7]]     [1, 2048, 7, 7]         8,192         EPSABlock-15      [[1, 2048, 7, 7]]     [1, 2048, 7, 7]           0            Conv2D-138       [[1, 2048, 7, 7]]      [1, 512, 7, 7]       1,048,576      BatchNorm2D-51      [[1, 512, 7, 7]]      [1, 512, 7, 7]         2,048           ReLU-35         [[1, 2048, 7, 7]]     [1, 2048, 7, 7]           0            Conv2D-139        [[1, 512, 7, 7]]      [1, 128, 7, 7]        589,824         Conv2D-140        [[1, 512, 7, 7]]      [1, 128, 7, 7]        409,600         Conv2D-141        [[1, 512, 7, 7]]      [1, 128, 7, 7]        401,408         Conv2D-142        [[1, 512, 7, 7]]      [1, 128, 7, 7]        331,776    AdaptiveAvgPool2D-18   [[1, 128, 7, 7]]      [1, 128, 1, 1]           0            Conv2D-143        [[1, 128, 1, 1]]       [1, 8, 1, 1]          1,032           ReLU-34           [[1, 8, 1, 1]]        [1, 8, 1, 1]            0            Conv2D-144         [[1, 8, 1, 1]]       [1, 128, 1, 1]         1,152          Sigmoid-18        [[1, 128, 1, 1]]      [1, 128, 1, 1]           0        SEWeightModule-18     [[1, 128, 7, 7]]      [1, 128, 1, 1]           0            Softmax-18      [[1, 4, 128, 1, 1]]   [1, 4, 128, 1, 1]          0           PSAModule-18       [[1, 512, 7, 7]]      [1, 512, 7, 7]           0          BatchNorm2D-52      [[1, 512, 7, 7]]      [1, 512, 7, 7]         2,048          Conv2D-145        [[1, 512, 7, 7]]     [1, 2048, 7, 7]       1,048,576      BatchNorm2D-53     [[1, 2048, 7, 7]]     [1, 2048, 7, 7]         8,192         EPSABlock-16      [[1, 2048, 7, 7]]     [1, 2048, 7, 7]           0       AdaptiveAvgPool2D-19  [[1, 2048, 7, 7]]     [1, 2048, 1, 1]           0             Linear-1           [[1, 2048]]           [1, 1000]          2,049,000   ================================================================================Total params: 22,614,835Trainable params: 22,508,595Non-trainable params: 106,240--------------------------------------------------------------------------------Input size (MB): 0.57Forward/backward pass size (MB): 272.07Params size (MB): 86.27Estimated Total Size (MB): 358.91--------------------------------------------------------------------------------

{'total_params': 22614835, 'trainable_params': 22508595}

在Cifar10数据集上进行对比

如下图所示，我们对比EPSANet-50和Paddle最新ResNet-50，看看他们谁的性能更好

数据准备

import paddle.vision.transforms as Tfrom paddle.vision.datasets import Cifar10paddle.set_device('gpu')#数据准备transform = T.Compose([    T.Resize(size=(224,224)),    T.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225],data_format='HWC'),    T.ToTensor()])train_dataset = Cifar10(mode='train', transform=transform)val_dataset = Cifar10(mode='test',  transform=transform)

Cache file /home/aistudio/.cache/paddle/dataset/cifar/cifar-10-python.tar.gz not found, downloading https://dataset.bj.bcebos.com/cifar/cifar-10-python.tar.gz Begin to downloadDownload finished

模型准备

# ResNet-50 vs EPSANet-50resnet50=paddle.Model(paddle.vision.models.resnet50(num_classes=10))epsanet50=paddle.Model(epsanet50(num_classes=10))

开始训练

# ResNet-50resnet50.prepare(optimizer=paddle.optimizer.Adam(learning_rate=0.001, parameters=resnet50.parameters()),              loss=paddle.nn.CrossEntropyLoss(),              metrics=paddle.metric.Accuracy())visualdl=paddle.callbacks.VisualDL(log_dir='resnet50_log') # 开启训练可视化resnet50.fit(    train_data=train_dataset,     eval_data=val_dataset,     batch_size=64,     epochs=10,     verbose=1,    callbacks=[visualdl] )

# EPSANet-50epsanet50.prepare(optimizer=paddle.optimizer.Adam(learning_rate=0.001, parameters=epsanet50.parameters()),              loss=paddle.nn.CrossEntropyLoss(),              metrics=paddle.metric.Accuracy())visualdl=paddle.callbacks.VisualDL(log_dir='epsanet50_log') # 开启训练可视化epsanet50.fit(    train_data=train_dataset,     eval_data=val_dataset,     batch_size=64,     epochs=10,     verbose=1,    callbacks=[visualdl] )

训练可视化

总结

免责声明

游乐网为非赢利性网站，所展示的游戏/软件/文章内容均来自于互联网或第三方用户上传分享，版权归原作者所有，本站不承担相应法律责任。如您发现有涉嫌抄袭侵权的内容，请联系youleyoucom@outlook.com。

同类文章