【动手学Paddle2.0系列】CoordConv实战

CoordConv实战

理论介绍

• CoordConv

  即它无法将空间表示转换成笛卡尔空间中的坐标和one-hot像素空间中的坐标。
卷积是等变的，也就是说当每个过滤器应用到输入上时，它不知道每个过滤器在哪。我们可以帮助卷积，让它知道过滤器的位置。这一过程需要在输入上添加两个通道实现，一个在i坐标，另一个在j坐标。我们将这个图层成为CoordConv，如下图所示：

  深度学习里的卷积运算是具有平移等变性的,这样可以在图像的不同位置共享统一的卷积核参数,但是这样卷积学习过程中是不能感知当前特征在图像中的坐标的。CoordConv就是通过在卷积的输入特征图中新增对应的通道来表征特征图像素点的坐标,让卷积学习过程中能够一定程度感知坐标来提升检测精度。

代码实战

  本部分根据CoordConv论文并参考飞桨的官方实现完成CoordConv的复现。

import paddle
import paddle.nn as nn
import paddle.nn.functional as F
from paddle import ParamAttr
from paddle.regularizer import L2Decay
from paddle.nn import AvgPool2D, Conv2D

class CoordConv(nn.Layer):
    def __init__(self, in_channels, out_channels, kernel_size, stride, padding):
        super(CoordConv, self).__init__()
        self.conv = Conv2D(
            in_channels + 2, out_channels , kernel_size , stride , padding)

    def forward(self, x):
        b = x.shape[0]
        h = x.shape[2]
        w = x.shape[3]

        gx = paddle.arange(w, dtype='float32') / (w - 1.) * 2.0 - 1.
        gx = gx.reshape([1, 1, 1, w]).expand([b, 1, h, w])
        gx.stop_gradient = True

        gy = paddle.arange(h, dtype='float32') / (h - 1.) * 2.0 - 1.
        gy = gy.reshape([1, 1, h, 1]).expand([b, 1, h, w])
        gy.stop_gradient = True

        y = paddle.concat([x, gx, gy], axis=1)
        y = self.conv(y)
        return y

class dcn2(paddle.nn.Layer):
    def __init__(self, num_classes=1):
        super(dcn2, self).__init__()

        self.conv1 = paddle.nn.Conv2D(in_channels=3, out_channels=32, kernel_size=(3, 3), stride=1, padding = 1)
        # self.pool1 = paddle.nn.MaxPool2D(kernel_size=2, stride=2)

        self.conv2 = paddle.nn.Conv2D(in_channels=32, out_channels=64, kernel_size=(3,3),  stride=2, padding = 0)
        # self.pool2 = paddle.nn.MaxPool2D(kernel_size=2, stride=2)

        self.conv3 = paddle.nn.Conv2D(in_channels=64, out_channels=64, kernel_size=(3,3), stride=2, padding = 0)

        self.offsets = paddle.nn.Conv2D(64, 18, kernel_size=3, stride=2, padding=1)
        self.mask = paddle.nn.Conv2D(64, 9, kernel_size=3, stride=2, padding=1)
        self.conv4 = CoordConv(64, 64, (3,3), 2, 1)

        # self.conv4 = paddle.nn.Conv2D(in_channels=64, out_channels=64, kernel_size=(3,3), stride=2, padding = 1)

        self.flatten = paddle.nn.Flatten()

        self.linear1 = paddle.nn.Linear(in_features=1024, out_features=64)
        self.linear2 = paddle.nn.Linear(in_features=64, out_features=num_classes)

    def forward(self, x):
        x = self.conv1(x)
        x = F.relu(x)
        # x = self.pool1(x)
        # print(x.shape)
        x = self.conv2(x)
        x = F.relu(x)
        # x = self.pool2(x)
        # print(x.shape)

        x = self.conv3(x)
        x = F.relu(x)
        # print(x.shape)
        
        # offsets = self.offsets(x)
        # masks = self.mask(x)
        # print(offsets.shape)
        # print(masks.shape)
        x = self.conv4(x)
        x = F.relu(x)
        # print(x.shape)

        x = self.flatten(x)
        x = self.linear1(x)
        x = F.relu(x)
        x = self.linear2(x)
        return x

cnn3 = dcn2()

model3 = paddle.Model(cnn3)

model3.summary((64, 3, 32, 32))

---------------------------------------------------------------------------
 Layer (type)       Input Shape          Output Shape         Param #    
===========================================================================
   Conv2D-26     [[64, 3, 32, 32]]     [64, 32, 32, 32]         896      
   Conv2D-27     [[64, 32, 32, 32]]    [64, 64, 15, 15]       18,496     
   Conv2D-28     [[64, 64, 15, 15]]     [64, 64, 7, 7]        36,928     
   Conv2D-31      [[64, 66, 7, 7]]      [64, 64, 4, 4]        38,080     
  CoordConv-4     [[64, 64, 7, 7]]      [64, 64, 4, 4]           0       
   Flatten-1      [[64, 64, 4, 4]]        [64, 1024]             0       
   Linear-1         [[64, 1024]]           [64, 64]           65,600     
   Linear-2          [[64, 64]]            [64, 1]              65       
===========================================================================
Total params: 160,065
Trainable params: 160,065
Non-trainable params: 0
---------------------------------------------------------------------------
Input size (MB): 0.75
Forward/backward pass size (MB): 26.09
Params size (MB): 0.61
Estimated Total Size (MB): 27.45
---------------------------------------------------------------------------






{'total_params': 160065, 'trainable_params': 160065}

class MyNet(paddle.nn.Layer):
    def __init__(self, num_classes=1):
        super(MyNet, self).__init__()

        self.conv1 = paddle.nn.Conv2D(in_channels=3, out_channels=32, kernel_size=(3, 3), stride=1, padding = 1)
        # self.pool1 = paddle.nn.MaxPool2D(kernel_size=2, stride=2)

        self.conv2 = paddle.nn.Conv2D(in_channels=32, out_channels=64, kernel_size=(3,3),  stride=2, padding = 0)
        # self.pool2 = paddle.nn.MaxPool2D(kernel_size=2, stride=2)

        self.conv3 = paddle.nn.Conv2D(in_channels=64, out_channels=64, kernel_size=(3,3), stride=2, padding = 0)

        self.conv4 = paddle.nn.Conv2D(in_channels=64, out_channels=64, kernel_size=(3,3), stride=2, padding = 1)

        self.flatten = paddle.nn.Flatten()

        self.linear1 = paddle.nn.Linear(in_features=1024, out_features=64)
        self.linear2 = paddle.nn.Linear(in_features=64, out_features=num_classes)

    def forward(self, x):
        x = self.conv1(x)
        x = F.relu(x)
        # x = self.pool1(x)
        # print(x.shape)
        x = self.conv2(x)
        x = F.relu(x)
        # x = self.pool2(x)
        # print(x.shape)

        x = self.conv3(x)
        x = F.relu(x)
        # print(x.shape)
        
        
        x = self.conv4(x)
        x = F.relu(x)
        # print(x.shape)

        x = self.flatten(x)
        x = self.linear1(x)
        x = F.relu(x)
        x = self.linear2(x)
        return x

# 可视化模型

cnn1 = MyNet()

model1 = paddle.Model(cnn1)

model1.summary((64, 3, 32, 32))

---------------------------------------------------------------------------
 Layer (type)       Input Shape          Output Shape         Param #    
===========================================================================
   Conv2D-1      [[64, 3, 32, 32]]     [64, 32, 32, 32]         896      
   Conv2D-2      [[64, 32, 32, 32]]    [64, 64, 15, 15]       18,496     
   Conv2D-3      [[64, 64, 15, 15]]     [64, 64, 7, 7]        36,928     
   Conv2D-4       [[64, 64, 7, 7]]      [64, 64, 4, 4]        36,928     
   Flatten-1      [[64, 64, 4, 4]]        [64, 1024]             0       
   Linear-1         [[64, 1024]]           [64, 64]           65,600     
   Linear-2          [[64, 64]]            [64, 1]              65       
===========================================================================
Total params: 158,913
Trainable params: 158,913
Non-trainable params: 0
---------------------------------------------------------------------------
Input size (MB): 0.75
Forward/backward pass size (MB): 25.59
Params size (MB): 0.61
Estimated Total Size (MB): 26.95
---------------------------------------------------------------------------






{'total_params': 158913, 'trainable_params': 158913}

总结

  相信通过之前的教程，相信大家已经能够熟练掌握了迅速开启训练的方法。所以，之后的教程我都会关注于具体的代码实现以及相关的理论介绍。如无必要，不再进行对比实验。本次教程主要对CoordConv的理论进行了介绍，对其进行了复现，并展示了其在网络结构中的用法。大家可以根据的实际需要，将其移植到自己的网络中。