填充=“相同”转换为PyTorch padding=#

Question

我正在尝试将下面的Keras模型代码转换为py手电筒，但在处理padding=“am”时遇到了问题。

    model = Sequential()
    model.add(Conv2D(64, (3, 3), input_shape=img_size))
    model.add(BatchNormalization(axis=1))
    model.add(Activation('relu'))
    model.add(Dropout(0.3))
    model.add(Conv2D(64, (3, 3), padding='same'))
    model.add(BatchNormalization(axis=1))
    model.add(Activation('relu'))
    model.add(MaxPooling2D(pool_size=(2,2), strides=(2,2), padding='same'))

它产生了以下摘要：

Layer (type)                 Output Shape              Param #   
=================================================================
conv2d_1 (Conv2D)            (None, 30, 30, 64)        1792      
_________________________________________________________________
batch_normalization_1 (Batch (None, 30, 30, 64)        120       
_________________________________________________________________
activation_1 (Activation)    (None, 30, 30, 64)        0         
_________________________________________________________________
dropout_1 (Dropout)          (None, 30, 30, 64)        0         
_________________________________________________________________
conv2d_2 (Conv2D)            (None, 30, 30, 64)        36928     
_________________________________________________________________
batch_normalization_2 (Batch (None, 30, 30, 64)        120       
_________________________________________________________________
activation_2 (Activation)    (None, 30, 30, 64)        0         
_________________________________________________________________
max_pooling2d_1 (MaxPooling2 (None, 15, 15, 64)        0         
=================================================================
Total params: 38,960
Trainable params: 38,840
Non-trainable params: 120

现在，我会写：

self.features = nn.Sequential(
            nn.Conv2d(3, 64, kernel_size=3,
                      bias=False),
            nn.BatchNorm2d(64),
            nn.ReLU(inplace=True),
            nn.Dropout(0.3),
            nn.Conv2d(64, 64, kernel_size=3, padding = ?
                      bias=False),
            nn.BatchNorm2d(64),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=3, stride=2, padding = ?),
        )

填充物应该有数值。我想知道是否有更简单的方法来计算这一点，因为我们使用的是填充=“相同”。

另外，Keras模型的下一行如下所示：

model.add(Conv2D(128, (3, 3), padding='same'))

因此，我真的需要仔细研究如何计算填充，特别是在跨步之后。从粗糙的眼睛，是填充2?

Answer 1

W:输入体积大小

F:内核大小

S:stride

P:填充物量

输出体积尺寸=(W+2P)/S+1

例如：

输入:7x7，内核:3x3，行程:1，pad:0

输出大小= (7-3+2*0)/1+1 =5 =>5x5

Answer 2

self.features = nn.Sequential(
            nn.Conv2d(3, 64, kernel_size=3,
                      bias=False),
            nn.BatchNorm2d(64),
            nn.ReLU(inplace=True),
            nn.Dropout(0.3),
            nn.Conv2d(64, 64, kernel_size=3, padding = 1
                      bias=False),
            nn.BatchNorm2d(64),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=3, stride=2, padding = 32),
        )

​

​

Answer 3

公式为:K=(n-1)/ 2，其中n是核大小。下面是一个可视化的例子：

​

​