将CNN从Keras转换为Pytorch

Question

我需要一些帮助。我正在尝试将CNN从Keras转换为Pytorch。我正在重建MR图像。输入是来自傅立叶域中扫描仪的图像，输出是重建的图像。输入图像有两个通道（第一个通道：实际部分，第二通道：假想部分）。不幸的是，结果完全不同，所以我相信我做错了什么。我只是找不到自己是什么。这是KERAS代码：

def AUTOMAP_Basic_Model(param):
    fc_1 = keras.Input(shape=(64,64,2), name='input')
    fc_2 = layers.Conv2D(64,(64,1),strides=1,padding='same',activation='relu')(fc_1)
    fc_4 = layers.Conv2D(64,(1,64),strides=1,padding='same',activation='relu')(fc_2)
    fc_4 = layers.Conv2D(64,(64,1),strides=1,padding='same',activation='relu')(fc_4)
    fc_5 = layers.Conv2D(64,(1,64),strides=1,padding='same',activation='relu')(fc_4)
    c_1 = layers.Conv2D(64,5,strides=1,padding='same',activation='relu')(fc_5)
    c_2 = layers.Conv2D(64,5,strides=1,padding='same',activation='relu')(c_1)
    c_3 = layers.Conv2DTranspose(1,7,strides=1,activation='sigmoid',padding='same')(c_2)
    model = keras.Model(inputs = fc_1,outputs = c_3)
    return model

这是我对Pytorch的翻译：

class AUTOMAP_Basic_Model(nn.Module):
    def __init__(self, inputShape, nrFilters):
        super(AUTOMAP_Basic_Model, self).__init__()

        self.conv1 = nn.Conv2d(2, 64, (64,1), padding='same')
        self.relu = nn.ReLU()
        self.conv2 = nn.Conv2d(64, 64, (1,64), padding ='same')
        self.conv3 = nn.Conv2d(64, 64, (64,1), padding='same')
        self.conv4 = nn.Conv2d(64,64,5,padding='same')
        self.conv5 = nn.Conv2d(64,64,5,padding='same')
        self.convTranspose = nn.ConvTranspose2d(64,1,7,padding=3,output_padding=0)
        self.sigmoid = nn.Sigmoid()
        self.tan = nn.Tanh()
    def forward(self, x):
        batch_size = len(x)
        
        out = self.conv1(x)
        out = self.relu(out)
        out = self.conv2(out)
        out = self.relu(out)
        out = self.conv3(out)
        out = self.relu(out)
        out = self.conv2(out)
        out = self.relu(out)
        out = self.conv4(out)
        out = self.relu(out)
        out = self.conv5(out)
        out = self.relu(out)
        out = self.convTranspose(out)
        out=self.sigmoid(out)
        return out

我是Pytorch的新手，这就是为什么我不知道可能是什么问题的原因。当Keras模型收敛到正确的图像时，Pytorch模型的恒定值为图像中的每个像素的恒定值为0.45。

Answer 1

似乎您在Keras和Pytorch中都有一些奇怪的顺序和命名。在第一个FC_3中，丢失了，这可能仍然可行，但我不明白为什么。

在Pytorch实现中，您需要具有4个Conv层（FC_2，FC_3，FC_4，FC_5），但仅实现3（Conv1，Conv2，Conv3）。

类似的内容重写该模型

class AUTOMAP_Basic_Model(nn.Module):
    def __init__(self, inputShape, nrFilters):
        super(AUTOMAP_Basic_Model, self).__init__()

        self.conv1 = nn.Conv2d(2, 64, (64, 1), padding='same')
        self.conv2 = nn.Conv2d(64, 64, (1, 64), padding='same')
        self.conv3 = nn.Conv2d(64, 64, (64, 1), padding='same')
        self.conv4 = nn.Conv2d(64, 64, (1, 64), padding='same')
        self.conv5 = nn.Conv2d(64, 64, 5, padding='same')
        self.conv6 = nn.Conv2d(64, 64, 5, padding='same')
        self.relu = nn.ReLU(inplace=True)
        self.convTranspose = nn.ConvTranspose2d(64, 1, 7, padding=3, output_padding=0)
        self.sigmoid = nn.Sigmoid()
        self.tan = nn.Tanh()

    def forward(self, x):
        batch_size = len(x)

        out = self.relu(self.conv1(x))
        out = self.relu(self.conv2(out))
        out = self.relu(self.conv3(out))
        out = self.relu(self.conv4(out))
        out = self.relu(self.conv5(out))
        out = self.relu(self.conv6(out))
        out = self.convTranspose(out)
        out = self.sigmoid(out)
        return out

我会用 “> conv+bn+relu