Tensorflow - 深度到空間后與 conv2d 不兼容的形狀

Question

我在實現超分辨率模型時遇到了問題

class SRNet(Model):
    def __init__(self, scale=4):
        super(SRNet, self).__init__()
        self.scale = scale

        self.conv1 = Sequential([
            layers.Conv2D(filters=64, kernel_size=3,
                          strides=(1, 1), padding="same", data_format="channels_first"),
            layers.ReLU(),
        ])

        self.residualBlocks = Sequential(
            [ResidualBlock() for _ in range(16)])

        self.convUp = Sequential([
            layers.Conv2DTranspose(filters=64, kernel_size=3, strides=(
                2, 2), padding="same", data_format="channels_first"),
            layers.ReLU(),
            layers.Conv2DTranspose(filters=64, kernel_size=3, strides=(
                2, 2), padding="same", data_format="channels_first"),
            layers.ReLU(),
        ])

        self.reluAfterPixleShuffle = layers.ReLU()

        self.convOut = layers.Conv2D(
            filters=3, kernel_size=3, strides=(1, 1), padding="same", data_format="channels_first", input_shape=(4, 1440, 2560))  # (kernel, kernel, channel, output)

    def call(self, lrCur_hrPrevTran):
        lrCur, hrPrevTran = lrCur_hrPrevTran
        x = tf.concat([lrCur, hrPrevTran], axis=1)
        x = self.conv1(x)
        x = self.residualBlocks(x)
        x = self.convUp(x)

        # pixel shuffle
        Subpixel_layer = Lambda(lambda x: tf.nn.depth_to_space(
            x, self.scale, data_format="NCHW"))
        x = Subpixel_layer(inputs=x)
        x = self.reluAfterPixleShuffle(x)
        
        x = self.convOut(x)
        return x

錯誤

/usr/src/app/generator.py:164 call  *
        x = self.convOut(x)
ValueError: Tensor's shape (3, 3, 64, 3) is not compatible with supplied shape (3, 3, 4, 3)

閱讀錯誤后我知道 (3, 3, 4, 3) is (kernel size, kernel size, channel, output) 意味着只有輸入通道不正確

所以我打印出輸入的形狀

# after pixel shuffle before convOut
print(x.shape)
>>> (1, 4, 1440, 2560) (batch size, channel, height, width)

但是pixel shuffle (depth_to_space)后x的形狀pixel shuffle (depth_to_space)是（1, 4, 1440, 2560）通道值是4，這和convOut需要的一樣

問題是為什么輸入的通道會從 4 變為 64 作為錯誤？

Answer 1

我找到了解決辦法

首先，我在訓練時使用檢查點來保存模型權重
在模型的實現和測試過程中，我改變了一些層，所以輸入大小也改變了，但我的體重仍然記得上一個檢查點的輸入大小

所以我刪除了檢查點文件夾，然后一切又恢復了