Pytorch代码的Tensorflow实现：添加卷积层

Question

我想在 Tensorflow 中实现此 PyTorch 代码，但我是新手，正在寻找一些 assistance/resources。

Pytorch中的代码在前向传播中结合了两个卷积：

class PytorchLayer(nn.Module):
    def __init__(self, in_features, out_features):
        super(PytorchLayer, self).__init__()
        self.in_features = in_features
        self.out_features = out_features
        self.layer1 = nn.Conv1d(in_features, out_features, 1)
        self.layer2 = nn.Conv1d(in_features, out_features, 1, bias=False)

    def forward(self, x):
        return self.layer1(x) + self.layer2(x - x.mean(dim=2, keepdim=True))

我如何在 tensorflow 中执行此操作？

我知道我可以像这样做一维卷积：

tf.keras.layers.Conv1D(in_features, kernel_size = 1, strides=1)

我也明白我可以像这样创建一个前馈网络：

tf.keras.Sequential([tf.keras.layers.Conv1D(in_features, kernel_size = 1, strides=1)])

但是，在 tensorflow 中，我如何从 Pytorch 代码实现这一行，它转换了卷积：

self.layer1(x) + self.layer2(x - x.mean(dim=2, keepdim=True))

很抱歉这个业余问题。找了半天也没找到和我的相似的post

Answer 1

您可能会找到 Keras 教程：

此任务的信息。使用 Keras 功能模型 API，这可能类似于：

out_features = 5  # Arbitrary for the example

layer1 = tf.keras.layers.Conv1D(
      out_features, kernel_size=1, strides=1, name='Conv1')
layer2 = tf.keras.layers.Conv1D(
      out_features, kernel_size=1, strides=1, use_bias=False, name='Conv2')
subtract = tf.keras.layers.Subtract(name='SubtractMean')
mean = tf.keras.layers.Lambda(
      lambda t: tf.reduce_mean(t, axis=2, keepdims=True), name='Mean')

# Connect the layers in a model.
x = tf.keras.Input(shape=(5,5))
average_x = mean(x)
normalized_x = subtract([x, average_x])
y = tf.keras.layers.Add(name='AddConvolutions')([layer1(x), layer2(normalized_x)])

m = tf.keras.Model(inputs=x, outputs=y)
m.summary()

>>> Model: "model"
>>> __________________________________________________________________________________________________
>>>  Layer (type)                   Output Shape         Param #     Connected to                     
>>> ==================================================================================================
>>>  input_1 (InputLayer)           [(None, 5, 5)]       0           []                               
>>>                                                                                                   
>>>  Mean (Lambda)                  (None, 5, 1)         0           ['input_1[0][0]']                
>>>                                                                                                   
>>>  SubtractMean (Subtract)        (None, 5, 5)         0           ['input_1[0][0]',                
>>>                                                                   'Mean[0][0]']                   
>>>                                                                                                   
>>>  Conv1 (Conv1D)                 (None, 5, 5)         30          ['input_1[0][0]']                
>>>                                                                                                   
>>>  Conv2 (Conv1D)                 (None, 5, 5)         25          ['SubtractMean[0][0]']           
>>>                                                                                                   
>>>  AddConvolutions (Add)          (None, 5, 5)         0           ['Conv1[0][0]',                  
>>>                                                                   'Conv2[0][0]']                  
>>>                                                                                                   
>>> ==================================================================================================
>>> Total params: 55
>>> Trainable params: 55
>>> Non-trainable params: 0
>>> __________________________________________________________________________________________________

Pytorch代码的Tensorflow实现：添加卷积层

Tensorflow implementation of Pytorch code: adding convolutional layers

python

keras

tensorflow

pytorch