Pytorch代碼的Tensorflow實作：添加卷積層

我想在 Tensorflow 中實作這個 PyTorch 代碼，但我是新手，正在尋找一些幫助/資源。

Pytorch 中的代碼在前向傳播中結合了兩個卷積：

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))

我怎樣才能在張量流中做到這一點？

我知道我可以像這樣進行一維卷積：

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

我也明白我可以像這樣創建一個前饋網路：

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

但是，在 tensorflow 中，我如何從 Pytorch 代碼中實作這一行，以轉換卷積：

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

為業余問題道歉。我搜索了很長時間，但找不到與我類似的帖子。

uj5u.com熱心網友回復：

您可以找到 Keras 教程：

• 函式式 API
• 通過子類化創建新層和模型

為這項任務提供資訊。使用 Keras 功能模型 API，這可能類似于：

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
>>> __________________________________________________________________________________________________

標籤：Python 张量流 喀拉斯 火炬

上一篇：如何從Tensorflow中的字串張量中隨機洗掉空格

下一篇：直觀理解Adam優化器