擅长:python、mysql、java
<p>只是为了确保您的输入形状应该是4D。正如<code>SeparableConv2D</code>期望输入形状为4D的张量:<code>(batch_size, channels, rows, cols)</code>如果数据格式为“首先通道”或形状为4D的张量:<code>(batch_size, rows, cols, channels)</code>如果数据格式为“最后通道”</p>
<p><strong>工作示例</strong></p>
<pre><code>import tensorflow as tf
input_shape = (16, 128, 128, 1)
x = tf.random.normal(input_shape)
y = tf.keras.layers.SeparableConv2D( 2, 3, activation='relu', input_shape=input_shape[1:])(x)
print(y.shape)
</code></pre>
<p><strong>输出</strong></p>
<pre><code>(16, 126, 126, 2)
</code></pre>