tensorflow 使用卷积替换全连接层实现方法

• 来源 https://github.com/google-research/morph-net/issues/26

---

As a workaround (besides just using GammaFlopsRegularizer) and for future reference, most modern convolutional networks forgo the flatten/fully_connected pattern, and instead use 1x1conv/reduce_mean.

• 原模型

  def base_model(x_ph, is_training_ph, scope, channels=[32, 64, 64], reuse=False):
        norm_params = {'is_training': False, 'scale': True, 'center': False}
        # Network Definition
        with tf.variable_scope(scope, reuse=reuse):
            with slim.arg_scope([slim.conv2d, slim.fully_connected],
                          normalizer_fn=slim.batch_norm,
                          normalizer_params=norm_params,
                          weights_initializer=tf.truncated_normal_initializer(0.0, 0.01),
                          weights_regularizer=slim.l2_regularizer(0.0005)):
                conv1 = slim.conv2d(x_ph, num_outputs=channels[0], kernel_size=3, scope='conv1')
                pool1 = slim.max_pool2d(conv1, kernel_size=2, scope='pool1')
                conv2 = slim.conv2d(pool1, num_outputs=channels[1], kernel_size=3, scope='conv2')
                pool2 = slim.max_pool2d(conv2, kernel_size=2, scope='pool2')
                conv3 = slim.conv2d(pool2, num_outputs=channels[2], kernel_size=3, scope='conv3')
                conv3_flat = slim.flatten(conv3)
                out = slim.fully_connected(conv3_flat, num_outputs=10, normalizer_fn=None, normalizer_params=None,
                    activation_fn=None, scope='output')
        pred = tf.argmax(out, axis=1)
        return out, pred
  

• 替换全连接

  def base_model(x_ph, is_training_ph, scope, channels=[32, 64, 64], reuse=False):
      norm_params = {'is_training': False, 'scale': True, 'center': False}
      # Network Definition
      with tf.variable_scope(scope, reuse=reuse):
        with slim.arg_scope([slim.conv2d, slim.fully_connected],
                            normalizer_fn=slim.batch_norm,
                            normalizer_params=norm_params,
                            weights_initializer=tf.truncated_normal_initializer(0.0, 0.01),
                            weights_regularizer=slim.l2_regularizer(0.0005)):
          conv1 = slim.conv2d(x_ph, num_outputs=channels[0], kernel_size=3, scope='conv1')
          pool1 = slim.max_pool2d(conv1, kernel_size=2, scope='pool1')
          conv2 = slim.conv2d(pool1, num_outputs=channels[1], kernel_size=3, scope='conv2')
          pool2 = slim.max_pool2d(conv2, kernel_size=2, scope='pool2')
          conv3 = slim.conv2d(pool2, num_outputs=channels[2], kernel_size=3, scope='conv3')
          out = slim.conv2d(
                  conv3, 10, [1, 1], activation_fn=None, normalizer_fn=None, scope='output_conv')
          out = tf.reduce_mean(out, [1, 2], name='output', keepdims=False)
          pred = tf.argmax(out, axis=1)
          return out, pred