目录

摘要

如何在Pytorch使用Mish函数

如何在Keras中使用Mish激活函数。

摘要

Diganta Misra的一篇题为“Mish: A Self Regularized Non-Monotonic Neural Activation Function”的新论文介绍了一个新的深度学习激活函数，该函数在最终准确度上比Swish(+.494%)和ReLU(+ 1.671%)都有提高

公式如下：

• 如何在Pytorch使用Mish函数

定义Mish函数。

      class Mish(torch.nn.Module):
          def __init__(self):
              super().__init__()
          def forward(self, x):
              x = x * (torch.tanh(torch.nn.functional.softplus(x)))
              return x
  
 

调用函数：

      class Path1_64(nn.Module):
          def __init__(self):
              super().__init__()
              self.conv1 = ConvBN(32, 64, 3)
              self.conv2 = ConvBN(64, 64, [1, 9])
              self.conv3 = ConvBN(64, 64, [9, 1])
              self.conv4 = ConvBN(64, 64, 1)
              self.resBlock = ResBlock(ch=64, nblocks=2)
              self.conv5 = ConvBN(64, 64, [1, 7])
              self.conv6 = ConvBN(64, 64, [7, 1])
              self.conv7 = ConvBN(64, 64, 1)
              self.relu = Mish()
          def forward(self, input):
              x1 = self.conv1(input)
              x2 = self.conv2(x1)
              x3 = self.conv3(x2)
              x4 = self.conv4(x3)
              r1 = self.resBlock(x4)
              x5 = self.conv5(r1)
              x6 = self.conv6(x5)
              x7 = self.conv7(x6)
              x7 = self.relu(x7 + x4)
              return x7
  
 

调用Mish激活函数和调用其他的激活函数一样，直接调用即可。

• 如何在Keras中使用Mish激活函数。

定义Mish激活函数

      import tensorflow as tf
      from tensorflow.python.keras.layers import *
      from tensorflow.keras.layers import Activation
      from tensorflow.keras.utils import get_custom_objects
      class Mish(Activation):
          def __init__(self, activation, **kwargs):
              super(Mish, self).__init__(activation, **kwargs)
              self.__name__ = 'Mish'
      def mish(inputs):
          return inputs * tf.math.tanh(tf.math.softplus(inputs))
      get_custom_objects().update({'Mish': Mish(mish)})
  
 

调用激活函数：

      def bn_prelu(x):
          x = BatchNormalization(epsilon=1e-5)(x)
          x = Activation('Mish')(x)
          return x
      def build_model(out_dims, input_shape=(100, 100, 3)):
          inputs_dim = Input(input_shape)
          x = Conv2D(32, (3, 3), strides=(2, 2), padding='same')(inputs_dim)
          x = bn_prelu(x)
          x = Conv2D(32, (3, 3), strides=(1, 1), padding='same')(x)
          x = bn_prelu(x)
          x = MaxPooling2D(pool_size=(2, 2))(x)
          x = Conv2D(64, (3, 3), strides=(1, 1), padding='same')(x)
          x = bn_prelu(x)
          x = Conv2D(64, (3, 3), strides=(1, 1), padding='same')(x)
          x = bn_prelu(x)
          x = MaxPooling2D(pool_size=(2, 2))(x)
          x = Conv2D(128, (3, 3), strides=(1, 1), padding='same')(x)
          x = bn_prelu(x)
          x = Conv2D(128, (3, 3), strides=(1, 1), padding='same')(x)
          x = bn_prelu(x)
          x = MaxPooling2D(pool_size=(2, 2))(x)
          x = Conv2D(256, (3, 3), strides=(1, 1), padding='same')(x)
          x = bn_prelu(x)
          x = Conv2D(256, (3, 3), strides=(1, 1), padding='same')(x)
          x = bn_prelu(x)
          x = GlobalAveragePooling2D()(x)
          dp_1 = Dropout(0.5)(x)
          fc2 = Dense(out_dims)(dp_1)
          fc2 = Activation('softmax')(fc2)  # 此处注意，为sigmoid函数
          model = Model(inputs=inputs_dim, outputs=fc2)
          return model
      model = build_model(2)  # 生成模型
      optimizer = Adam(lr=1e-3)  # 加入优化器，设置优化器的学习率。
      model.compile(optimizer=optimizer, loss='sparse_categorical_crossentropy', metrics=['accuracy'])
  
 

文章来源: wanghao.blog.csdn.net，作者：AI浩，版权归原作者所有，如需转载，请联系作者。

原文链接：wanghao.blog.csdn.net/article/details/110123219