Je souhaite utiliser la fonction d'activation Mish

Nouvelle fonction d'activation Mish

• Ci-dessous, GitHub où est écrite l'implémentation de l'auteur Mish

GitHub - digantamisra98/Mish: Mish: A Self Regularized Non-Monotonic Neural Activation Function

Cela semble être une implémentation de Tensorflow-Keras

Mish/mish.py at master · digantamisra98/Mish · GitHub

Je ne sais pas ce qui est difficile, mais j'ai essayé de le coller

• Exécutez avec google colaboratory
• keras/mnist_cnn.py at master · keras-team/keras · GitHub
• Exécutez avec le code CNN ci-dessus
• Remplacez ReLU par Mish
• Copiez et collez l'implémentation Tensorflow-Keras de la classe Mish

Une implémentation détaillée de pytorch et Keras a été écrite ici ...

• J'ai fait de mon mieux pour copier et coller, mais voir ci-dessous
• https://towardsdatascience.com/mish-8283934a72df

Le code que je copiais et collais pour la première fois est le suivant

• Cela fonctionnait ici aussi, alors peut-être que la copie est correcte?

python::1

from __future__ import print_function
from tensorflow.python import keras
from tensorflow.python.keras.datasets import mnist
from tensorflow.python.keras.models import Sequential
from tensorflow.python.keras.layers import Dense, Dropout, Flatten
from tensorflow.python.keras.layers import Conv2D, MaxPooling2D
from tensorflow.python.keras import backend as K
 

"""Tensorflow-Keras Implementation of Mish"""

## Import Necessary Modules
import tensorflow as tf
from tensorflow.keras.layers import Activation
from tensorflow.keras.utils import get_custom_objects

class Mish(Activation):
    '''
    Mish Activation Function.
    .. math::
        mish(x) = x * tanh(softplus(x)) = x * tanh(ln(1 + e^{x}))
    Shape:
        - Input: Arbitrary. Use the keyword argument `input_shape`
        (tuple of integers, does not include the samples axis)
        when using this layer as the first layer in a model.
        - Output: Same shape as the input.
    Examples:
        >>> X = Activation('Mish', name="conv1_act")(X_input)
    '''

    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)})



batch_size = 128
num_classes = 10
epochs = 12
 
# input image dimensions
img_rows, img_cols = 28, 28
 
# the data, split between train and test sets
(x_train, y_train), (x_test, y_test) = mnist.load_data()
 
if K.image_data_format() == 'channels_first':
    x_train = x_train.reshape(x_train.shape[0], 1, img_rows, img_cols)
    x_test = x_test.reshape(x_test.shape[0], 1, img_rows, img_cols)
    input_shape = (1, img_rows, img_cols)
else:
    x_train = x_train.reshape(x_train.shape[0], img_rows, img_cols, 1)
    x_test = x_test.reshape(x_test.shape[0], img_rows, img_cols, 1)
    input_shape = (img_rows, img_cols, 1)
 
x_train = x_train.astype('float32')
x_test = x_test.astype('float32')
x_train /= 255
x_test /= 255
print('x_train shape:', x_train.shape)
print(x_train.shape[0], 'train samples')
print(x_test.shape[0], 'test samples')
 
# convert class vectors to binary class matrices
y_train = keras.utils.to_categorical(y_train, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes)
 
model = Sequential()
model.add(Conv2D(32, kernel_size=(3, 3),
                 activation='Mish',
                 input_shape=input_shape))
model.add(Conv2D(64, (3, 3), activation='Mish'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(128, activation='Mish'))
model.add(Dropout(0.5))
model.add(Dense(num_classes, activation='softmax'))
 
model.compile(loss=keras.losses.categorical_crossentropy,
              optimizer=keras.optimizers.Adadelta(),
              metrics=['accuracy'])
 
model.fit(x_train, y_train,
          batch_size=batch_size,
          epochs=epochs,
          verbose=1,
          validation_data=(x_test, y_test))
score = model.evaluate(x_test, y_test, verbose=0)
print('Test loss:', score[0])
print('Test accuracy:', score[1])