gy15635282365
/
tensorlayer3
Not watched
1
0
Fork 0
Code
Releases 0 Wiki evaluate Activity
Issues 0 Pull Requests 0 Datasets Model Cloudbrain HPC
You can not select more than 25 topics Topics must start with a chinese character,a letter or number, can include dashes ('-') and can be up to 35 characters long.
Tree: cd40a1b505
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from 'cd40a1b505'
${ noResults }
tensorlayer3/docs/modules/activation.rst

84 lines
1.5 kB
Raw Blame History 

  1. API - Activations

  2. =========================

  3. 

  4. To make TensorLayer simple, we minimize the number of activation functions as much as

  5. we can. So we encourage you to use Customizes activation function.

  6. For parametric activation, please read the layer APIs.

  7. 

  8. The shortcut of ``tensorlayer.activation`` is ``tensorlayer.act``.

  9. 

  10. Your activation

  11. -------------------

  12. 

  13. Customizes activation function in TensorLayer is very easy.

  14. The following example implements an activation that multiplies its input by 2.

  15. For more complex activation, TensorFlow(MindSpore/PaddlePaddle) API will be required.

  16. 

  17. .. code-block:: python

  18. 

  19.   class DoubleActivation(object):

  20.     def __init__(self):

  21.         pass

  22.     def __call__(self, x):

  23.         return x * 2

  24.   double_activation = DoubleActivation()

  25. 

  26. .. automodule:: tensorlayer.layers.activation

  27. 

  28. .. autosummary::

  29. 

  30.    PRelu

  31.    PRelu6

  32.    PTRelu6

  33.    LeakyReLU

  34.    LeakyReLU6

  35.    LeakyTwiceRelu6

  36.    Ramp

  37.    Swish

  38.    HardTanh

  39.    Mish

  40. 

  41. PRelu

  42. ------

  43. .. autofunction:: PRelu

  44. 

  45. PRelu6

  46. ------------

  47. .. autofunction:: PRelu6

  48. 

  49. PTRelu6

  50. ------------

  51. .. autofunction:: PTRelu6

  52. 

  53. LeakyReLU

  54. -----------------

  55. .. autofunction:: LeakyReLU

  56. 

  57. LeakyReLU6

  58. ------------

  59. .. autofunction:: LeakyReLU6

  60. 

  61. LeakyTwiceRelu6

  62. ---------------------

  63. .. autofunction:: LeakyTwiceRelu6

  64. 

  65. Ramp

  66. ---------------------

  67. .. autofunction:: Ramp

  68. 

  69. Swish

  70. --------------------

  71. .. autofunction:: Swish

  72. 

  73. HardTanh

  74. ----------------

  75. .. autofunction:: HardTanh

  76. 

  77. Mish

  78. ---------

  79. .. autofunction:: Mish

  80. 

  81. Parametric activation

  82. ------------------------------

  83. See ``tensorlayer.layers``.