常用的正则化方法总结

常用的正则化方法：

运行代码：

import tensorflow as tf
print(help(tf.contrib.layers))

得到：

import tensorflow as tf
print(help(tf.contrib.layers))/usr/local/Cellar/python/3.7.0/Frameworks/Python.framework/Versions/3.7/lib/python3.7/importlib/_bootstrap.py:219: RuntimeWarning: compiletime version 3.6 of module 'tensorflow.python.framework.fast_tensor_util' does not match runtime version 3.7return f(*args, **kwds)
Help on package tensorflow.contrib.layers in tensorflow.contrib:NAMEtensorflow.contrib.layers - Ops for building neural network layers, regularizers, summaries, etc.DESCRIPTIONSee the @{$python/contrib.layers} guide.@@avg_pool2d@@avg_pool3d@@batch_norm@@convolution2d@@convolution3d@@conv2d_in_plane@@convolution2d_in_plane@@conv2d_transpose@@convolution2d_transpose@@conv3d_transpose@@convolution3d_transpose@@dense_to_sparse@@dropout@@elu@@embedding_lookup_unique@@flatten@@fully_connected@@GDN@@gdn@@layer_norm@@linear@@max_pool2d@@max_pool3d@@one_hot_encoding@@relu@@relu6@@repeat@@recompute_grad@@RevBlock@@rev_block@@safe_embedding_lookup_sparse@@scale_gradient@@separable_conv2d@@separable_convolution2d@@softmax@@spatial_softmax@@stack@@unit_norm@@bow_encoder@@embed_sequence@@maxout@@apply_regularization@@l1_l2_regularizer@@l1_regularizer@@l2_regularizer@@sum_regularizer@@xavier_initializer@@xavier_initializer_conv2d@@variance_scaling_initializer@@optimize_loss@@summarize_activation@@summarize_tensor@@summarize_tensors@@summarize_collection@@summarize_activations@@bucketized_column@@check_feature_columns@@create_feature_spec_for_parsing@@crossed_column@@embedding_column@@scattered_embedding_column@@input_from_feature_columns@@transform_features@@joint_weighted_sum_from_feature_columns@@make_place_holder_tensors_for_base_features@@multi_class_target@@one_hot_column@@parse_feature_columns_from_examples@@parse_feature_columns_from_sequence_examples@@real_valued_column@@shared_embedding_columns@@sparse_column_with_hash_bucket@@sparse_column_with_integerized_feature@@sparse_column_with_keys@@sparse_column_with_vocabulary_file@@weighted_sparse_column@@weighted_sum_from_feature_columns@@infer_real_valued_columns@@sequence_input_from_feature_columns@@instance_normPACKAGE CONTENTSops (package)python (package)SUBMODULESfeature_columnsummariesDATAOPTIMIZER_CLS_NAMES = {'Adagrad': <class 'tensorflow.python.training.a...OPTIMIZER_SUMMARIES = ['learning_rate', 'loss', 'gradients', 'gradient...SPARSE_FEATURE_CROSS_DEFAULT_HASH_KEY = 956888297470elu = functools.partial(<function add_arg_scope.<local...58>, activati...legacy_linear = functools.partial(<function legacy_fully_connected at ...legacy_relu = functools.partial(<function legacy_fully_connect...0>, a...linear = functools.partial(<function add_arg_scope.<local...nc_with_ar...relu = functools.partial(<function add_arg_scope.<local...8>, activati...relu6 = functools.partial(<function add_arg_scope.<local...>, activati...scale_gradient = <tensorflow.python.framework.function._OverloadedFunc...FILE/usr/local/lib/python3.7/site-packages/tensorflow/contrib/layers/__init__.pyNone
[Finished in 5.2s]

最常用的是

@@l1_regularizer
@@l2_regularizer

来看看l2正则化是什么意思：

import tensorflow as tf
print(help(tf.contrib.layers.l2_regularizer))/usr/local/Cellar/python/3.7.0/Frameworks/Python.framework/Versions/3.7/lib/python3.7/importlib/_bootstrap.py:219: RuntimeWarning: compiletime version 3.6 of module 'tensorflow.python.framework.fast_tensor_util' does not match runtime version 3.7return f(*args, **kwds)
Help on function l2_regularizer in module tensorflow.contrib.layers.python.layers.regularizers:l2_regularizer(scale, scope=None)Returns a function that can be used to apply L2 regularization to weights.
阻止过拟合用的    Small values of L2 can help prevent overfitting the training data.Args:scale: A scalar multiplier `Tensor`. 0.0 disables the regularizer.scope: An optional scope name.Returns:A function with signature `l2(weights)` that applies L2 regularization.Raises:ValueError: If scale is negative or if scale is not a float.None
[Finished in 2.3s]

再来看看l1正则化：

import tensorflow as tf
print(help(tf.contrib.layers.l1_regularizer))/usr/local/Cellar/python/3.7.0/Frameworks/Python.framework/Versions/3.7/lib/python3.7/importlib/_bootstrap.py:219: RuntimeWarning: compiletime version 3.6 of module 'tensorflow.python.framework.fast_tensor_util' does not match runtime version 3.7return f(*args, **kwds)
Help on function l1_regularizer in module tensorflow.contrib.layers.python.layers.regularizers:l1_regularizer(scale, scope=None)Returns a function that can be used to apply L1 regularization to weights.L1 regularization encourages sparsity.让矩阵更稀疏导致某一维的权重为0 ，产生稀疏权重矩阵Args:scale: A scalar multiplier `Tensor`. 0.0 disables the regularizer.scope: An optional scope name.Returns:A function with signature `l1(weights)` that apply L1 regularization.Raises:ValueError: If scale is negative or if scale is not a float.None
[Finished in 2.4s]

认识你是我们的缘分，同学，等等，学习人工智能，记得关注我。

微信扫一扫
关注该公众号

《湾区人工智能》

常用的正则化方法总结相关推荐

人工智能算法模型必会之——正则化方法综述
https://www.toutiao.com/a6718749367164994055/ 什么是正则化? 首先英文原文为regularization,直译应为规则化,简单来说就是对模型加入规则,加入 ...
正则化方法/防止过拟合提高泛化能力的方法：L1和L2 regularization、数据集扩增、dropout
转载自:http://blog.csdn.net/u012162613/article/details/44261657 本文是<Neural networks and deep learnin ...
正则化方法：数据增强、regularization、dropout
文章目录过拟合 overfitting 数据增强正则化项范数 norm L1 正则 Lasso regularizer L2 正则 Ridge Regularizer / Weight Deca ...
python正则_正则化方法及Python实现
正则化有助于克服过度拟合模型的问题.过度拟合是偏差和方差平衡的概念.如果过度拟合,机器学习模型将具有较低的准确性.当我们的机器学习模型试图从数据中学习更多属性时,就会添加来自训练数据的噪声.这里的噪声 ...
python正则化函数_正则化方法及Python实现
正则化有助于克服过度拟合模型的问题.过度拟合是偏差和方差平衡的概念.如果过度拟合,机器学习模型将具有较低的准确性.当我们的机器学习模型试图从数据中学习更多属性时,就会添加来自训练数据的噪声.这里的噪声 ...
数据维度爆炸怎么办？详解5大常用的特征选择方法
↑↑↑关注后"星标"Datawhale 每日干货 & 每月组队学习,不错过 Datawhale干货作者:Edwin Jarvis,cnblog博客整理在许多机器学习相关 ...
数据维度爆炸怎么办？详解 5 大常用的特征选择方法
点击上方"小白学视觉",选择加"星标"或"置顶" 重磅干货,第一时间送达在许多机器学习相关的书里,很难找到关于特征选择的内容,因为特征选择 ...
常用特征工程方法总结
点击上方"小白学视觉",选择加"星标"或"置顶" 重磅干货,第一时间送达摘要:对于数据挖掘项目,本文将学习应该从哪些角度做特征工程?从哪些 ...
常用的 Normalization 方法：BN、LN、IN、GN（附代码＆链接）
来源:知乎本文约2700字,建议阅读8分钟. 本文带你了解并区分常用的Normalization. 常用的Normalization方法主要有: Batch Normalization(BN,201 ...

常用的正则化方法总结

常用的正则化方法总结相关推荐

最新文章

热门文章