neural-network - 如何正确添加和使用BatchNormLayer？

Question

简介

根据烤宽面条文档: “该层应插入到线性变换(例如 DenseLayer 或 Conv2DLayer)及其非线性之间。方便的函数batch_norm() 修改现有层以在其非线性之前插入批量归一化。”

不过千层面也有实用功能:

lasagne.layers.batch_norm

但是，由于我这边的实现，我无法使用该功能。

我的问题是:我应该如何以及在哪里添加 BatchNormLayer？

class lasagne.layers.BatchNormLayer(incoming, axes='auto', epsilon=1e-4, alpha=0.1, beta=lasagne.init.Constant(0), gamma=lasagne.init.Constant(1), mean=lasagne.init.Constant(0), inv_std=lasagne.init.Constant(1), **kwargs)

我可以在卷积层之后添加它吗？或者我应该在 maxpool 之后添加？ 我是否必须手动消除图层的偏差？

使用的方法 我只是这样使用过:

try:
        import lasagne
        import theano
        import theano.tensor as T

        input_var = T.tensor4('inputs')
        target_var = T.fmatrix('targets')

        network = lasagne.layers.InputLayer(shape=(None, 1, height, width), input_var=input_var)

        from lasagne.layers import BatchNormLayer

        network = BatchNormLayer(network,
                                 axes='auto',
                                 epsilon=1e-4,
                                 alpha=0.1,
                                 beta=lasagne.init.Constant(0),
                                 gamma=lasagne.init.Constant(1),
                                 mean=lasagne.init.Constant(0),
                                 inv_std=lasagne.init.Constant(1))

        network = lasagne.layers.Conv2DLayer(
            network, num_filters=60, filter_size=(3, 3), stride=1, pad=2,
            nonlinearity=lasagne.nonlinearities.rectify,
            W=lasagne.init.GlorotUniform())

        network = lasagne.layers.Conv2DLayer(
            network, num_filters=60, filter_size=(3, 3), stride=1, pad=1,
            nonlinearity=lasagne.nonlinearities.rectify,
            W=lasagne.init.GlorotUniform())


        network = lasagne.layers.MaxPool2DLayer(incoming=network, pool_size=(2, 2), stride=None, pad=(0, 0),
                                                ignore_border=True)


        network = lasagne.layers.DenseLayer(
            lasagne.layers.dropout(network, p=0.5),
            num_units=32,
            nonlinearity=lasagne.nonlinearities.rectify)


        network = lasagne.layers.DenseLayer(
            lasagne.layers.dropout(network, p=0.5),
            num_units=1,
            nonlinearity=lasagne.nonlinearities.sigmoid)


        return network, input_var, target_var

引用文献:

https://github.com/Lasagne/Lasagne/blob/master/lasagne/layers/normalization.py#L120-L320

http://lasagne.readthedocs.io/en/latest/modules/layers/normalization.html

Answer 1

如果不使用batch_norm:

• BatchNormLayer 应添加在密集层或卷积层之后、非线性之前。
• Maxpool 是一种非线性下采样，它将保留该层上的最高值。如果您在卷积/密集层之后添加 BatchNormLayer，采样值将被标准化。
• 如果不使用 batch_norm，请手动删除偏差，因为它是多余的。

请测试下面的代码，并告诉我们它是否适合您想要实现的目标。 如果不起作用，您可以尝试调整 batch_norm code .

import lasagne
import theano
import theano.tensor as T
from lasagne.layers import batch_norm

input_var = T.tensor4('inputs')
target_var = T.fmatrix('targets')

network = lasagne.layers.InputLayer(shape=(None, 1, height, width), input_var=input_var)

network = lasagne.layers.Conv2DLayer(
    network, num_filters=60, filter_size=(3, 3), stride=1, pad=2,
    nonlinearity=lasagne.nonlinearities.rectify,
    W=lasagne.init.GlorotUniform())
network = batch_norm(network)

network = lasagne.layers.Conv2DLayer(
    network, num_filters=60, filter_size=(3, 3), stride=1, pad=1,
    nonlinearity=lasagne.nonlinearities.rectify,
    W=lasagne.init.GlorotUniform())
network = batch_norm(network)

network = lasagne.layers.MaxPool2DLayer(incoming=network, pool_size=(2, 2), stride=None, pad=(0, 0),
                                        ignore_border=True)

network = lasagne.layers.DenseLayer(
    lasagne.layers.dropout(network, p=0.5),
    num_units=32,
    nonlinearity=lasagne.nonlinearities.rectify)
network = batch_norm(network)

network = lasagne.layers.DenseLayer(
    lasagne.layers.dropout(network, p=0.5),
    num_units=1,
    nonlinearity=lasagne.nonlinearities.sigmoid)
network = batch_norm(network)

当获取参数为您的更新方法创建图表时，请记住将 trainable 设置为 True:

params = lasagne.layers.get_all_params(l_out, trainable=True)
updates = lasagne.updates.adadelta($YOUR_LOSS_HERE, params)`