weightlayer的简单介绍

weigh是什么意思

1.考虑...称重...

他用手称包裹的重量。

他用手称了一下包裹。

2.

考虑；权衡

他们在做决定前权衡了利弊。

他们在做决定前权衡了利弊。

3.

起锚。

4.

沉重，弯曲...；给?增加太多负担

梨树的树枝被果实压弯了。

梨树的树枝被沉甸甸的果实压弯了。一站式出国留学攻略

什么是动画权重

每个动画层都具有一个“权重”(Weight)值，该值决定了该层动画在结果动画中播放的量。

将“权重”(Weight)值设定为 1 时，所有层的动画都会在结果中播放。“权重”(Weight)值为 0 意味着没有任何层的动画将在结果中播放。

计算结果动画时，需将动画层的属性乘以层的“权重”(Weight)值。例如，如果为 AnimLayer1 上反弹球的“translateY”值设置动画，然后将“权重”(Weight)值减少到 0.5，则播放 AnimLayer1 的动画时该球仅反弹一半高度。

如果要在覆盖-穿过模式下使用层，通过“权重”(Weight)值还可以控制“覆盖”(Override)层的不透明度。

关于Animator.setLayerWeight这是什么意思

Character Animator是adobe的一款新应用，可以将Photoshop和Illustrator中的静态图像，通过摄像头和麦克风等辅助设备，与我们的面部表情相连接，让这些静态图像和角色可以随着我们的表情变化而产生相应的表情，真正做到“活”起来。用户可以通过相应软件，改变这个虚拟角色的外观和细节，让角色更具个性。也可以通过相关程序的编写，让这个虚拟角色进行更多的行为和活动表现。以前很多电影（尤其是动画电影）上面会用到这项专业技术，现在Character Animator将其实现民用化了

如何看MATLAB运行神经网络的结果

如何看MATLAB运行神经网络的结果

从图中Neural Network可以看出，你的网络结构是两个隐含层，2-3-1-1结构的网络，算法是traindm，显示出来的误差变化为均方误差值mse。经过482次迭代循环完成训练，耗时5秒。相同计算精度的话，训练次数越少，耗时越短，网络结构越优秀。达到设定的网络精度0.001的时候，误差下降梯度为0.0046，远大于默认的1e-5，说明此时的网络误差仍在快速下降，所以可以把训练精度目标再提高一些，比如设为0.0001或者1e-5。

Very Deep Convolutional Networks for Large-Scale Image Recognition翻译[上]

Very Deep Convolutional Networks for Large-Scale Image Recognition翻译 下

code

Very Deep Convolutional Networks for Large-Scale Image Recognition

用于大规模图像识别的非常深的卷积网络

论文：

ABSTRACT

摘要

) convolution ?lters, which shows that a signi?cant improvement on the prior-art con?gurations can be achieved by pushing the depth to 16–19 weight layers. These ?ndings were the basis of our ImageNet Challenge 2014 submission, where our team secured the ?rst and the second places in the localisation and classi?cation tracks respectively. We also show that our representations generalise well to other datasets, where they achieve state-of-the-art results. We have made our two best-performing ConvNet models publicly available to facilitate further research on the use of deep visual representations in computer vision.

）卷积滤波器的体系结构对深度网络进行深入评估，这表明通过将深度推到16-19个重量层可以实现对现有技术配置的显着改进。这些发现是我们ImageNet Challenge 2014提交的基础，我们的团队分别获得了本地化和分类轨道的第一和第二名。我们还表明，我们的表示很好地适用于其他数据集，他们在那里获得最新的结果。我们已经公开发布了两款性能最佳的ConvNet模型，以便于进一步研究在计算机视觉中使用深度视觉表示。

1 INTRODUCTION

1引言

Convolutional networks (ConvNets) have recently enjoyed a great success in large-scale image and video recognition (Krizhevsky et al., 2012; Zeiler Fergus, 2013; Sermanet et al., 2014; Simonyan Zisserman, 2014) which has become possible due to the large public image repositories, such as ImageNet (Deng et al., 2009), and high-performance computing systems, such as GPUs or large-scale distributed clusters (Dean et al., 2012). In particular, an important role in the advance of deep visual recognition architectures has been played by the ImageNet Large-Scale Visual Recognition Challenge (ILSVRC) (Russakovsky et al., 2014), which has served as a testbed for a few generations of large-scale image classi?cation systems, from high-dimensional shallow feature encodings (Perronnin et al., 2010) (the winner of ILSVRC-2011) to deep ConvNets (Krizhevsky et al., 2012) (the winner of ILSVRC-2012).

卷积网络（ConvNets）最近在大规模图像和视频识别（Krizhevsky等，2012; Zeiler＆Fergus，2013; Sermanet等，2014; Simonyan＆Zisserman，2014）方面取得了巨大的成功，这已经成为可能由于大型公共图像库（如ImageNet（Deng等，2009））和高性能计算系统（如GPU或大规模分布式群集）（Dean等，2012）。特别是，ImageNet大规模视觉识别挑战（ILSVRC）（Russakovsky et al。，2014）对深度视觉识别架构的发展起到了重要作用，它已经成为几代大型（Perronnin et al。，2010）（ILSVRC-2011的获胜者）到深层ConvNets（Krizhevsky等，2012）（ILSVRC-2012的获胜者）的高分辨率图像分类系统。

) convolution ?lters in all layers.

）卷积滤波器，这是可行的。

As a result, we come up with signi?cantly more accurate ConvNet architectures, which not only achieve the state-of-the-art accuracy on ILSVRC classi?cation and localisation tasks, but are also applicable to other image recognition datasets, where they achieve excellent performance even when used as a part of a relatively simple pipelines (e.g. deep features classi?ed by a linear SVM without ?ne-tuning). We have released our two best-performing models1 to facilitate further research.

因此，我们提出了更加精确的ConvNet架构，它不仅实现了ILSVRC分类和本地化任务的最新准确度，而且还适用于其他图像识别数据集，甚至可以实现卓越的性能当用作相对简单的管道的一部分时（例如，不需要微调的线性SVM对深度特征进行分类）。我们发布了两款性能最好的模型1，以便于进一步研究。

The rest of the paper is organised as follows. In Sect. 2, we describe our ConvNet con?gurations. The details of the image classi?cation training and evaluation are then presented in Sect. 3, and the ?current af?liation: Google DeepMind +current af?liation: University of Oxford and Google DeepMind 1 ?vgg/research/very_deep/ con?gurations are compared on the ILSVRC classi?cation task in Sect. 4. Sect. 5 concludes the paper. For completeness, we also describe and assess our ILSVRC-2014 object localisation system in Appendix A, and discuss the generalisation of very deep features to other datasets in Appendix B. Finally, Appendix C contains the list of major paper revisions.

本文的其余部分安排如下。在Sect。 2，我们描述了我们的ConvNet配置。图像分类培训和评估的细节将在第二部分中介绍。 3和*当前补充：Google DeepMind +当前补充：牛津大学和Google DeepMind 1http： // 配置在ILSVRC分类任务中进行比较教派。 4. Sect。 5结束了论文。为了完整起见，我们还在附录A中描述和评估了ILSVRC-2014对象定位系统，并讨论了附录B中对其他数据集的深入特征的概括。最后，附录C包含主要论文修订版的列表。

2 CONVNET CONFIGURATIONS

2 CONVNET配置

To measure the improvement brought by the increased ConvNet depth in a fair setting, all our ConvNet layer con?gurations are designed using the same principles, inspired by Ciresan et al. (2011); Krizhevsky et al. (2012). In this section, we ?rst describe a generic layout of our ConvNet con?gurations (Sect. 2.1) and then detail the speci?c con?gurations used in the evaluation (Sect. 2.2). Our design choices are then discussed and compared to the prior art in Sect. 2.3.

为了衡量公平环境下ConvNet深度增加所带来的改进，我们所有的ConvNet层配置都采用了Ciresan等人的相同原则设计。 （2011）; Krizhevsky等人。 （2012年）。在本节中，我们首先描述ConvNet配置的一般布局（第2.1节），然后详细介绍评估中使用的特定配置（第2.2节）。然后讨论我们的设计选择，并与Sect中的现有技术进行比较。 2.3。

2.1 ARCHITECTURE

2.1体系结构

A stack of convolutional layers (which has a different depth in different architectures) is followed by three Fully-Connected (FC) layers: the ?rst two have 4096 channels each, the third performs 1000way ILSVRC classi?cation and thus contains 1000 channels (one for each class). The ?nal layer is the soft-max layer. The con?guration of the fully connected layers is the same in all networks.

一堆卷积层（在不同的体系结构中具有不同的深度）之后是三个全连接（FC）层：前两个层各有4096个通道，第三层执行1000way ILSVRC分类，因此包含1000个通道（每个类）。最后一层是软 - 最大层。全连接层的配置在所有网络中都是相同的。

All hidden layers are equipped with the recti?cation (ReLU (Krizhevsky et al., 2012)) non-linearity. We note that none of our networks (except for one) contain Local Response Normalisation (LRN) normalisation (Krizhevsky et al., 2012): as will be shown in Sect. 4, such normalisation does not improve the performance on the ILSVRC dataset, but leads to increased memory consumption and computation time. Where applicable, the parameters for the LRN layer are those of (Krizhevsky et al., 2012).

所有隐藏层都配备了整合（ReLU（Krizhevsky et al。，2012））非线性。我们注意到我们的网络（除了一个网络）都没有包含本地响应规范化（LRN）规范化（Krizhevsky et al。，2012）。如图4所示，这种归一化不会提高ILSVRC数据集的性能，但会导致内存消耗和计算时间增加。在适用的情况下，LRN层的参数是（Krizhevsky et al。，2012）的参数。

2.2 CONFIGURATIONS

2.2配置

The ConvNet con?gurations, evaluated in this paper, are outlined in Table 1, one per column. In the following we will refer to the nets by their names (A–E). All con?gurations follow the generic design presented in Sect. 2.1, and differ only in the depth: from 11 weight layers in the network A (8 conv. and 3 FC layers) to 19 weight layers in the network E (16 conv. and 3 FC layers). The width of conv. layers (the number of channels) is rather small, starting from 64 in the ?rst layer and then increasing by a factor of 2 after each max-pooling layer, until it reaches 512.

本文中评估的ConvNet配置在表1中列出，每列一列。下面我们将以他们的名字（A-E）来提及网。所有的配置都遵循Sect中的通用设计。 2.1，并且仅在深度上有所不同：从网络A中的11个权重层（8个转发层和3个FC层）到网络E中的19个权重层（16个转发层和3个FC层）。conv的宽度。层数（通道数量）相当小，从第一层64层开始，然后在每个最大池层后增加2倍，直到达到512。

In Table 2 we report the number of parameters for each con?guration. In spite of a large depth, the number of weights in our nets is not greater than the number of weights in a more shallow net with larger conv. layer widths and receptive ?elds (144M weights in (Sermanet et al., 2014)).

在表2中，我们报告了每个配置的参数数量。尽管深度很大，但我们的网中的重量数量不会超过更大的转化次数的更浅网中的重量数量。图层宽度和接受域（Sermanet et al。，2014）中的144M权重）。

2.3 DISCUSSION

2.3讨论

3 CLASSIFICATION FRAMEWORK

3分类框架

In the previous section we presented the details of our network con?gurations. In this section, we describe the details of classi?cation ConvNet training and evaluation.

在上一节中，我们介绍了我们网络配置的细节。在本节中，我们将描述分类ConvNet培训和评估的细节。

3.1 TRAINING

3.1培训