Going Deeper with Convolutions

Abstract

We propose a deep convolutional neural network architecture codenamed Inception that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14). The main hallmark of this architecture is the improved utilization of the computing resources inside the network. By a carefully crafted design, we increased the depth and width of the network while keeping the computational budget constant. To optimize quality, the architectural decisions were based on the Hebbian principle and the intuition of multi-scale processing. One particular incarnation used in our submission for ILSVRC14 is called GoogLeNet, a 22 layers deep network, the quality of which is assessed in the context of classification and detection.

我们在ImageNet大规模视觉识别挑战赛2014（ILSVRC14）上提出了一种代号为Inception的深度卷积神经网络结构，并在分类和检测上取得了新的最好结果。这个架构的主要特点是提高了网络内部计算资源的利用率。通过精心的手工设计，我们在增加了网络深度和广度的同时保持了计算预算不变。为了优化质量，架构的设计以赫布理论和多尺度处理直觉为基础。我们在ILSVRC14提交中应用的一个特例被称为GoogLeNet，一个22层的深度网络，其质量在分类和检测的背景下进行了评估。

1. Introduction

In the last three years, our object classification and detection capabilities have dramatically improved due to advances in deep learning and convolutional networks [10]. One encouraging news is that most of this progress is not just the result of more powerful hardware, larger datasets and bigger models, but mainly a consequence of new ideas, algorithms and improved network architectures. No new data sources were used, for example, by the top entries in the ILSVRC 2014 competition besides the classification dataset of the same competition for detection purposes. Our GoogLeNet submission to ILSVRC 2014 actually uses 12 times fewer parameters than the winning architecture of Krizhevsky et al [9] from two years ago, while being significantly more accurate. On the object detection front, the biggest gains have not come from naive application of bigger and bigger deep networks, but from the synergy of deep architectures and classical computer vision, like the R-CNN algorithm by Girshick et al [6].

1. 引言

过去三年中，由于深度学习和卷积网络的发展[10]，我们的目标分类和检测能力得到了显著提高。一个令人鼓舞的消息是，大部分的进步不仅仅是更强大硬件、更大数据集、更大模型的结果，而主要是新的想法、算法和网络结构改进的结果。例如，ILSVRC 2014竞赛中最靠前的输入除了用于检测目的的分类数据集之外，没有使用新的数据资源。我们在ILSVRC 2014中的GoogLeNet提交实际使用的参数只有两年前Krizhevsky等人[9]获胜结构参数的1/12，而结果明显更准确。在目标检测前沿，最大的收获不是来自于越来越大的深度网络的简单应用，而是来自于深度架构和经典计算机视觉的协同，像Girshick等人[6]的R-CNN算法那样。

Another notable factor is that with the ongoing traction of mobile and embedded computing, the efficiency of our algorithms —— especially their power and memory use —— gains importance. It is noteworthy that the considerations leading to the design of the deep architecture presented in this paper included this factor rather than having a sheer fixation on accuracy numbers. For most of the experiments, the models were designed to keep a computational budget of 1.5 billion multiply-adds at inference time, so that the they do not end up to be a purely academic curiosity, but could be put to real world use, even on large datasets, at a reasonable cost.

另一个显著因素是随着移动和嵌入式设备的推动，我们的算法的效率很重要——尤其是它们的电力和内存使用。值得注意的是，正是包含了这个因素的考虑才得出了本文中呈现的深度架构设计，而不是单纯的为了提高准确率。对于大多数实验来说，模型被设计为在一次推断中保持15亿乘加的计算预算，所以最终它们不是单纯的学术好奇心，而是能在现实世界中应用，甚至是以合理的代价在大型数据集上使用。

In this paper, we will focus on an efficient deep neural network architecture for computer vision, codenamed Inception, which derives its name from the Network in network paper by Lin et al [12] in conjunction with the famous “we need to go deeper” internet meme [1]. In our case, the word “deep” is used in two different meanings: first of all, in the sense that we introduce a new level of organization in the form of the “Inception module” and also in the more direct sense of increased network depth. In general, one can view the Inception model as a logical culmination of [12] while taking inspiration and guidance from the theoretical work by Arora et al [2]. The benefits of the architecture are experimentally verified on the ILSVRC 2014 classification and detection challenges, where it significantly outperforms the current state of the art.

在本文中，我们将关注一个高效的计算机视觉深度神经网络架构，代号为Inception，它的名字来自于Lin等人[12]网络论文中的Network与著名的“we need to go deeper”网络迷因[1]的结合。在我们的案例中，单词“deep”用在两个不同的含义中：首先，在某种意义上，我们以“Inception module”的形式引入了一种新层次的组织方式，在更直接的意义上增加了网络的深度。一般来说，可以把Inception模型看作论文[12]的逻辑顶点同时从Arora等人[2]的理论工作中受到了鼓舞和引导。这种架构的好处在ILSVRC 2014分类和检测挑战赛中通过实验得到了验证，它明显优于目前的最好水平。

2. Related Work 近期工作

Starting with LeNet-5 [10], convolutional neural networks (CNN) have typically had a standard structure —— stacked convolutional layers (optionally followed by contrast normalization and max-pooling) are followed by one or more fully-connected layers. Variants of this basic design are prevalent in the image classification literature and have yielded the best results to-date on MNIST, CIFAR and most notably on the ImageNet classification challenge [9, 21]. For larger datasets such as Imagenet, the recent trend has been to increase the number of layers [12] and layer size [21, 14], while using dropout [7] to address the problem of overfitting.

从LeNet-5 [10]开始，卷积神经网络（CNN）通常有一个标准结构——堆叠的卷积层（后面可以选择有对比归一化和最大池化）后面是一个或更多的全连接层。这个基本设计的变种在图像分类著作流行，并且目前为止在MNIST，CIFAR和更著名的ImageNet分类挑战赛中[9, 21]的已经取得了最佳结果。对于更大的数据集例如ImageNet来说，最近的趋势是增加层的数目[12]和层的大小[21, 14]，同时使用丢弃[7]来解决过拟合问题。

Despite concerns that max-pooling layers result in loss of accurate spatial information, the same convolutional network architecture as [9] has also been successfully employed for localization [9, 14], object detection [6, 14, 18, 5] and human pose estimation [19].

尽管担心最大池化层会引起准确空间信息的损失，但与[9]相同的卷积网络结构也已经成功的应用于定位[9, 14]，目标检测[6, 14, 18, 5]和行人姿态估计[19]。

Inspired by a neuroscience model of the primate visual cortex, Serre et al. [15] used a series of fixed Gabor filters of different sizes to handle multiple scales. We use a similar strategy here. However, contrary to the fixed 2-layer deep model of [15], all filters in the Inception architecture are learned. Furthermore, Inception layers are repeated many times, leading to a 22-layer deep model in the case of the GoogLeNet model.

受灵长类视觉皮层神经科学模型的启发，Serre等人[15]使用了一系列固定的不同大小的Gabor滤波器来处理多尺度。我们使用一个了类似的策略。然而，与[15]的固定的2层深度模型相反，Inception结构中所有的滤波器是学习到的。此外，Inception层重复了很多次，在GoogLeNet模型中得到了一个22层的深度模型。

Network-in-Network is an approach proposed by Lin et al. [12] in order to increase the representational power of neural networks. In their model, additional 1 × 1 convolutional layers are added to the network, increasing its depth. We use this approach heavily in our architecture. However, in our setting, 1 × 1 convolutions have dual purpose: most critically, they are used mainly as dimension reduction modules to remove computational bottlenecks, that would otherwise limit the size of our networks. This allows for not just increasing the depth, but also the width of our networks without a significant performance penalty.

Network-in-Network是Lin等人[12]为了增加神经网络表现能力而提出的一种方法。在他们的模型中，网络中添加了额外的1 × 1卷积层，增加了网络的深度。我们的架构中大量的使用了这个方法。但是，在我们的设置中，1 × 1卷积有两个目的：最关键的是，它们主要是用来作为降维模块来移除卷积瓶颈，否则将会限制我们网络的大小。这不仅允许了深度的增加，而且允许我们网络的宽度增加但没有明显的性能损失。

Finally, the current state of the art for object detection is the Regions with Convolutional Neural Networks (R-CNN) method by Girshick et al. [6]. R-CNN decomposes the overall detection problem into two subproblems: utilizing low-level cues such as color and texture in order to generate object location proposals in a category-agnostic fashion and using CNN classifiers to identify object categories at those locations. Such a two stage approach leverages the accuracy of bounding box segmentation with low-level cues, as well as the highly powerful classification power of state-of-the-art CNNs. We adopted a similar pipeline in our detection submissions, but have explored enhancements in both stages, such as multi-box [5] prediction for higher object bounding box recall, and ensemble approaches for better categorization of bounding box proposals.

最后，目前最好的目标检测是Girshick等人[6]的基于区域的卷积神经网络（R-CNN）方法。R-CNN将整个检测问题分解为两个子问题：利用低层次的信号例如颜色，纹理以跨类别的方式来产生目标位置候选区域，然后用CNN分类器来识别那些位置上的对象类别。这样一种两个阶段的方法利用了低层特征分割边界框的准确性，也利用了目前的CNN非常强大的分类能力。我们在我们的检测提交中采用了类似的方式，但探索增强这两个阶段，例如对于更高的目标边界框召回使用多盒[5]预测，并融合了更好的边界框候选区域分类方法。

3. Motivation and High Level Considerations 动机和高层思考

The most straightforward way of improving the performance of deep neural networks is by increasing their size. This includes both increasing the depth —— the number of network levels —— as well as its width: the number of units at each level. This is an easy and safe way of training higher quality models, especially given the availability of a large amount of labeled training data. However, this simple solution comes with two major drawbacks.
Bigger size typically means a larger number of parameters, which makes the enlarged network more prone to overfitting, especially if the number of labeled examples in the training set is limited. This is a major bottleneck as strongly labeled datasets are laborious and expensive to obtain, often requiring expert human raters to distinguish between various fine-grained visual categories such as those in ImageNet (even in the 1000-class ILSVRC subset) as shown in Figure 1.

提高深度神经网络性能最直接的方式是增加它们的尺寸。这不仅包括增加深度——网络层次的数目——也包括它的宽度：每一层的单元数目。这是一种训练更高质量模型容易且安全的方法，尤其是在可获得大量标注的训练数据的情况下。但是这个简单方案有两个主要的缺点。更大的尺寸通常意味着更多的参数，这会使增大的网络更容易过拟合，尤其是在训练集的标注样本有限的情况下。这是一个主要的瓶颈，因为要获得强标注数据集费时费力且代价昂贵，经常需要专家评委在各种细粒度的视觉类别进行区分，例如图1中显示的ImageNet中的类别（甚至是1000类ILSVRC的子集）。

Figure 1: Two distinct classes from the 1000 classes of the ILSVRC 2014 classification challenge. Domain knowledge is required to distinguish between these classes.

图1: ILSVRC 2014分类挑战赛的1000类中两个不同的类别。区分这些类别需要领域知识。

The other drawback of uniformly increased network size is the dramatically increased use of computational resources. For example, in a deep vision network, if two convolutional layers are chained, any uniform increase in the number of their filters results in a quadratic increase of computation. If the added capacity is used inefficiently (for example, if most weights end up to be close to zero), then much of the computation is wasted. As the computational budget is always finite, an efficient distribution of computing resources is preferred to an indiscriminate increase of size, even when the main objective is to increase the quality of performance.

均匀增加网络尺寸的另一个缺点是计算资源使用的显著增加。例如，在一个深度视觉网络中，如果两个卷积层相连，它们的滤波器数目的任何均匀增加都会引起计算量平方式的增加。如果增加的能力使用时效率低下（例如，如果大多数权重结束时接近于0），那么会浪费大量的计算能力。由于计算预算总是有限的，计算资源的有效分布更偏向于尺寸无差别的增加，即使主要目标是增加性能的质量。

A fundamental way of solving both of these issues would be to introduce sparsity and replace the fully connected layers by the sparse ones, even inside the convolutions. Besides mimicking biological systems, this would also have the advantage of firmer theoretical underpinnings due to the groundbreaking work of Arora et al. [2]. Their main result states that if the probability distribution of the dataset is representable by a large, very sparse deep neural network, then the optimal network topology can be constructed layer after layer by analyzing the correlation statistics of the preceding layer activations and clustering neurons with highly correlated outputs. Although the strict mathematical proof requires very strong conditions, the fact that this statement resonates with the well known Hebbian principle —— neurons that fire together, wire together —— suggests that the underlying idea is applicable even under less strict conditions, in practice.

解决这两个问题的一个基本的方式就是引入稀疏性并将全连接层替换为稀疏的全连接层，甚至是卷积层。除了模仿生物系统之外，由于Arora等人[2]的开创性工作，这也具有更坚固的理论基础优势。他们的主要成果说明如果数据集的概率分布可以通过一个大型稀疏的深度神经网络表示，则最优的网络拓扑结构可以通过分析前一层激活的相关性统计和聚类高度相关的神经元来一层层的构建。虽然严格的数学证明需要在很强的条件下，但事实上这个声明与著名的赫布理论产生共鸣——神经元一起激发，一起连接——实践表明，基础概念甚至适用于不严格的条件下。

Unfortunately, today’s computing infrastructures are very inefficient when it comes to numerical calculation on non-uniform sparse data structures. Even if the number of arithmetic operations is reduced by 100×, the overhead of lookups and cache misses would dominate: switching to sparse matrices might not pay off. The gap is widened yet further by the use of steadily improving and highly tuned numerical libraries that allow for extremely fast dense matrix multiplication, exploiting the minute details of the underlying CPU or GPU hardware [16, 9]. Also, non-uniform sparse models require more sophisticated engineering and computing infrastructure. Most current vision oriented machine learning systems utilize sparsity in the spatial domain just by the virtue of employing convolutions. However, convolutions are implemented as collections of dense connections to the patches in the earlier layer. ConvNets have traditionally used random and sparse connection tables in the feature dimensions since [11] in order to break the symmetry and improve learning, yet the trend changed back to full connections with [9] in order to further optimize parallel computation. Current state-of-the-art architectures for computer vision have uniform structure. The large number of filters and greater batch size allows for the efficient use of dense computation.

遗憾的是，当碰到在非均匀的稀疏数据结构上进行数值计算时，现在的计算架构效率非常低下。即使算法运算的数量减少100倍，查询和缓存丢失上的开销仍占主导地位：切换到稀疏矩阵可能是不可行的。随着稳定提升和高度调整的数值库的应用，差距仍在进一步扩大，数值库要求极度快速密集的矩阵乘法，利用底层的CPU或GPU硬件[16, 9]的微小细节。非均匀的稀疏模型也要求更多的复杂工程和计算基础结构。目前大多数面向视觉的机器学习系统通过采用卷积的优点来利用空域的稀疏性。然而，卷积被实现为对上一层块的密集连接的集合。为了打破对称性，提高学习水平，从论文[11]开始，ConvNets习惯上在特征维度使用随机的稀疏连接表，然而为了进一步优化并行计算，论文[9]中趋向于变回全连接。目前最新的计算机视觉架构有统一的结构。更多的滤波器和更大的批大小要求密集计算的有效使用。

This raises the question of whether there is any hope for a next, intermediate step: an architecture that makes use of filter-level sparsity, as suggested by the theory, but exploits our current hardware by utilizing computations on dense matrices. The vast literature on sparse matrix computations (e.g. [3]) suggests that clustering sparse matrices into relatively dense submatrices tends to give competitive performance for sparse matrix multiplication. It does not seem far-fetched to think that similar methods would be utilized for the automated construction of non-uniform deep-learning architectures in the near future.

这提出了下一个中间步骤是否有希望的问题：一个架构能利用滤波器水平的稀疏性，正如理论所认为的那样，但能通过利用密集矩阵计算来利用我们目前的硬件。稀疏矩阵乘法的大量文献（例如[3]）认为对于稀疏矩阵乘法，将稀疏矩阵聚类为相对密集的子矩阵会有更佳的性能。在不久的将来会利用类似的方法来进行非均匀深度学习架构的自动构建，这样的想法似乎并不牵强。

The Inception architecture started out as a case study for assessing the hypothetical output of a sophisticated network topology construction algorithm that tries to approximate a sparse structure implied by [2] for vision networks and covering the hypothesized outcome by dense, readily available components. Despite being a highly speculative undertaking, modest gains were observed early on when compared with reference networks based on [12]. With a bit of tuning the gap widened and Inception proved to be especially useful in the context of localization and object detection as the base network for [6] and [5]. Interestingly, while most of the original architectural choices have been questioned and tested thoroughly in separation, they turned out to be close to optimal locally. One must be cautious though: although the Inception architecture has become a success for computer vision, it is still questionable whether this can be attributed to the guiding principles that have lead to its construction. Making sure of this would require a much more thorough analysis and verification.

Inception架构开始是作为案例研究，用于评估一个复杂网络拓扑构建算法的假设输出，该算法试图近似[2]中所示的视觉网络的稀疏结构，并通过密集的、容易获得的组件来覆盖假设结果。尽管是一个非常投机的事情，但与基于[12]的参考网络相比，早期可以观测到适度的收益。随着一点点调整加宽差距，作为[6]和[5]的基础网络，Inception被证明在定位上下文和目标检测中尤其有用。有趣的是，虽然大多数最初的架构选择已被质疑并分离开进行全面测试，但结果证明它们是局部最优的。然而必须谨慎：尽管Inception架构在计算机上领域取得成功，但这是否可以归因于构建其架构的指导原则仍是有疑问的。确保这一点将需要更彻底的分析和验证。

4. Architectural Details 架构细节

The main idea of the Inception architecture is to consider how an optimal local sparse structure of a convolutional vision network can be approximated and covered by readily available dense components. Note that assuming translation invariance means that our network will be built from convolutional building blocks. All we need is to find the optimal local construction and to repeat it spatially. Arora et al. [2] suggests a layer-by-layer construction where one should analyze the correlation statistics of the last layer and cluster them into groups of units with high correlation. These clusters form the units of the next layer and are connected to the units in the previous layer. We assume that each unit from an earlier layer corresponds to some region of the input image and these units are grouped into filter banks. In the lower layers (the ones close to the input) correlated units would concentrate in local regions. Thus, we would end up with a lot of clusters concentrated in a single region and they can be covered by a layer of 1×1 convolutions in the next layer, as suggested in [12]. However, one can also expect that there will be a smaller number of more spatially spread out clusters that can be covered by convolutions over larger patches, and there will be a decreasing number of patches over larger and larger regions. In order to avoid patch-alignment issues, current incarnations of the Inception architecture are restricted to filter sizes 1×1, 3×3 and 5×5; this decision was based more on convenience rather than necessity. It also means that the suggested architecture is a combination of all those layers with their output filter banks concatenated into a single output vector forming the input of the next stage. Additionally, since pooling operations have been essential for the success of current convolutional networks, it suggests that adding an alternative parallel pooling path in each such stage should have additional beneficial effect, too (see Figure 2(a)).

Inception架构的主要想法是考虑怎样近似卷积视觉网络的最优稀疏结构并用容易获得的密集组件进行覆盖。注意假设转换不变性，这意味着我们的网络将以卷积构建块为基础。我们所需要做的是找到最优的局部构造并在空间上重复它。Arora等人[2]提出了一个层次结构，其中应该分析最后一层的相关统计并将它们聚集成具有高相关性的单元组。这些聚类形成了下一层的单元并与前一层的单元连接。我们假设较早层的每个单元都对应输入层的某些区域，并且这些单元被分成滤波器组。在较低的层（接近输入的层）相关单元集中在局部区域。因此，如[12]所示，我们最终会有许多聚类集中在单个区域，它们可以通过下一层的1×1卷积层覆盖。然而也可以预期，将存在更小数目的在更大空间上扩展的聚类，其可以被更大块上的卷积覆盖，在越来越大的区域上块的数量将会下降。为了避免块校正的问题，目前Inception架构形式的滤波器的尺寸仅限于1×1、3×3、5×5，这个决定更多的是基于便易性而不是必要性。这也意味着提出的架构是所有这些层的组合，其输出滤波器组连接成单个输出向量形成了下一阶段的输入。另外，由于池化操作对于目前卷积网络的成功至关重要，因此建议在每个这样的阶段添加一个替代的并行池化路径应该也应该具有额外的有益效果（看图2(a)）。

As these “Inception modules” are stacked on top of each other, their output correlation statistics are bound to vary: as features of higher abstraction are captured by higher layers, their spatial concentration is expected to decrease. This suggests that the ratio of 3×3 and 5×5 convolutions should increase as we move to higher layers.

由于这些“Inception模块”在彼此的顶部堆叠，其输出相关统计必然有变化：由于较高层会捕获较高的抽象特征，其空间集中度预计会减少。这表明随着转移到更高层，3×3和5×5卷积的比例应该会增加。

One big problem with the above modules, at least in this naive form, is that even a modest number of 5×5 convolutions can be prohibitively expensive on top of a convolutional layer with a large number of filters. This problem becomes even more pronounced once pooling units are added to the mix: the number of output filters equals to the number of filters in the previous stage. The merging of output of the pooling layer with outputs of the convolutional layers would lead to an inevitable increase in the number of outputs from stage to stage. While this architecture might cover the optimal sparse structure, it would do it very inefficiently, leading to a computational blow up within a few stages.

上述模块的一个大问题是在具有大量滤波器的卷积层之上，即使适量的5×5卷积也可能是非常昂贵的，至少在这种朴素形式中有这个问题。一旦池化单元添加到混合中，这个问题甚至会变得更明显：输出滤波器的数量等于前一阶段滤波器的数量。池化层输出和卷积层输出的合并会导致这一阶段到下一阶段输出数量不可避免的增加。虽然这种架构可能会覆盖最优稀疏结构，但它会非常低效，导致在几个阶段内计算量爆炸。

This leads to the second idea of the Inception architecture: judiciously reducing dimension wherever the computational requirements would increase too much otherwise. This is based on the success of embeddings: even low dimensional embeddings might contain a lot of information about a relatively large image patch. However, embeddings represent information in a dense, compressed form and compressed information is harder to process. The representation should be kept sparse at most places (as required by the conditions of [2]) and compress the signals only whenever they have to be aggregated en masse. That is, 1×1 convolutions are used to compute reductions before the expensive 3×3 and 5×5 convolutions. Besides being used as reductions, they also include the use of rectified linear activation making them dual-purpose. The final result is depicted in Figure 2(b).

这导致了Inception架构的第二个想法：在计算要求会增加太多的地方，明智地减少维度。这是基于嵌入的成功：甚至低维嵌入可能包含大量关于较大图像块的信息。然而嵌入以密集、压缩形式表示信息并且压缩信息更难处理。这种表示应该在大多数地方保持稀疏（根据[2]中条件的要求】）并且仅在它们必须汇总时才压缩信号。也就是说，在昂贵的3×3和5×5卷积之前，1×1卷积用来计算降维。除了用来降维之外，它们也包括使用线性修正单元使其两用。最终的结果如图2(b)所示。

In general, an Inception network is a network consisting of modules of the above type stacked upon each other, with occasional max-pooling layers with stride 2 to halve the resolution of the grid. For technical reasons (memory efficiency during training), it seemed beneficial to start using Inception modules only at higher layers while keeping the lower layers in traditional convolutional fashion. This is not strictly necessary, simply reflecting some infrastructural inefficiencies in our current implementation.

通常，Inception网络是一个由上述类型的模块互相堆叠组成的网络，偶尔会有步长为2的最大池化层将网络分辨率减半。出于技术原因（训练过程中内存效率），只在更高层开始使用Inception模块而在更低层仍保持传统的卷积形式似乎是有益的。这不是绝对必要的，只是反映了我们目前实现中的一些基础结构效率低下。

A useful aspect of this architecture is that it allows for increasing the number of units at each stage significantly without an uncontrolled blow-up in computational complexity at later stages. This is achieved by the ubiquitous use of dimensionality reduction prior to expensive convolutions with larger patch sizes. Furthermore, the design follows the practical intuition that visual information should be processed at various scales and then aggregated so that the next stage can abstract features from the different scales simultaneously.

该架构的一个有用的方面是它允许显著增加每个阶段的单元数量，而不会在后面的阶段出现计算复杂度不受控制的爆炸。这是在尺寸较大的块进行昂贵的卷积之前通过普遍使用降维实现的。此外，设计遵循了实践直觉，即视觉信息应该在不同的尺度上处理然后聚合，为的是下一阶段可以从不同尺度同时抽象特征。

The improved use of computational resources allows for increasing both the width of each stage as well as the number of stages without getting into computational difficulties. One can utilize the Inception architecture to create slightly inferior, but computationally cheaper versions of it. We have found that all the available knobs and levers allow for a controlled balancing of computational resources resulting in networks that are 3—10× faster than similarly performing networks with non-Inception architecture, however this requires careful manual design at this point.

计算资源的改善使用允许增加每个阶段的宽度和阶段的数量，而不会陷入计算困境。可以利用Inception架构创建略差一些但计算成本更低的版本。我们发现所有可用的控制允许计算资源的受控平衡，导致网络比没有Inception结构的类似执行网络快3—10倍，但是在这一点上需要仔细的手动设计。

5. GoogLeNet

By the “GoogLeNet” name we refer to the particular incarnation of the Inception architecture used in our submission for the ILSVRC 2014 competition. We also used one deeper and wider Inception network with slightly superior quality, but adding it to the ensemble seemed to improve the results only marginally. We omit the details of that network, as empirical evidence suggests that the influence of the exact architectural parameters is relatively minor. Table 1 illustrates the most common instance of Inception used in the competition. This network (trained with different image patch sampling methods) was used for 6 out of the 7 models in our ensemble.

通过“GoogLeNet”这个名字，我们提到了在ILSVRC 2014竞赛的提交中使用的Inception架构的特例。我们也使用了一个稍微优质的更深更宽的Inception网络，但将其加入到组合中似乎只稍微提高了结果。我们忽略了该网络的细节，因为经验证据表明确切架构的参数影响相对较小。表1说明了竞赛中使用的最常见的Inception实例。这个网络（用不同的图像块采样方法训练的）使用了我们组合中7个模型中的6个。

All the convolutions, including those inside the Inception modules, use rectified linear activation. The size of the receptive field in our network is 224×224 in the RGB color space with zero mean. “#3×3 reduce” and “#5×5 reduce” stands for the number of 1×1 filters in the reduction layer used before the 3×3 and 5×5 convolutions. One can see the number of 1×1 filters in the projection layer after the built-in max-pooling in the pool proj column. All these reduction/projection layers use rectified linear activation as well.

所有的卷积都使用了修正线性激活，包括Inception模块内部的卷积。在我们的网络中感受野是在均值为0的RGB颜色空间中，大小是224×224。“#3×3 reduce”和“#5×5 reduce”表示在3×3和5×5卷积之前，降维层使用的1×1滤波器的数量。在pool proj列可以看到内置的最大池化之后，投影层中1×1滤波器的数量。所有的这些降维/投影层也都使用了线性修正激活。

The network was designed with computational efficiency and practicality in mind, so that inference can be run on individual devices including even those with limited computational resources, especially with low-memory footprint.The network