《亚洲五月色情久草在线》

在(🙄)Altera SoC DE1板卡上跑完整的卷积神经网络

这次为大家详细展示(🚊)一个利用卷积神经网络实现图片自动分类的例程。

神经网络的(🚵)优点：自动从数据中学习经验知识，无需复杂的模型和算法。

缺点：有监督学习，需(🙅)要大量的带标签数据；参数量太少时容易过拟合，泛化能力差，参数量太大时训练收敛很慢（有可能需要几个月到几(🤢)年）。

为了(👸)克服上述缺点，人们发掘了各种计算(😡)资源，包括多核CPU、GPU、DSP、ASIC、FPGA，甚(😌)至使用模拟电路。

使用CPU实现卷积神经(🍊)网络比较方便调试，但性能太(😯)差(🖥)，一般人们都选用更快的GPU实现。目前开源(🥡)的框(👘)架大多都支持GPU，如伯克利大学Caffe和Google Convnet。

微软在2015年2月宣布使用Stratix V完成了CNN加速器，处理 CIFAR10 图片(🐡)速度可达每秒2300多张。

这里我们也(🥃)使用CIFAR10图片数(😈)据，在Cyclone V板子上跑一个卷积神经网络CNN demo。由于板子(🐀)上计算资源太少（DSP Slice只有80多个），实现完整的网络不太现实，只(💦)能在FPGA上实现基本计算单元，然后由HPS统一调度。性能预期不会太高，后面给出。

CIFAR10图片都是(🏇)什么呢？先来张图！

有兴趣的朋友可以到(📏)官网下载（CIFAR10官网）(🔽)。上面提到过，CNN是有监督学习系统，需要大量带label的数据，CIFAR10就(😚)是这样一个开放的数据库，提供了60000张不同类别的图片，分为10个类（如上图左侧所示），每个类别有600张图。这个数(🎄)据集不算特别大，适合在(🌃)嵌入式平台上实现(🔋)。而更大的数据集有ImageNet-1000（ImageNet官网），拥有120多万张高清无码大图，我下载到硬(🚀)盘，占用了近200GB空间（只能忍痛将其他rmvb和avi删掉了）！

有朋(😐)友会问，不用(👛)这些数据行不行(🗼)，我们的智能手机里面照片能不能(🥞)用于CNN做训练？

答案是可以的，只是(💁)你的数据集很不“均匀”，采样不够“完备”，训(⛲)练出的模型是真实模型的“有偏估计”，而上述两个数据集经过了种种考验，已经是学术界公认的优质数据集(⏲)，一年一度的ILSVRC比赛就采用了这些(🚰)数据集。

说(😚)完数据，再说模型。先来(📤)看一张经典(😤)的CNN结构：

这是世界上第一个将CNN实用化的例(🔵)子，实现了手写体字母自(🎣)动识别。在这个CNN模型中，可以看到输入是一张32 x 32的(🥂)二维图像，经过卷积层(Convolution)、(🐓)下采样层（Subsampling，也称Pooling)、全连接层（Full Connection，也称Inner Product)后，得到一组概率(🔔)密度，我们选其中概率最大的元素作(🏙)为该模型对输入图像的分类结果(⏫)。所以实现CNN时，只需要实现三种基本算法：卷积(🌅)、下采样、矩阵乘。除此之外，每层输出都可选择是否经过非线性变换，常用的非线性(🐥)变换有ReLU和Sigmoid，前者计算较为简单，使用较为(🛵)广泛。

Caffe框架中提供了专门为cifar10数据定制的模型，是用proto格式写的，我们的demo也基于(🆕)这个模型。内容如下：

name: "CIFAR10_quick_test"input: "data"input_dim: 1input_dim: 3input_dim: 32input_dim: 32layers {name: "conv1"type: CONVOLUTIONbottom: "data"top: "conv1"blobs_lr: 1blobs_lr: 2convolution_param {num_output: 32pad: 2kernel_size: 5stride: 1}}layers {name: "pool1"type: POOLINGbottom: "conv1"top: "pool1"pooling_param {pool: MAXkernel_size: 3stride: 2}}layers {name: "relu1"type: RELUbottom: "pool1"top: "pool1"}layers {name: "conv2"type: CONVOLUTIONbottom: "pool1"top: "conv2"blobs_lr: 1blobs_lr: 2convolution_param {num_output: 32pad: 2kernel_size: 5stride: 1}}layers {name: "relu2"type: RELUbottom: "conv2"top: "conv2"}layers {name: "pool2"type: POOLINGbottom: "conv2"top: "pool2"pooling_param {pool: AVEkernel_size: 3stride: 2}}layers {name: "conv3"type: CONVOLUTIONbottom: "pool2"top: "conv3"blobs_lr: 1blobs_lr: 2convolution_param {num_output: 64pad: 2kernel_size: 5stride: 1}}layers {name: "relu3"type: RELUbottom: "conv3"top: "conv3"}layers {name: "pool3"type: POOLINGbottom: "conv3"top: "pool3"pooling_param {pool: AVEkernel_size: 3stride: 2}}layers {name: "ip1"type: INNER_PRODUCTbottom: "pool3"top: "ip1"blobs_lr: 1blobs_lr: 2inner_product_param {num_output: 64}}layers {name: "ip2"type: INNER_PRODUCTbottom: "ip1"top: "ip2"blobs_lr: 1blobs_lr: 2inner_product_param {num_output: 10}}layers {name: "prob"type: SOFTMAXbottom: "ip2"top: "prob"}

复制代码

可见，上述模型经过了(🆔)3个卷积层（conv1, conv2, conv3），每个卷积层后(⛏)面都跟着下采样层（pool1, pool2, pool3），之后有两个全连接层(ip1, ip2)，最后一层prob为SOFTMAX分类层，是计算概率密度的，这里我们不需要关心。

下面三张图分别统计了CNN模型各层的参数量、数据量(🕖)和计算量。

可以看出，卷积层的参数量很少，但数(🥋)据量很大；全连接层刚好相反，参数量(🐯)较大，但数据量很少。

通过计算量统计发现conv2计算量最大，其(🔏)次是conv3和conv1。全连接层的计算量相对卷积层较小，但不可忽略。其他层（pool1, pool2以及各(🚔)级relu）由于计算量(😊)太小，本设计中没有将其(😅)实现为Open CL kernel，而是直接CPU端实现。

综上所述，我们重点实现两个算法：卷积和矩阵乘，分别对应卷积层、全连接层的实现。

在DE1-SOC上(🍹)我利用了友晶提(🦊)供的(💥)Open CL BSP，支持C语言开发FPGA。

卷积层计算kernel函数如下：

__attribute__((num_compute_units(4)))__kernelvoid conv(__global float * a, __global float * b, __global float * c, const int M, const int N, const int K){int gx = get_global_id(0);int gy = get_global_id(1);float tmp=0.0f;for(int x = 0; x < K; x ++){for(int y = 0; y < K; y ++){tmp += a[(gx + x) * M + (gy + y)] * b[x * K + y];}}

复制代码(🙉)

全连接层计算采用矩阵乘实现，kernel函数如下：

__attribute__((num_compute_units(4)))__kernelvoid gemm(__global float * a, __global float * b, __global float * c, const int M, const int N, const int K){int gx = get_global_id(0);int gy = get_global_id(1);int sy = get_global_size(1);int sx = get_global_size(0);int s = sx * sy;for(int x = gx; x < M; x += sx){for(int y = gy; y < N; y += sy){float tmp=0.0f;for(int z = 0; z < K; z++){tmp += a[z * M + x] * b[y * K + z];}c[y * M + x] = tmp;}}}

复制代码

编译kernel函数需要使用Altera SDK for OpenCL，我用的版本(🍏)是14.0.0.200，申请了两个月的license。编译使用命令行aoc，得到*.aocx文件。

Open CL编译输出报告中给出了资源占用情况：

+--------------------------------------------------------------------+; Estimated Resource Usage Summary ;+----------------------------------------+---------------------------+; Resource + Usage ;+----------------------------------------+---------------------------+; Logic utilization ; 83% ;; Dedicated logic registers ; 46% ;; Memory blocks ; 57% ;; DSP blocks ; 25% ;+----------------------------------------+---------------------------;

复制代码

可(🥘)见，逻辑资源、存储器资源消耗较为明显，而DSP资源并未用尽，说明还有优化的空间。

编译主程序需要使用SoCEDS，我用的版本(🕍)为14.0.2.274，也是命令行方式，在工程(💑)目录下执行make，结束后得到可执行文件cnn。

将这两个文件拷贝到SD卡，按照前面的博客对板子进行设置，将CNN的模型、CIFAR10数据也拷贝到SD卡中，板子上电，mount SD卡到/mnt，执行cnn，得到输出如下：

<div class="blockcode"><blockquote>Please input the number of images(1~100):100Loading data...OK!Constructing CNN...OK!Begin calculation...Elapsed Time = 141.861 s.Real Label = 3(cat), Calc Label = 3(cat), error count = 0Real Label = 8(ship), Calc Label = 8(ship), error count = 0Real Label = 8(ship), Calc Label = 8(ship), error count = 0Real Label = 0(airplane), Calc Label = 0(airplane), error count = 0Real Label = 6(frog), Calc Label = 6(frog), error count = 0Real Label = 6(frog), Calc Label = 6(frog), error count = 0Real Label = 1(automobile), Calc Label = 1(automobile), error count = 0Real Label = 6(frog), Calc Label = 6(frog), error count = 0Real Label = 3(cat), Calc Label = 3(cat), error count = 0Real Label = 1(automobile), Calc Label = 1(automobile), error count = 0Real Label = 0(airplane), Calc Label = 0(airplane), error count = 0Real Label = 9(truck), Calc Label = 9(truck), error count = 0Real Label = 5(dog), Calc Label = 5(dog), error count = 0Real Label = 7(horse), Calc Label = 7(horse), error count = 0Real Label = 9(truck), Calc Label = 9(truck), error count = 0Real Label = 8(ship), Calc Label = 8(ship), error count = 0Real Label = 5(dog), Calc Label = 5(dog), error count = 0Real Label = 7(horse), Calc Label = 7(horse), error count = 0Real Label = 8(ship), Calc Label = 8(ship), error count = 0Real Label = 6(frog), Calc Label = 6(frog), error count = 0Real Label = 7(horse), Calc Label = 7(horse), error count = 0Real Label = 0(airplane), Calc Label = 2(bird), error count = 1Real Label = 4(deer), Calc Label = 4(deer), error count = 1Real Label = 9(truck), Calc Label = 9(truck), error count = 1Real Label = 5(dog), Calc Label = 4(deer), error count = 2Real Label = 2(bird), Calc Label = 3(cat), error count = 3Real Label = 4(deer), Calc Label = 4(deer), error count = 3Real Label = 0(airplane), Calc Label = 0(airplane), error count = 3Real Label = 9(truck), Calc Label = 9(truck), error count = 3Real Label = 6(frog), Calc Label = 6(frog), error count = 3Real Label = 6(frog), Calc Label = 6(frog), error count = 3Real Label = 5(dog), Calc Label = 5(dog), error count = 3Real Label = 4(deer), Calc Label = 4(deer), error count = 3Real Label = 5(dog), Calc Label = 5(dog), error count = 3Real Label = 9(truck), Calc Label = 9(truck), error count = 3Real Label = 2(bird), Calc Label = 3(cat), error count = 4Real Label = 4(deer), Calc Label = 7(horse), error count = 5Real Label = 1(automobile), Calc Label = 9(truck), error count = 6Real Label = 9(truck), Calc Label = 9(truck), error count = 6Real Label = 5(dog), Calc Label = 5(dog), error count = 6Real Label = 4(deer), Calc Label = 4(deer), error count = 6Real Label = 6(frog), Calc Label = 6(frog), error count = 6Real Label = 5(dog), Calc Label = 5(dog), error count = 6Real Label = 6(frog), Calc Label = 6(frog), error count = 6Real Label = 0(airplane), Calc Label = 0(airplane), error count = 6Real Label = 9(truck), Calc Label = 9(truck), error count = 6Real Label = 3(cat), Calc Label = 5(dog), error count = 7Real Label = 9(truck), Calc Label = 9(truck), error count = 7Real Label = 7(horse), Calc Label = 7(horse), error count = 7Real Label = 6(frog), Calc Label = 6(frog), error count = 7Real Label = 9(truck), Calc Label = 9(truck), error count = 7Real Label = 8(ship), Calc Label = 8(ship), error count = 7Real Label = 0(airplane), Calc Label = 2(bird), error count = 8Real Label = 3(cat), Calc Label = 3(cat), error count = 8Real Label = 8(ship), Calc Label = 8(ship), error count = 8Real Label = 8(ship), Calc Label = 8(ship), error count = 8Real Label = 7(horse), Calc Label = 7(horse), error count = 8Real Label = 7(horse), Calc Label = 7(horse), error count = 8Real Label = 4(deer), Calc Label = 3(cat), error count = 9Real Label = 6(frog), Calc Label = 3(cat), error count = 10Real Label = 7(horse), Calc Label = 7(horse), error count = 10Real Label = 3(cat), Calc Label = 5(dog), error count = 11Real Label = 6(frog), Calc Label = 6(frog), error count = 11Real Label = 3(cat), Calc Label = 3(cat), error count = 11Real Label = 6(frog), Calc Label = 6(frog), error count = 11Real Label = 2(bird), Calc Label = 2(bird), error count = 11Real Label = 1(automobile), Calc Label = 1(automobile), error count = 11Real Label = 2(bird), Calc Label = 2(bird), error count = 11Real Label = 3(cat), Calc Label = 3(cat), error count = 11Real Label = 7(horse), Calc Label = 9(truck), error count = 12Real Label = 2(bird), Calc Label = 2(bird), error count = 12Real Label = 6(frog), Calc Label = 6(frog), error count = 12Real Label = 8(ship), Calc Label = 8(ship), error count = 12Real Label = 8(ship), Calc Label = 8(ship), error count = 12Real Label = 0(airplane), Calc Label = 0(airplane), error count = 12Real Label = 2(bird), Calc Label = 2(bird), error count = 12Real Label = 9(truck), Calc Label = 0(airplane), error count = 13Real Label = 3(cat), Calc Label = 3(cat), error count = 13Real Label = 3(cat), Calc Label = 2(bird), error count = 14Real Label = 8(ship), Calc Label = 8(ship), error count = 14Real Label = 8(ship), Calc Label = 8(ship), error count = 14Real Label = 1(automobile), Calc Label = 1(automobile), error count = 14Real Label = 1(automobile), Calc Label = 1(automobile), error count = 14Real Label = 7(horse), Calc Label = 7(horse), error count = 14Real Label = 2(bird), Calc Label = 2(bird), error count = 14Real Label = 5(dog), Calc Label = 7(horse), error count = 15Real Label = 2(bird), Calc Label = 2(bird), error count = 15Real Label = 7(horse), Calc Label = 7(horse), error count = 15Real Label = 8(ship), Calc Label = 8(ship), error count = 15Real Label = 9(truck), Calc Label = 9(truck), error count = 15Real Label = 0(airplane), Calc Label = 0(airplane), error count = 15Real Label = 3(cat), Calc Label = 4(deer), error count = 16Real Label = 8(ship), Calc Label = 8(ship), error count = 16Real Label = 6(frog), Calc Label = 6(frog), error count = 16Real Label = 4(deer), Calc Label = 4(deer), error count = 16Real Label = 6(frog), Calc Label = 6(frog), error count = 16Real Label = 6(frog), Calc Label = 6(frog), error count = 16Real Label = 0(airplane), Calc Label = 2(bird), error count = 17Real Label = 0(airplane), Calc Label = 0(airplane), error count = 17Real Label = 7(horse), Calc Label = 7(horse), error count = 17Classify Score = 83 %.

上(📽)面的执行流程是这样的，首先输入测试样本数(🤴)目（1到100），由于DE1板子FPGA端SDRAM容量较小，难以加载全部测试数据（10000张图片），故(🚽)每次最多装入100张图片。之后载入数据(🐓)到HPS内存，然后开(🐕)始构建(😱)CNN模型，构建过程中也实现了Open CL的初始化。构建完毕，将输入图像依次通过CNN，得到一系列分类结果，与标签进行对比，统计错误分类个数，计算分(🏎)类准确率。

经过测试，分类(🐣)准确率达到83%，与Caffe测试结果一致。

经过以(😉)上测试，可以得到结论：

（1）使用Open CL可以很方便地移植高级语言编写的算法；

（2）CNN在移植(💢)过程中需要考虑实际硬件，定制合适的模型和(🦎)数据；

（3）Cyclone 5逻辑资源较少（85K，Open CL kernel占用了83%），如果希望(😘)进一步提高计算速度，一方面可以选用高性能器件（如Stratix V、Arria 10），另一方面可以使用RTL自己搭建计(🎃)算系统。

以上图文内容均是EEWORLD论坛网友zhaoyongke原创(🏬)，在(🚮)此感(👐)谢。

欢迎微博@EEWORLD

如果你也写过此类原创干货请关注(🔙)微信订(🌏)阅号（ID：eeworldbbs，将(🗡)你的原创发至(📅)：bbs_service@eeworld.com.cn，一经入选，我们将帮你登上头条！

与更多(🍦)行业内网友进(🌤)行交流请登陆EEWORLD论坛。

【亚洲五月色情久草在线的相关新闻】