《快手福利视频网87》

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。

【快手福利视频网87的相关新闻】