Single Shot Multibox Detection (SSD)实战(下)

2. Training

将逐步解释如何训练SSD模型进行目标检测。

2.1. Data Reading and Initialization

创建的Pikachu数据集。

batch_size = 32

train_iter, _ = d2l.load_data_pikachu(batch_size)

Pikachu数据集中有1个类别。在定义模块之后,我们需要初始化模型参数并定义优化算法。

ctx, net = d2l.try_gpu(), TinySSD(num_classes=1)

net.initialize(init=init.Xavier(), ctx=ctx)

trainer = gluon.Trainer(net.collect_params(), 'sgd',

{'learning_rate': 0.2, 'wd': 5e-4})

2.2. Defining Loss and Evaluation Functions

目标检测有两种损失。一是锚箱类损失。为此,我们可以简单地重用我们在图像分类中使用的交叉熵损失函数。第二个损失是正锚箱偏移损失。偏移量预测是一个规范化问题。但是,在这里,我们没有使用前面介绍的平方损失。相反,我们使用L1范数损失,即预测值与地面真实值之差的绝对值。mask变量bbox_masks从损失计算中删除负锚定框和填充锚定框。最后,我们加入锚箱类别和补偿损失,以找到模型的最终损失函数。

cls_loss = gluon.loss.SoftmaxCrossEntropyLoss()

bbox_loss = gluon.loss.L1Loss()

def calc_loss(cls_preds, cls_labels, bbox_preds, bbox_labels, bbox_masks):

cls = cls_loss(cls_preds, cls_labels)

bbox = bbox_loss(bbox_preds * bbox_masks, bbox_labels * bbox_masks)

return cls + bbox

我们可以用准确率来评价分类结果。当我们使用L1范数损失,我们将使用平均绝对误差来评估包围盒预测结果。

def cls_eval(cls_preds, cls_labels):

# Because the category prediction results are placed in the final

# dimension, argmax must specify this dimension

return float((cls_preds.argmax(axis=-1) == cls_labels).sum())

def bbox_eval(bbox_preds, bbox_labels, bbox_masks):

return float((np.abs((bbox_labels - bbox_preds) * bbox_masks)).sum())

2.3. Training the Model

在模型训练过程中,我们必须在模型的正向计算过程中生成多尺度锚盒(anchors),并预测每个锚盒的类别(cls_preds)和偏移量(bbox_preds)。然后,我们根据标签信息Y标记每个锚定框的类别(cls_labels)和偏移量(bbox_labels)。最后,我们使用预测和标记的类别和偏移量值计算损失函数。为了简化代码,这里不计算训练数据集。

num_epochs, timer = 20, d2l.Timer()

animator = d2l.Animator(xlabel='epoch', xlim=[1, num_epochs],

legend=['class error', 'bbox mae'])

for epoch in range(num_epochs):

# accuracy_sum, mae_sum, num_examples, num_labels

metric = d2l.Accumulator(4)

train_iter.reset()  # Read data from the start.

for batch in train_iter:

timer.start()

X = batch.data[0].as_in_ctx(ctx)

Y = batch.label[0].as_in_ctx(ctx)

with autograd.record():

# Generate multiscale anchor boxes and predict the category and

# offset of each

anchors, cls_preds, bbox_preds = net(X)

# Label the category and offset of each anchor box

bbox_labels, bbox_masks, cls_labels = npx.multibox_target(

anchors, Y, cls_preds.transpose(0, 2, 1))

# Calculate the loss function using the predicted and labeled

# category and offset values

l = calc_loss(cls_preds, cls_labels, bbox_preds, bbox_labels,

bbox_masks)

l.backward()

trainer.step(batch_size)

metric.add(cls_eval(cls_preds, cls_labels), cls_labels.size,

bbox_eval(bbox_preds, bbox_labels, bbox_masks),

bbox_labels.size)

cls_err, bbox_mae = 1-metric[0]/metric[1], metric[2]/metric[3]

animator.add(epoch+1, (cls_err, bbox_mae))

print('class err %.2e, bbox mae %.2e' % (cls_err, bbox_mae))

print('%.1f examples/sec on %s' % (train_iter.num_image/timer.stop(), ctx))

class err 2.35e-03, bbox mae 2.68e-03

4315.5 examples/sec on gpu(0)

3. Prediction

在预测阶段,我们要检测图像中所有感兴趣的对象。下面,我们读取测试图像并转换其大小。然后,我们将其转换为卷积层所需的四维格式。

img = image.imread('../img/pikachu.jpg')

feature = image.imresize(img, 256, 256).astype('float32')

X = np.expand_dims(feature.transpose(2,
0, 1), axis=0)

利用MultiBoxDetection函数,我们根据锚定框及其预测的偏移量来预测边界框。然后,我们使用非最大值抑制来移除类似的边界框。

def predict(X):

anchors, cls_preds, bbox_preds =
net(X.as_in_ctx(ctx))

cls_probs = npx.softmax(cls_preds).transpose(0,
2, 1)

output = npx.multibox_detection(cls_probs,
bbox_preds, anchors)

idx = [i for i, row in
enumerate(output[0]) if row[0] != -1]

return output[0, idx]

output = predict(X)

最后,我们取置信度至少为0.3的所有边界框,并将它们显示为最终输出。

def display(img, output, threshold):

d2l.set_figsize((5, 5))

fig = d2l.plt.imshow(img.asnumpy())

for row in output:

score = float(row[1])

if score < threshold:

continue

h, w = img.shape[0:2]

bbox = [row[2:6] * np.array((w,
h, w, h), ctx=row.ctx)]

d2l.show_bboxes(fig.axes, bbox,
'%.2f' % score, 'w')

display(img, output, threshold=0.3)

4. Loss
Function

由于空间的限制,我们在本实验中忽略了SSD模型的一些实现细节。您能否在以下方面进一步改进该模型?

For the predicted offsets, replace L1L1 norm loss with L1L1 regularization loss. This
loss function uses a square function around zero for greater smoothness. This
is the regularized area controlled by the hyperparameter σσ:

When σσ is large, this loss is similar
to the L1L1 norm loss. When the value is
small, the loss function is smoother.

sigmas = [10, 1, 0.5]

lines = ['-', '--', '-.']

x = np.arange(-2, 2, 0.1)

d2l.set_figsize()

for l, s in zip(lines, sigmas):

y = npx.smooth_l1(x, scalar=s)

d2l.plt.plot(x.asnumpy(), y.asnumpy(), l, label='sigma=%.1f' % s)

d2l.plt.legend

def focal_loss(gamma, x):

return -(1 - x) ** gamma * np.log(x)

x = np.arange(0.01, 1, 0.01)

for l, gamma in zip(lines, [0, 1, 5]):

y = d2l.plt.plot(x.asnumpy(), focal_loss(gamma, x).asnumpy(), l,

label='gamma=%.1f' % gamma)

d2l.plt.legend();

Training
and Prediction

When
an object is relatively large compared to the image, the model normally adopts
a larger input image size.

This generally produces a large
number of negative anchor boxes when labeling anchor box categories. We can
sample the negative anchor boxes to better balance the data categories. To do
this, we can set the MultiBoxTarget function’s negative_mining_ratio parameter.

Assign hyper-parameters with different weights to the
anchor box category loss and positive anchor box offset loss in the loss
function.

Refer to the SSD paper. What methods
can be used to evaluate the precision of object detection models?

5. Summary

  • SSD is a multiscale object detection model. This model generates different
    numbers of anchor boxes of different sizes based on the base network block
    and each multiscale feature block and predicts the categories and offsets
    of the anchor boxes to detect objects of different sizes.
  • During SSD model training, the loss function is calculated using the
    predicted and labeled category and offset values.

Single Shot Multibox Detection (SSD)实战(下)的更多相关文章

  1. Single Shot Multibox Detection (SSD)实战(上)

    Single Shot Multibox Detection (SSD)实战(上) 介绍了边界框.锚框.多尺度对象检测和数据集.现在,我们将利用这些背景知识构建一个目标检测模型:单次多盒检测(SSD) ...

  2. 论文笔记 SSD: Single Shot MultiBox Detector

    转载自:https://zhuanlan.zhihu.com/p/33544892 前言 目标检测近年来已经取得了很重要的进展,主流的算法主要分为两个类型(参考RefineDet):(1)two-st ...

  3. SSD: Single Shot MultiBox Detector

    By Wei Liu, Dragomir Anguelov, Dumitru Erhan, Christian Szegedy, Scott Reed, Cheng-Yang Fu, Alexande ...

  4. 目标检测--SSD: Single Shot MultiBox Detector(2015)

    SSD: Single Shot MultiBox Detector 作者: Wei Liu, Dragomir Anguelov, Dumitru Erhan, Christian Szegedy, ...

  5. SSD(single shot multibox detector)算法及Caffe代码详解[转]

    转自:AI之路 这篇博客主要介绍SSD算法,该算法是最近一年比较优秀的object detection算法,主要特点在于采用了特征融合. 论文:SSD single shot multibox det ...

  6. SSD(Single Shot MultiBox Detector)的安装配置和运行

    下文图文介绍转自watersink的博文SSD(Single Shot MultiBox Detector)不得不说的那些事. 该方法出自2016年的一篇ECCV的oral paper,SSD: Si ...

  7. SSD(single shot multibox detector)

    SSD,全称Single Shot MultiBox Detector,是Wei Liu在ECCV 2016上提出的一种目标检测算法,截至目前是主要的检测框架之一,相比Faster RCNN有明显的速 ...

  8. SSD: Single Shot MultiBox Detector 编译方法总结

    SSD是一个基于单网络的目标检测框架,它是基于caffe实现的,所以下面的教程是基于已经编译好的caffe进行编译的. caffe的编译可以参考官网 caffe Installation Instal ...

  9. [论文理解]SSD:Single Shot MultiBox Detector

    SSD:Single Shot MultiBox Detector Intro SSD是一套one-stage算法实现目标检测的框架,速度很快,在当时速度超过了yolo,精度也可以达到two-stag ...

随机推荐

  1. DVWA之SQL Injection

    SQL Injection SQL Injection,即SQL注入,是指攻击者通过注入恶意的SQL命令,破坏SQL查询语句的结构,从而达到执行恶意SQL语句的目的.SQL注入漏洞的危害是巨大的,常常 ...

  2. net -snmp 的监控策略

    yum install net-snmp net-snmp-utils -y vim /etc/snmp/snmpd.conf 最后添加:rocommunity nmap 192.168.1.0/24 ...

  3. React-列表 & Key

    <!DOCTYPE html> <html> <head> <meta charset="UTF-8" /> <title&g ...

  4. uni-app&H5&Android混合开发二 || 使用Android Studio打包应用APK

    前言: 在上一章节我们已经讲了如何uni-app离线打包Android平台教程,这一章就该来讲讲如何使用Android Studio打包应用APK提供给Android手机安装使用了. 第一步.首先打开 ...

  5. SecureCRT 基本设置

    1:字体与大小 Lucida Console   四号 2:声音关闭 Terminal-->Audio bell不勾选 默认网络工程师常用: Terminal-->Emulation--& ...

  6. 使用DevExpress的GridControl实现多层级或无穷级的嵌套列表展示

    在我早期的随笔<在GridControl表格控件中实现多层级主从表数据的展示>中介绍过GridControl实现二级.三级的层级列表展示,主要的逻辑就是构建GridLevelNode并添加 ...

  7. Windows进程间通讯(IPC)----信号量

    线程同步内核对象 操作系统进行进程间同步是利用信号量机制.对于windows系统而言,可以利用一些内核对象进行线程同步,因为这些内核对象可以命名并且属于系统内核,所以可以支持不同进程间的线程同步进而实 ...

  8. C++逆向分析----虚函数与多层继承

    虚函数 C++通过关键字virtual来将函数声明为一个虚函数.当一个类包含虚函数后编译器就会给类的实例对象增加一个虚表指针,所谓的虚表指针就是指向虚表的指针.虚表就是一张地址表,它包含了这个类中所有 ...

  9. base64stego 还不懂base64的隐写,详解15行代码带你领略

    网上写了好多关于xctf MISC新手篇的base64Stego隐写的教程,但大都不太清楚,基本上都是讲了一段隐写原理,直接上代码了.但是代码是这道题的关键,代码讲了如何解码这个隐写的完整流程,这次我 ...

  10. 面试遇到的坑CSS篇 1

    ------------恢复内容开始------------ 1.display: none和 visibility: hidden 代码 <style type="text/css& ...