吴恩达深度学习笔记 course4 week2 测验

答案仅供参考,非标准答案,欢迎交流html

Which of the following do you typically see as you move to deeper layers in a ConvNet?react

$n_HnH and n_WnW increases, while n_CnC decreases$ 网络

$n_HnH and n_WnW increases, while n_CnC also increases$ app

$n_HnH and n_WnW decrease, while n_CnC increases √$ dom

$n_HnH and n_WnW decreases, while n_CnC also decreases$ ide

第 2 个问题

1
point

2. 第 2 个问题

Which of the following do you typically see in a ConvNet? (Check all that apply.)函数

Multiple CONV layers followed by a POOL layer学习

Multiple POOL layers followed by a CONV layerui

FC layers in the last few layersthis

FC layers in the first few layers

第 3 个问题

1
point

3. 第 3 个问题

In order to be able to build very deep networks, we usually only use pooling layers to downsize the height/width of the activation volumes while convolutions are used with “valid” padding. Otherwise, we would downsize the input of the model too quickly.

True

False √

第 4 个问题

1
point

4. 第 4 个问题

Training a deeper network (for example, adding additional layers to the network) allows the network to fit more complex functions and thus almost always results in lower training error. For this question, assume we’re referring to “plain” networks.

True

False √

第 5 个问题

1
point

5. 第 5 个问题

The following equation captures the computation in a ResNet block. What goes into the two blanks above?

0 and $a^{[l]}a[l], respectively$

$z^{[l+1]}z[l+1], respectively$

$z^{[l]}z[l] and a^{[l]}a[l], respectively$

$a^{[l]}a[l] and 0, respectively √$

第 6 个问题

1
point

6. 第 6 个问题

Which ones of the following statements on Residual Networks are true? (Check all that apply.)

Using a skip-connection helps the gradient to backpropagate and thus helps you to train deeper networks

The skip-connection makes it easy for the network to learn an identity mapping between the input and the output within the ResNet block.

The skip-connections compute a complex non-linear function of the input to pass to a deeper layer in the network.

A ResNet with L layers would have on the order of $L^2L2 skip connections in total.$

第 7 个问题

1
point

7. 第 7 个问题

Suppose you have an input volume of dimension 64x64x16. How many parameters would a single 1x1 convolutional filter have (including the bias)?

17 √

4097

2

1

第 8 个问题

1
point

8. 第 8 个问题

Suppose you have an input volume of dimension $n_HnH x n_WnW x n_CnC. Which of the following statements you agree with? (Assume that “1x1 convolutional layer” below always uses a stride of 1 and no padding.)$

You can use a 1x1 convolutional layer to reduce $n_HnH, n_WnW, and n_CnC.$

You can use a 1x1 convolutional layer to reduce $n_CnC but not n_HnH, n_WnW.$

You can use a pooling layer to reduce $n_HnH, n_WnW, and n_CnC.$

You can use a pooling layer to reduce $n_HnH, n_WnW, but not n_CnC.$

第 9 个问题

1
point

9. 第 9 个问题

Which ones of the following statements on Inception Networks are true? (Check all that apply.)

Inception blocks usually use 1x1 convolutions to reduce the input data volume’s size before applying 3x3 and 5x5 convolutions.

Inception networks incorporates a variety of network architectures (similar to dropout, which randomly chooses a network architecture on each step) and thus has a similar regularizing effect as dropout.

A single inception block allows the network to use a combination of 1x1, 3x3, 5x5 convolutions and pooling.

Making an inception network deeper (by stacking more inception blocks together) should not hurt training set performance.

第 10 个问题

1
point

10. 第 10 个问题

Which of the following are common reasons for using open-source implementations of ConvNets (both the model and/or weights)? Check all that apply.

Parameters trained for one computer vision task are often useful as pretraining for other computer vision tasks.

It is a convenient way to get working an implementation of a complex ConvNet architecture.

A model trained for one computer vision task can usually be used to perform data augmentation even for a different computer vision task.

The same techniques for winning computer vision competitions, such as using multiple crops at test time, are widely used in practical deployments (or production system deployments) of ConvNets.

中文版源自:https://blog.csdn.net/u013733326/article/details/80166080

--------------------------------------------------------------------中文版---------------------------------------------------------------------

1. Question 1

在典型的卷积神经网络中，随着网络的深度增长，你能看到的现象是？

【】 $n_{H}$
【】 $n_{H}$
【】 $n_{H}$
【★】 $n_{H}$

2. Question 2

在典型的卷积神经网络中，你能看到的是？

【★】多个卷积层后面跟着的是一个池化层。
【】多个池化层后面跟着的是一个卷积层。
【★】全链接层（FC）位于最后的几层。
【】全链接层（FC）位于开始的几层。

3. Question 3

为了构建一个很是深的网络，咱们常常在卷积层使用“valid”的填充，只使用池化层来缩小激活值的宽/高度，不然的话就会使得输入迅速的变小。

【】 True
【★】 False

博主注：咱们常常使用“SAME”的padding方式。

4. Question 4

咱们使用普通的网络结构来训练一个很深的网络，要使得网络适应一个很复杂的功能（好比增长层数)，总会有更低的训练偏差。

【】 True
【★】 False

博主注：在没有残差的普通神经网络中，理论上是偏差愈来愈低的，可是其实是随着网络层数的加深，先减少再增长；在有残差的ResNet中，即便网络再深，训练偏差都会随着网络层数的加深逐渐减少。

5. Question 5

下面计算残差(ResNet)块的公式中，横线上应该分别填什么？

a [l + 2] = g (W [l + 2] g (W [l + 1] a l + b [l + 1]) +

【】分别是 $0$
【★】分别是 $a^{[l]}$
【】分别是 $z^{[l]}$
【】分别是 $0$

博主注：推导一下公式就行了。

a [l + 2] = g (z [l + 2] + a [l]) = g

6. Question 6

关于残差网络下面哪一个（些）说法是正确的？

【】使用跳越链接可以对反向传播的梯度降低有益且可以帮你对更深的网络进行训练。
【★】跳跃链接计算输入的复杂的非线性函数以传递到网络中的更深层。
【】有L层的残差网络一共有 $L^{2}$
【★】跳跃链接可以使得网络轻松地学习残差块类的输入输出间的身份映射。

博主注：请参考这里

7. Question 7

假设你的输入的维度为64x64x16，单个1x1的卷积过滤器含有多少个参数（包括误差）？

【】 2
【★】 17
【】 4097
【】 1

8. Question 8

假设你有一个维度为 $n_{H} \times n_{W} \times n_{C}$

【★】你可以使用1x1的卷积层来减小 $n_{C}$
【★】你能够使用池化层减小 $n_{H}$
【】你能够使用一个1x1的卷积层来减小 $n_{H}$
【】你能够使用池化层减小 $n_{H}$

9. Question 9

关于 Inception 网络下面哪些说法是正确的

【】 Inception 网络包含了各类网络的体系结构（相似于随机删除节点模式，它会在每一步中随机选择网络的结构），所以它具备随机删除节点的正则化效应。
【★】 Inception 块一般使用1x1的卷积来减小输入卷积的大小，而后再使用3x3和5x5的卷积。
【★】一个inception 块容许网络使用1x1, 3x3, 5x5 的和卷积个池化层的组合。
【】经过叠加inception块的方式让inception 网络更深不会损害训练集的表现。

10. Question 10

下面哪些是使用卷积网络的开源实现（包含模型/权值）的常见缘由？

【】为一个计算机视觉任务训练的模型一般能够用来数据扩充，即便对于不一样的计算机视觉任务也是如此。
【★】为一个计算机视觉任务训练的参数一般对其余计算机视觉任务的预训练是有用的。
【】使用得到计算机视觉竞赛奖项的相同的技术，普遍应用于实际部署。
【★】使用开源实现能够很简单的来实现复杂的卷积结构。