吳恩達深度學習筆記 course4 week2 測驗

答案僅供參考,非標準答案,歡迎交流html

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

$n_HnH and n_WnW increases, while n_CnC decreases$ 網絡

$n_HnH and n_WnW increases, while n_CnC also increases$ 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 個問題

1
point

2. 第 2 個問題

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

Multiple CONV layers followed by a POOL layer學習

Multiple POOL layers followed by a CONV layerui

FC layers in the last few layersthis

FC layers in the first few layers

第 3 個問題

1
point

3. 第 3 個問題

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 個問題

1
point

4. 第 4 個問題

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 個問題

1
point

5. 第 5 個問題

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 個問題

1
point

6. 第 6 個問題

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 個問題

1
point

7. 第 7 個問題

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 個問題

1
point

8. 第 8 個問題

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 個問題

1
point

9. 第 9 個問題

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 個問題

1
point

10. 第 10 個問題

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

在典型的卷積神經網絡中，隨着網絡的深度增長，你能看到的現象是？

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

2. Question 2

在典型的卷積神經網絡中，你能看到的是？

【★】多個卷積層後面跟着的是一個池化層。
【】多個池化層後面跟着的是一個卷積層。
【★】全鏈接層（FC）位於最後的幾層。
【】全鏈接層（FC）位於開始的幾層。

3. Question 3

爲了構建一個很是深的網絡，咱們常常在卷積層使用「valid」的填充，只使用池化層來縮小激活值的寬/高度，不然的話就會使得輸入迅速的變小。

【】 True
【★】 False

博主注：咱們常常使用「SAME」的padding方式。

4. Question 4

咱們使用普通的網絡結構來訓練一個很深的網絡，要使得網絡適應一個很複雜的功能（好比增長層數)，總會有更低的訓練偏差。

【】 True
【★】 False

博主注：在沒有殘差的普通神經網絡中，理論上是偏差愈來愈低的，可是其實是隨着網絡層數的加深，先減少再增長；在有殘差的ResNet中，即便網絡再深，訓練偏差都會隨着網絡層數的加深逐漸減少。

5. Question 5

下面計算殘差(ResNet)塊的公式中，橫線上應該分別填什麼？

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

【】分別是 $0$
【★】分別是 $a^{[l]}$
【】分別是 $z^{[l]}$
【】分別是 $0$

博主注：推導一下公式就行了。

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

6. Question 6

關於殘差網絡下面哪一個（些）說法是正確的？

【】使用跳越鏈接可以對反向傳播的梯度降低有益且可以幫你對更深的網絡進行訓練。
【★】跳躍鏈接計算輸入的複雜的非線性函數以傳遞到網絡中的更深層。
【】有L層的殘差網絡一共有 $L^{2}$
【★】跳躍鏈接可以使得網絡輕鬆地學習殘差塊類的輸入輸出間的身份映射。

博主注：請參考這裏

7. Question 7

假設你的輸入的維度爲64x64x16，單個1x1的卷積過濾器含有多少個參數（包括誤差）？

【】 2
【★】 17
【】 4097
【】 1

8. Question 8

假設你有一個維度爲 $n_{H} \times n_{W} \times n_{C}$

【★】你可以使用1x1的卷積層來減小 $n_{C}$
【★】你能夠使用池化層減小 $n_{H}$
【】你能夠使用一個1x1的卷積層來減小 $n_{H}$
【】你能夠使用池化層減小 $n_{H}$

9. Question 9

關於 Inception 網絡下面哪些說法是正確的

【】 Inception 網絡包含了各類網絡的體系結構（相似於隨機刪除節點模式，它會在每一步中隨機選擇網絡的結構），所以它具備隨機刪除節點的正則化效應。
【★】 Inception 塊一般使用1x1的卷積來減小輸入卷積的大小，而後再使用3x3和5x5的卷積。
【★】一個inception 塊容許網絡使用1x1, 3x3, 5x5 的和卷積個池化層的組合。
【】經過疊加inception塊的方式讓inception 網絡更深不會損害訓練集的表現。

10. Question 10

下面哪些是使用卷積網絡的開源實現（包含模型/權值）的常見緣由？

【】爲一個計算機視覺任務訓練的模型一般能夠用來數據擴充，即便對於不一樣的計算機視覺任務也是如此。
【★】爲一個計算機視覺任務訓練的參數一般對其餘計算機視覺任務的預訓練是有用的。
【】使用得到計算機視覺競賽獎項的相同的技術，普遍應用於實際部署。
【★】使用開源實現能夠很簡單的來實現複雜的卷積結構。