吴恩达 Convolutional Neural Network

1.Which of the following do you typically see as you move to deeper layers in a ConvNet?
nH and nW decreases, while nC also decreases
nH and nW increases, while nC decreases
nH and nW decrease, while nC increases
nH and nW increases, while nC also increases
随着网络的加深，通道数越来越多，feature map size 变小
2.Which of the following do you typically see in a ConvNet? (Check all that apply.)
Multiple CONV layers followed by a POOL layer
Multiple POOL layers followed by a CONV layer
FC layers in the last few layers
FC layers in the first few layers

3.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
这题为false，第一次做错了，这里错在的是valid padding ,一般用的是same padding（1.the most commonly used padding mode in CNN is "same" padding,one of the advantage over the other padding modes is that same padding preserves the height and width of the input images or tensors,which make designing a network architecture more convenient.2.one of the disadvantage of the valid padding versus same padding ,for example,is that the volume of the tensors would decrease substantially in neural networks with many layers,which can be dangerous to the network performance.3.in practice,it is recommended that you preserve the spatial size using same padding for the convolutional layers and decrease the spatial size via pooling layers instead.）

4.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
这题也是false，自己做错的原因是题目看错了，人家的本意是即使是plain 的network 随着网络的加深 trian error也降低，这明显就是错的。
5.

6. Which ones of the following statements on Residual Networks are true? (Check all that apply.)
   The skip-connection makes it easy for the network to learn an identity mapping between the input and the output within the ResNet block.
   Using a skip-connection helps the gradient to backpropagate and thus helps you to train deeper networks
   A ResNet with L layers would have on the order of L2 skip connections in total. 不是L的平方，应该是L除以2.
   The skip-connections compute a complex non-linear function of the input to pass to a deeper layer in the network.

7. Suppose you have an input volume of dimension 64x64x16. How many parameters would a single 1x1 convolutional filter have (including the bias)?
   2
   17
   4097
   1
   1x1x16 +bias 1 = 17

8.Suppose you have an input volume of dimension nH x nW x nC. 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 nH, nW, and nC.
You can use a pooling layer to reduce nH, nW, but not nC.
You can use a 1x1 convolutional layer to reduce nC but not nH, nW.
You can use a pooling layer to reduce nH, nW, and nC.

9.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.
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.错在自己对should not 的理解上，这里不是不应该，就是not 的意思。只有resnet 可以说随着网络的加深，train error 一直下降 其他都是先降后升
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.
自己之前选了前三个，是错的 所以选1 2 试一下 确实是1 2

10. Which of the following are common reasons for using open-source implementations of ConvNets (both the model and/or weights)? Check all that apply.
    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.在paper之类的会用，在实际应用场景中用的少，毕竟加大了很多计算量然后运行时间也变多了，就是带来的性能提升比其计算代价小，所以工程上不用。
    Parameters trained for one computer vision task are often useful as pretraining for other computer vision tasks.
    选了 1 3 4 是错的 这次选 3 4 还是错的 其实是1 4 3为什么是错的，估计是因为这样太耗费资源了。
    错误 ：3.4.9.10

有疑问的时候去论坛搜索，比直接Google更容易找到答案，要是没有人问过，自己问，毕竟有助教。感觉论坛大法好。可以很好的解答自己的疑惑。