深度学习Course4第二周Deep Convolutional Models习题整理

Deep Convolutional Models

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

2. In LeNet - 5 we can see that as we get into deeper networks the number of channels increases while the height and width of the volume decreases. True/False?

3. 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.

解析：Resnets are here to help us train very deep neural networks.

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

• 
• 0 and, respectively
• 0 and, respectively
• and, respectively

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

• A ResNet with L layers would have on the order of
• 
  

This should not be selected
This is false, skip connections make it easy for the model to learn an identity mapping, not a complex non-linear function.

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

• You can use a 1x1 convolutional layer to reducebut notand.

Yes, a 1x1 convolutional layer with a small number of filters is going to reduce nCnC but will keep the dimensions nHnH and nWnW

• You can use a 2D pooling layer to reduceand, but not.
• You can use a 2D pooling layer to reduceand, and.
• You can use a 1x1 convolutional layer to reduce,, and.

7. Which of the following are true about the inception Network? (Check all that apply)

The use of several different types of layers and stacking up the results to get a single volume is at the heart of the inception network.

That is why the bottleneck layer is used to reduce the computational cost.

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

Using multiple crops at test time is not common.

9. Which of the following are true about Depth wise-separable convolutions? (Choose all that apply)

• The result has always the same number of channels
• 
  
• 
  

this combination is what we call depth wise separable convolutions.

Yes, as seen in the lectures the use of the depthwise and pointwise convolution reduces the computational cost significantly.

11. Fill in the missing dimensions shown in the image below (marked W, Y, Z).