Deep convolutional models
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
answer(B) reason:池化层用于减少宽/高,卷积层填充也有避免图像速效太快的原因,但是不能至少only,卷积层也可以减少宽高,并不总是填充
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 L2 skip connections in total.
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
The skip-connections compute a complex non-linear function of the input to pass to a deeper layer in the network.
answer(B,C) reason:学习恒等函数通常是比较简单的;另外增加条约连接通常可以提高性能。
9.Which ones of the following statements on Inception Networks are true? (Check all that apply.)
Making an inception network deeper (by stacking more inception blocks together) should not hurt training set performance.
A single inception block allows the network to use a combination of 1x1, 3x3, 5x5 convolutions and pooling.
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.
Inception blocks usually use 1x1 convolutions to reduce the input data volume’s size before applying 3x3 and 5x5 convolutions.
answer(B,D) reason:Inception块通常组合1*1,3*3,5*5卷积和池化,常在通道上堆叠,1*1通常用来所见通道数量,减少参数量,成为Bottleneck layer;Inception块并非堆叠的越多越好,C课程没有讲到。
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.
Parameters trained for one computer vision task are often useful as pretraining for other computer vision tasks.
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.
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.
answer(A,C) reason:D说法不对,训练的模型并不一定能适合数据增强,而B中说过,竞赛中使用较多,但是实际部署中会采用很少。