Deep convolutional models

* If You Click Mistakenly Then Please Refresh The Page To Get The Right Answers.

Deep convolutional models

TOTAL POINTS 10

1 point

[latex]n_H[/latex] and n_WnW increases, while n_C decreases
[latex]n_H[/latex] and n_WnW increases, while n_C also increases
[latex]n_H[/latex] and n_WnW decreases, while n_C also decreases
[latex]n_H[/latex] and n_WnW decrease, while n_C increases

1 point

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

1 point

True

False

1 point

True

False

1 point

and

z^{[l + 1]}

, respectively

z^{[l]}

and

a^{[l]}

, respectively

0 and

a^{[l]}

, respectively

a^{[l]}

and 0, respectively

1 point

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

L^2

skip connections in total.

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

1 point

4097

1 point

You can use a 1×1 convolutional layer to reduce

n_C

but not

n_H

n_W

You can use a pooling layer to reduce

n_H

n_W

, and

n_C

You can use a 1×1 convolutional layer to reduce

n_H

n_W

, and

n_C

You can use a pooling layer to reduce

n_H

n_W

, but not

n_C

1 point

A single inception block allows the network to use a combination of 1×1, 3×3, 5×5 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 1×1 convolutions to reduce the input data volume’s size before applying 3×3 and 5×5 convolutions.

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

1 point

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

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.

Deep convolutional models

Deep convolutional models >> Convolutional Neural Networks

Deep convolutional models

Leave a Comment Cancel reply

Deep convolutional models >> Convolutional Neural Networks

Deep convolutional models

Related Questions & Answers:

Leave a Comment Cancel reply