herokillerever / coursera-deep-learning Goto Github PK

Hi
I think the answer should be 151516. Since it first apply a pooling with stride of 2, it becomes 161616, then a filter with size 2, then (16-2)+1 * (16-2)+1 *16. What do you think?

The answer to the 8th question seems to be wrong.

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 nC but not nH, nW.

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 pooling layer to reduce nH, nW, and nC.

The second option regarding pooling layers has been highlighted with the wrong answer:
It should be: You can use a pooling layer to reduce nH, nW, but not nC.
and not: You can use a pooling layer to reduce nH, nW, and nC.

only init_zero and sigmoid are correct.
Please correct them ASAP

It is true.

the answer of 8 will be
: 1/9
and
the answer of 9 will be: 5

Change answer to True
https://towardsdatascience.com/understanding-and-calculating-the-number-of-parameters-in-convolution-neural-networks-cnns-fc88790d530d

many ans were wrong
change the values

The answer to question 10 of the 4th week's quiz in "Convolutional Neural Networks" should be 30 * 30 * 30 * 32

where can i find the dataset for programming assignment 1 (logistic regression one)

Please help me rectify this error

3: does not need bh and bw
8: 1/9

Question No 9:
In lecture, we talked about “parameter sharing” as a benefit of using convolutional networks. Which of the following statements about parameter sharing in ConvNets are true? (Check all that apply.)

1. It allows parameters learned for one task to be shared even for a different task (transfer learning).
2. It reduces the total number of parameters, thus reducing overfitting.
3. It allows gradient descent to set many of the parameters to zero, thus making the connections sparse.
4. It allows a feature detector to be used in multiple locations throughout the whole input image/input volume.

The answer should be:

• It reduces the total number of parameters, thus reducing overfitting.

• It allows a feature detector to be used in multiple locations throughout the whole input image/input volume.

In the verify graded function under the Facial Recognition assignment notebook of the CNNs course, one of the graded code fields in not filled in:

 if None:
        print("It's " + str(identity) + ", welcome home!")
        door_open = True
    else:
        print("It's not " + str(identity) + ", please go away")
        door_open = False

The None should be replaced with

    if dist<0.7
        print("It's " + str(identity) + ", welcome home!")
        door_open = True
    else:
        print("It's not " + str(identity) + ", please go away")
        door_open = False```

I'm believe the original data set itself is not available, Could you provide it? One simply can not go through the notebook without it. Thanks in advance