C5W1A2: Keep getting wrong values error

Course Q&A Deep Learning Specialization Sequence Models
1

Hello,
I keep getting the assertion error for wrong values in the sample/ sample test. The same error I guess propagates in the model() function. In the sample. I have added the bias terms, used random choice by using ravel() on probability vector. Also before next iteration i shuffle the probability vector.

sample_model_output
sample_model_output1259×490 28.2 KB

model_output
model_output903×624 13.9 KB

Can someone give a hint where I am going wrong

2

First, let’s talk about the sample function. This is the structure of the code given to you:

### START CODE HERE ###
    # Step 1: Create the a zero vector x that can be used as the one-hot vector
    # Representing the first character (initializing the sequence generation). (≈1 line)
    x = None
    # Step 1': Initialize a_prev as zeros (≈1 line)
    a_prev = None

    # Create an empty list of indices. This is the list which will contain the list of indices of the characters to generate (≈1 line)
    indices = []

    # idx is the index of the one-hot vector x that is set to 1
    # All other positions in x are zero.
    # Initialize idx to -1
    idx = None

    # Loop over time-steps t. At each time-step:
    # Sample a character from a probability distribution
    # And append its index (`idx`) to the list "indices".
    # You'll stop if you reach 50 characters
    # (which should be very unlikely with a well-trained model).
    # Setting the maximum number of characters helps with debugging and prevents infinite loops.
    counter = 0
    newline_character = char_to_ix['\n']

    while (idx != newline_character and counter != 50):

        # Step 2: Forward propagate x using the equations (1), (2) and (3)
        a = None
        z = None
        y = None

        # For grading purposes
        np.random.seed(counter + seed)

        # Step 3: Sample the index of a character within the vocabulary from the probability distribution y
        # (see additional hints above)
        idx = None

        # Append the index to "indices"
        indices.append(idx)

        # Step 4: Overwrite the input x with one that corresponds to the sampled index `idx`.
        # (see additional hints above)
        x = None
        x[idx] = None

        # Update "a_prev" to be "a"
        a_prev = None

        # for grading purposes
        seed += 1
        counter +=1

    ### END CODE HERE ###

Most of the steps are simple but how you are doing the step 3? Please explain it in words (without revealing your code).

3

In step 3, I used the 2D to 1D converted probability vector to sample a single random index from an ordered list of indices.

4

I think this is correct. I am sending you a private message to see your code.

5

To update others, for step 4, we have:

x = None
x[idx] = None

Think about it. All values of x are zero as we use np.zeros but we want to replace one value of zero with 1. And that value index is idx. So, how to do this?

If I want to replace any value of a particular index, I will do like this:
x[index] = replaced_value

1 Like
6

This was helpful. Thanks for explanation.

1 Like