Questions about Week 1 assignment 2

Course Q&A Deep Learning Specialization Sequence Models
1

I am struggling in Exercise 4 - model in Week 1 assignment 2. Does anyone know what’s wrong with my code? The error shows TypeError: ‘NoneType’ object is not subscriptable

{mentor edit: code removed}

1 Like
2

In “idx = …” , don’t use j + 1. Just use “j % len(examples)”

3

Not working. Should be something else. I have passed Q1-Q3, and the issues should happen in Q4. Do you have any ideas?

The following are the error message:

TypeError Traceback (most recent call last)
in
----> 1 parameters, last_name = model(data.split("\n"), ix_to_char, char_to_ix, 22001, verbose = True)
2
3 assert last_name == ‘Trodonosaurus\n’, “Wrong expected output”
4 print("\033[92mAll tests passed!")

in model(data_x, ix_to_char, char_to_ix, num_iterations, n_a, dino_names, vocab_size, verbose)
61 # Perform one optimization step: Forward-prop → Backward-prop → Clip → Update parameters
62 # Choose a learning rate of 0.01
—> 63 curr_loss, gradients, a_prev = optimize(X, Y, a_prev, parameters, learning_rate = 0.01)
64
65 ### END CODE HERE ###

in optimize(X, Y, a_prev, parameters, learning_rate)
32
33 # Forward propagate through time (≈1 line)
—> 34 loss, cache = rnn_forward(X, Y, a_prev, parameters)
35
36 # Backpropagate through time (≈1 line)

~/work/W1A2/utils.py in rnn_forward(X, Y, a0, parameters, vocab_size)
100
101 # Update the loss by substracting the cross-entropy term of this time-step from it.
→ 102 loss -= np.log(y_hat[t][Y[t],0])
103
104 cache = (y_hat, a, x)

TypeError: ‘NoneType’ object is not subscriptable

4

That doesn’t look right. It’s supposed to multiply y-hat and y, but seems to be missing a multiplication operator.

Update: Well, that’s not the problem, because that’s from one of the provided utility functions (rnn_forward). I don’t get how it works though.

5

This one line code is in the rnn_forward function which is provided by the assignment. Do you mean there is something wrong with the prebuilt function?

6

But that’s the line of code that is causing the error. It’s in rnn_forward(), which is called from your optimize() function.

So maybe in optimize(), you’re passing an incorrect argument to rnn_forward().

7

Could you check the optimize for me, please? I cannot identify the error since I have passed the test for optimize.

{mentor edit: code removed}

return loss, gradients, a[len(X)-1]
9

{mentor edit - text removed}

10

I don’t see any problems there.

11

Back in the model() function, maybe it doesn’t like your code for setting the Y value.
Try this instead:
Y = X[1:]
Y.append(ix_newline)

They should be the same, but maybe they aren’t.

1 Like
12

It works. Thanks so much.