Course 5 Week 4 Assignment Exercise 8 code comment typo?

Course Q&A Deep Learning Specialization Sequence Models
1

This concerns a possible typo?
“”""
Forward pass for the entire Transformer
Arguments:
input_sentence – Tensor of shape (batch_size, input_seq_len, fully_connected_dim)
An array of the indexes of the words in the input sentence
output_sentence – Tensor of shape (batch_size, target_seq_len, fully_connected_dim)
An array of the indexes of the words in the output sentence
“”""
I thought the input should be 2-D [batch, max_sentence_length], why is fully_connected_dim involved in input_sentence. I also read the unit_test and

sentence_lang_a = np.array([[2, 1, 4, 3, 0]])

the argument passed as input_sentence is 2-D and whats expected.

Is this a typo?

1 Like
2

Hi,

Did you find an answer? I was wondering the same… I think the input sentence should have dims (batch_size, input_seq_len) for instances
Hi, how are you => [2, 3, 4, 5]
Hello, what is your name => [6, 7, 8, 9, 1]

So the dims are: 2 X 5… is not it?