Challenge: Implementing Positional Encoding
Sveip for å vise menyen
Task
Implement get_positional_encoding — a function that precomputes the full positional encoding matrix for a given sequence length and embedding dimension.
The function should:
- Accept
seq_lenandd_modelas arguments; - Return a tensor of shape
(seq_len, d_model)where each row is the encoding for one position; - Apply
sinto even indices andcosto odd indices using the sinusoidal formula from the previous chapter.
Run it with seq_len=10 and d_model=16, print the resulting tensor, and inspect how the values change across positions and dimensions. Then create a random embedding tensor of shape (10, 16) and add the positional encoding to it to confirm the shapes are compatible.
Takk for tilbakemeldingene dine!
Spør AI
Spør AI
Spør om hva du vil, eller prøv ett av de foreslåtte spørsmålene for å starte chatten vår
Challenge: Implementing Positional Encoding
Task
Implement get_positional_encoding — a function that precomputes the full positional encoding matrix for a given sequence length and embedding dimension.
The function should:
- Accept
seq_lenandd_modelas arguments; - Return a tensor of shape
(seq_len, d_model)where each row is the encoding for one position; - Apply
sinto even indices andcosto odd indices using the sinusoidal formula from the previous chapter.
Run it with seq_len=10 and d_model=16, print the resulting tensor, and inspect how the values change across positions and dimensions. Then create a random embedding tensor of shape (10, 16) and add the positional encoding to it to confirm the shapes are compatible.
Takk for tilbakemeldingene dine!
