Typo in chapter 15 multi_head_attention function

[tangbiao]

The calculation should use the projected vectors?

def multi_head_attention(query, key, value):
    head_outputs = []
    for i in range(num_heads):
        query = query_dense[i](query)
        key = key_dense[i](key)
        value = value_dense[i](value)
        scores = np.einsum("btd,bsd->bts", query, key)
        scores = softmax(scores / math.sqrt(head_dim), axis=-1)
        head_output = np.einsum("bts,bsd->btd", scores, key)
        head_outputs.append(head_output)
    outputs = ops.concatenate(head_outputs, axis=-1)
    return output_dense(outputs)