التضمينات والسلاسل والأطوال

import torch
from torch import nn
from torch.nn.utils.rnn import pack_padded_sequence
embedding = nn.Embedding(4,2,padding_idx=0,dtype=torch.float64,device="cpu")
with torch.no_grad():
    embedding.weight.copy_(torch.tensor([[0.0,0.0],[1.0,2.0],[3.0,4.0],[5.0,6.0]],dtype=torch.float64,device="cpu"))
tokens = torch.tensor([[1,2,0],[3,0,0]],dtype=torch.long,device="cpu")
lengths = torch.tensor([2,1],dtype=torch.long,device="cpu")
values = embedding(tokens)
valid = torch.arange(tokens.shape[1],device="cpu")[None,:] < lengths[:,None]
pooled = values.masked_fill(~valid[:,:,None],0.0).sum(dim=1)/lengths[:,None]
packed = pack_padded_sequence(values,lengths,batch_first=True,enforce_sorted=False)
print("embedding shape", tuple(values.shape))
print("valid means", pooled.tolist())
print("packed data shape", tuple(packed.data.shape))

embedding shape (2, 3, 2)
valid means [[2.0, 3.0], [5.0, 6.0]]
packed data shape (3, 2)

تحدد صفوف التضمين الثابتة والأطوال الموجبة على CPU والقناع الصريح الأشكال والمتوسطات. لم ينفذ تضمين أو دالة حزم أو نموذج متكرر.

sequences = [[1.0,3.0,99.0],[5.0,99.0,99.0]]
lengths = [2,1]
assert all(0 < n <= len(row) for row,n in zip(sequences,lengths))
means = [sum(row[:n])/n for row,n in zip(sequences,lengths)]
flattened = [value for row,n in zip(sequences,lengths) for value in row[:n]]
print("valid means", means)
print("valid positions", len(flattened))
print("padding excluded", 99.0 not in flattened)

valid means [2.0, 5.0]
valid positions 3
padding excluded True

يفحص المرافق اختيار مواضع صالحة صراحة من قوائم؛ ولا يعيد ترتيب PackedSequence أو تدرجات التضمين أو حساب حالة متكررة.