Deep Learning Academy · 课时

打包序列并处理填充

高效训练不同长度的序列

打包序列并处理填充 是 CoddyKit 上的免费 Deep Learning Academy 课时。这是第 4 节课，共 4 节。你可以在下方免费阅读本课时的完整内容 — 然后在浏览器中使用内置代码编辑器和全天候 AI 导师进行实践。这是 Deep Learning Academy 学习路径的一部分，你的进度在网页和 CoddyKit 应用中同步。 Deep Learning Academy 课程共包含 4 节课。

本课时的部分内容尚未翻译，以英文显示。

Batches Want Rectangles

To process many sequences at once, a batch must be a neat rectangle. But real sentences have different lengths, so they don't line up.

Padding to a Common Length

The fix is padding: add filler tokens, usually zeros, to short sequences so every row in the batch is the same length.

pad_sequence Helper

PyTorch's pad_sequence stacks a list of variable-length tensors into one padded batch in a single call.

from torch.nn.utils.rnn import pad_sequence
batch = pad_sequence(seqs, batch_first=True)

Padding Wastes Compute

Those filler tokens are fake. If the RNN processes them anyway, it burns compute and can let the padding pollute the hidden state.

Track the Real Lengths

Before padding, record each sequence's true length. You'll hand these lengths to PyTorch so it knows where the real data ends.

lengths = [len(s) for s in seqs]

Packing the Batch

pack_padded_sequence turns the padded batch plus lengths into a compact form the RNN can run without touching the padding.

packed = pack_padded_sequence(batch, lengths, batch_first=True)

Run the RNN on Packed Data

Feed the packed object straight into nn.LSTM or nn.GRU. The cell skips padded steps, so memory stays clean and clear.

out_packed, h_n = lstm(packed)

Unpack the Output

To read per-step outputs again, call pad_packed_sequence to restore the rectangular padded shape after the RNN finishes.

out, lengths = pad_packed_sequence(out_packed, batch_first=True)

Sort by Length

Classic packing wants sequences sorted longest first. Set enforce_sorted to False and PyTorch handles unsorted batches for you.

Mask the Loss

Even with packing, ignore padded positions when scoring. A mask or ignore_index keeps fake tokens out of the loss.

loss_fn = nn.CrossEntropyLoss(ignore_index=PAD_ID)

Wire It Into the DataLoader

Do the padding inside a custom collate_fn so every batch arrives already padded, with lengths ready for packing.

Quick Check

Why pack a padded batch before feeding it to an RNN?

Recap

Pad to align a batch, track true lengths, then pack so the RNN ignores filler. Mask padded tokens in the loss too. ✅

常见问题解答

「打包序列并处理填充」课时是免费的吗？

是的 — 「打包序列并处理填充」的完整文本可在网页上免费阅读。要进行交互式练习（内置代码编辑器和全天候 AI 导师）并解锁 Deep Learning Academy 课程的其余内容，请升级到 CoddyKit PRO。 Deep Learning Academy 课程共包含 4 节课。

「打包序列并处理填充」这节课中我会学到什么？

高效训练不同长度的序列你通过在浏览器中直接运行的动手代码来练习 Deep Learning Academy，全天候 AI 导师会在你学习这节课的过程中回答你的问题。

学习 Deep Learning Academy 需要有经验吗？

无需任何先前经验。CoddyKit 上的 Deep Learning Academy 课程适合初学者到高级学习者，你可以从这里开始或从头开始，按照自己的节奏学习。这是第 4 节课，共 4 节。

「打包序列并处理填充」课时需要多长时间？

大多数 CoddyKit 课程大约需要 5–10 分钟。每节课都很精短且互动，所以你能稳步进步，并在网页和应用中从离开的地方继续。

我能在这节 Deep Learning Academy 课中编写并运行代码吗？

能。每节 Deep Learning Academy 课都包含内置代码编辑器，你可以在浏览器中直接编写并运行真实代码，并获得即时 AI 反馈 — 无需本地设置。

此课程中的所有课时

← 返回 Deep Learning Academy