Deep Learning Academy · 课时

训练时跟踪准确率

将预测结果转换为分数

训练时跟踪准确率 是 CoddyKit 上的免费 Deep Learning Academy 课时。这是第 3 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。

Loss Alone Lies a Little

A falling loss feels good, but it is abstract. To know if your model is truly useful you also want accuracy, the share of predictions it gets right. 🎯

From Logits to a Choice

Your model outputs raw scores per class. To pick a prediction you take the index of the largest score with argmax along the class dimension.

preds = pred.argmax(dim=1)

Compare to the Truth

Now compare each predicted class to the real label. The result is a boolean tensor where True marks every example the model got right.

correct = preds == y

Count the Wins

Booleans add up like ones and zeros, so summing the matches gives a count of correct predictions in this batch.

num_correct = correct.sum().item()

Turn Count Into a Rate

Divide correct predictions by the batch size and you get accuracy, a number from zero to one that is easy to read as a percentage.

acc = num_correct / y.size(0)

Accumulate Across Batches

Per-batch accuracy is noisy, so keep running totals of correct and seen examples. Their ratio gives a stable epoch accuracy.

total_correct += num_correct
total_seen += y.size(0)

Report Each Epoch

At the end of an epoch compute the overall rate and print it beside the loss. Now you see both how confident and how correct the model is.

epoch_acc = total_correct / total_seen

Keep Metrics off the Graph

When you only measure, wrap scoring in no_grad. It stops PyTorch from tracking operations you never plan to backpropagate, saving memory.

with torch.no_grad():
    preds = model(x).argmax(dim=1)

Accuracy Is Not Enough Alone

On imbalanced data accuracy can fool you: always guessing the common class scores high yet learns nothing. Pair it with loss and other metrics.

Watch the Trend

One epoch's number means little; the trend is everything. Rising accuracy with falling loss is the clear sign your training is on track.

A Window Into Learning

Tracking accuracy turns training from a black box into something you can watch. Each epoch you get honest feedback on real progress.

Quick Check

How do you turn class scores into a single predicted label?

Recap

You learned to track accuracy: argmax the scores, compare to labels, count correct, and divide. Watch the trend alongside loss. 🎉

常见问题解答

「训练时跟踪准确率」课时是免费的吗？

是的 — 「训练时跟踪准确率」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。

「训练时跟踪准确率」这节课中我会学到什么？

将预测结果转换为分数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 3 节课，共 4 节。

「训练时跟踪准确率」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