带验证的周期循环
每次遍历数据后进行评估
带验证的周期循环 是 CoddyKit 上的免费 Deep Learning Academy 课时。 这是第 2 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。
What an Epoch Means
One epoch is a single full pass over your entire training set. Real training repeats this pass many times so the model keeps improving.
The Outer Loop
Wrap your whole routine in a loop over epochs. Each turn of this outer loop trains once and then checks progress on validation.
for epoch in range(num_epochs):
train_one_epoch()
validate()The Inner Training Loop
Inside an epoch you loop over batches from the DataLoader. Each batch runs the familiar forward, loss, backward, step rhythm.
for x, y in train_loader:
optimizer.zero_grad()
loss = loss_fn(model(x), y)
loss.backward()
optimizer.step()Switch to Train Mode
Before training a pass, call model.train(). It turns on layers like dropout and batch norm that should behave differently while learning.
model.train()Switch to Eval Mode
Before validating, call model.eval(). This freezes dropout and uses running batch-norm stats so your scores are steady and fair.
model.eval()No Gradients While Validating
Validation only reads the model, so wrap it in torch.no_grad(). Skipping the graph saves memory and runs noticeably faster.
with torch.no_grad():
for x, y in val_loader:
out = model(x)Track the Running Loss
Add up each batch's loss across the epoch, then divide by the count. This average loss is one clean number to compare epoch to epoch.
total += loss.item() * x.size(0)
epoch_loss = total / len(loader.dataset)Measure Validation Loss
Compute the same average on the validation set. This validation loss reveals how well the model generalizes beyond what it trained on.
Print Progress Each Epoch
Log both losses every epoch so you can watch the curves. Seeing the trend live makes overfitting easy to catch the moment it starts.
print(epoch, train_loss, val_loss)Read the Two Curves
Healthy training shows both losses falling. When validation loss starts climbing while training keeps dropping, the model is beginning to overfit.
Don't Backward on Validation
A frequent bug is calling backward() during validation. Never update weights from val data, or you contaminate your honest measurement.
Quick Check
What should you call right before running the validation pass?
Recap
Each epoch trains in train mode, then validates in eval mode under no_grad. Track both losses and watch the gap to catch overfitting early. 📈
常见问题解答
「带验证的周期循环」课时是免费的吗？
是的 — 「带验证的周期循环」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。
「带验证的周期循环」这节课中我会学到什么？
每次遍历数据后进行评估 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 2 节课，共 4 节。
「带验证的周期循环」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。