Notebook 4 - one s too many in the fit function before the random sampling section

[waterboy96]

Notebook 4 - one s too many in the fit function before the random sampling section

[PiotrCzapla]

Out of curiosity do you have a minimal example maybe that shows the issue?

[waterboy96]

Hi @PiotrCzapla

Right before the random sampling section we define fit as:

def fit():
    for epoch in range(epochs):
        for xb,yb in train_dl:
            pred = model(xb)
            loss = loss_func(pred, yb)
            loss.backward()
            opt.step()
            opt.zero_grad()
        report(loss, preds, yb)

We define pred on line 4 in our loop, but we call report on preds in the last line. In most of the other fit functions it assigns the prediction to preds correctly such as the first fit function in the same notebook:

def fit():
    for epoch in range(epochs):
        for i in range(0, n, bs):
            s = slice(i, min(n,i+bs))
            xb,yb = x_train[s],y_train[s]
            preds = model(xb)
            loss = loss_func(preds, yb)
            loss.backward()
            with torch.no_grad():
                for p in model.parameters(): p -= p.grad * lr
                model.zero_grad()
        report(loss, preds, yb)

[PiotrCzapla]

I see what you mean, it is in 04_minibatch_training just before jupyter chapter "Random sampling". :) I made a fix #19 with github.dev it is super easy nowadays to make such changes directly in the browser even to notebooks ! :)

Thank you.

[waterboy96]

I did not know that. Thanks, I will try it next time!