adamoudad

def myfunc(a: int = 1, b: str = "", c: list = []):
    pass

adamoudad

def myfunc(a, b, c):
    pass

config = {
    "a": 1,
    "b": 2,
    "c": 5
}

myfunc(**config)

adamoudad

def myfunc(a, b, c, d, e, f):
    # Do stuff
    pass

myfunc(a=1, b="foo", c=42, d=100, f="bar")

adamoudad

class EmptyClass:
    pass

def some_function():
    pass

adamoudad

for i in range(n):
    # Do stuff...
    if condition_is_met:
        break
else:
    # This will be executed only if break is never read.

adamoudad

for i in range(n):
    # Do stuff...
    if condition_is_met:
        break

adamoudad

for i in range(n):
    try:
        data = next(dataiter)
    except ValueError:
        continue
    # The code here is ignored if ValueError is raised in the "try" block
    # Otherwise, run the rest of the loop here ...

adamoudad

epoch_history["loss"].append(sum(batch_history["loss"]) / len(batch_history["loss"]))
epoch_history["accuracy"].append(sum(batch_history["accuracy"]) / len(batch_history["accuracy"]))
model.eval()
print("Validation...")
val_loss, val_accuracy = validate(model, valid_loader)
epoch_history["val_loss"].append(val_loss)
epoch_history["val_accuracy"].append(val_accuracy)
print(f"{epoch_history=}")

adamoudad

from tqdm import tqdm, trange
for i in trange(epochs, unit="epoch", desc="Train"):
    model.train()
    with tqdm(train_loader, desc="Train") as tbatch:
        for i, (samples, targets) in enumerate(tbatch):
            model.train()
            samples = samples.to(device).long()
            targets = targets.to(device)
            model.zero_grad()
            predictions, _ = model(samples.transpose(0, 1))

adamoudad

model = BiLSTM(input_dim, embedding_dim, hidden_dim)
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
criterion = nn.BCELoss().to(device)
optimizer = torch.optim.Adam(model.parameters())
model.to(device)
batch_history = {
    "loss": [],
    "accuracy": []
}
epoch_history = {