Wie benutze ich mein ausgebildetes KI -Modell, um Vorhersagen zu treffen? ⇐ Python

[Anonymous]

Ich habe ein KI -Modell für die Klassifizierung mit mehreren Ebenen gemacht, es lief gut und alles, aber ich weiß nicht, wie man das trainierte Modell verwendet, um eine einzelne Vorhersage oder viele weitere zu machen.

Code: Select all

n_epochs = 200
batch_size = 5
batches_per_epoch = len(X_train) // batch_size

best_acc = 0
best_weights = None
train_loss_hist = []
train_acc_hist = []
test_loss_hist = []
test_acc_hist = []

# training loop
for epoch in range(n_epochs):

epoch_loss = []
epoch_acc = []
model.train()
with tqdm.trange(batches_per_epoch, unit="batch", mininterval=0) as bar:
bar.set_description(f"Epoch {epoch}")
for i in bar:
#take a batch
start = i * batch_size
X_batch = X_train[start:start+batch_size]
y_batch = y_train[start:start+batch_size]
# forward pass
y_pred = model(X_batch)
loss = loss_fn(y_pred, y_batch)
# backward pass
optimizer.zero_grad()
loss.backward()
# Update weights
optimizer.step()
# compute and store metrics
acc = (torch.argmax(y_pred, 1) == torch.argmax(y_batch, 1)).float().mean()
epoch_loss.append(float(loss))
epoch_acc.append(float(acc))
bar.set_postfix(
loss=float(loss),
acc=float(acc)
)
# set model in evaluation mode and run throught the test set
model.eval()
y_pred = model(X_test)
ce = loss_fn(y_pred, y_test)
acc = (torch.argmax(y_pred, 1) == torch.argmax(y_test, 1)).float().mean()
ce = float(ce)
acc = float(acc)
# save best model
train_loss_hist.append(np.mean(epoch_loss))
train_acc_hist.append(np.mean(epoch_acc))
test_loss_hist.append(ce)
test_acc_hist.append(acc)
if acc > best_acc:
best_acc = acc
best_weights = copy.deepcopy(model.state_dict())
print(f"Epoch {epoch} validation: Cross-entropy={ce:.2f}, Accuracy={acc*100:.1f}%")
< /code>
Ich habe Pytorch verwendet, um das Modell zu erstellen. Dies ist mein Modell: < /p>
class Multiclass(nn.Module):
def __init__(self):
super().__init__()
self.hidden = nn.Linear(4, 8)
self.act = nn.ReLU()
self.output = nn.Linear(8, 3)

def forward(self, x):
x = self.act(self.hidden(x))
x = self.output(x)
return x