I made an AI model for multiclass classification, it ran good and all, but I don't know how to use the trained model to make a single prediction or maybe many more. I know that it may be in the piece of code below, but I can't figure it out. 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}%") I used pytorch to build the model. This is my model: 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 Continue reading...
