Deep Learning with PyTorch

Training the model

Once the network is created, we can train the model using the same code as seen in the previous examples. The following is the code for training the model:

model = IMDBRnn(n_vocab,n_hidden,3,bs=32)model = model.cuda()optimizer = optim.Adam(model.parameters(),lr=1e-3)def fit(epoch,model,data_loader,phase='training',volatile=False):    if phase == 'training':        model.train()    if phase == 'validation':        model.eval()        volatile=True    running_loss = 0.0    running_correct = 0    for batch_idx , batch in enumerate(data_loader):        text , target = batch.text , batch.label        if is_cuda:            text,target = text.cuda(),target.cuda()                if phase == 'training':            optimizer.zero_grad()        output = model(text)        loss = F.nll_loss(output,target)         running_loss += F.nll_loss(output,target,size_average=False).data[0] ...