train_ALL_CNN_1.py 文件源码

def eval(data_iter, model, args, scheduler):
    model.eval()
    corrects, avg_loss = 0, 0
    for batch in data_iter:
        feature, target = batch.text, batch.label
        feature.data.t_(), target.data.sub_(1)  # batch first, index align
        if args.cuda:
            feature, target = feature.cuda(), feature.cuda()

        logit = model(feature)
        loss = F.cross_entropy(logit, target, size_average=False)
        # scheduler.step(loss.data[0])
        # if args.init_clip_max_norm is not None:
        #     # print("aaaa {} ".format(args.init_clip_max_norm))
        #     utils.clip_grad_norm(model.parameters(), max_norm=args.init_clip_max_norm)

        avg_loss += loss.data[0]
        corrects += (torch.max(logit, 1)[1].view(target.size()).data == target.data).sum()

    size = len(data_iter.dataset)
    avg_loss = loss.data[0]/size
    # accuracy = float(corrects)/size * 100.0
    accuracy = 100.0 * corrects/size
    model.train()
    print('\nEvaluation - loss: {:.6f}  acc: {:.4f}%({}/{}) \n'.format(avg_loss,
                                                                       accuracy,
                                                                       corrects,
                                                                       size))