Python utils.loadData() Examples

def trainBatch(net, criterion, optimizer):
    data = train_iter.next()
    cpu_images, cpu_texts = data
    batch_size = cpu_images.size(0)
    utils.loadData(image, cpu_images)
    t, l = converter.encode(cpu_texts)
    utils.loadData(text, t)
    utils.loadData(length, l)

    preds = crnn(image)
    preds_size = Variable(torch.IntTensor([preds.size(0)] * batch_size))
    cost = criterion(preds, text, preds_size, length) / batch_size
    crnn.zero_grad()
    cost.backward()
    optimizer.step()
    return cost 

def trainBatch(net, optimizer):
    data = train_iter.next()
    cpu_images, cpu_texts = data
    batch_size = cpu_images.size(0)
    utils.loadData(image, cpu_images)
    t, l = converter.encode(cpu_texts)
    utils.loadData(text, t)
    utils.loadData(length, l)

    preds = crnn(image)
    preds_size = Variable(torch.IntTensor([preds.size(0)] * batch_size))
    H, cost = seg_ctc_ent_cost(preds, text, preds_size, length, uni_rate=opt.uni_rate)
    h_cost = (1-opt.h_rate)*cost-opt.h_rate*H
    cost_sum = h_cost.data.sum()
    inf = float("inf")
    if cost_sum == inf or cost_sum == -inf or cost_sum > 200*batch_size:
        print("Warning: received an inf loss, setting loss value to 0")
        return torch.zeros(H.size()), torch.zeros(cost.size()), torch.zeros(h_cost.size())

    crnn.zero_grad()
    h_cost.backward()
    torch.nn.utils.clip_grad_norm(crnn.parameters(), opt.max_norm)
    optimizer.step()
    return H / batch_size, cost / batch_size, h_cost / batch_size 

def trainBatch(net, criterion, optimizer):
    data = train_iter.next()
    cpu_images, cpu_texts = data
    batch_size = cpu_images.size(0)
    utils.loadData(image, cpu_images)
    t, l = converter.encode(cpu_texts)
    utils.loadData(text, t)
    utils.loadData(length, l)

    preds = crnn(image)
    preds_size = Variable(torch.IntTensor([preds.size(0)] * batch_size))
    cost = criterion(preds, text, preds_size, length) / batch_size
    crnn.zero_grad()
    cost.backward()
    optimizer.step()
    return cost 

def trainBatch(net, criterion, optimizer, train_iter):
    data = train_iter.next()
    cpu_images, cpu_texts = data
    # print('----cpu_images-----')
    # print(cpu_images.shape)
    batch_size = cpu_images.size(0)
    utils.loadData(image, cpu_images)
    t, l = converter.encode(cpu_texts)
    utils.loadData(text, t)
    utils.loadData(length, l)
    # print('----image-----')
    # print(image.shape)
    preds = crnn(image)
    preds_size = Variable(torch.IntTensor([preds.size(0)] * batch_size))
    cost = criterion(preds, text, preds_size, length) / batch_size
    crnn.zero_grad()
    cost.backward()
    optimizer.step()
    return cost 

def trainBatch(net, criterion, optimizer):
    data = train_iter.next()
    cpu_images, cpu_texts = data
    batch_size = cpu_images.size(0)
    utils.loadData(image, cpu_images)
    t, l = converter.encode(cpu_texts)
    utils.loadData(text, t)
    utils.loadData(length, l)

    preds = crnn(image)
    preds_size = Variable(torch.IntTensor([preds.size(0)] * batch_size))
    cost = criterion(preds, text, preds_size, length) / batch_size
    crnn.zero_grad()
    cost.backward()
    optimizer.step()
    return cost 

def trainBatch(net, criterion, optimizer):
    data = train_iter.next()
    cpu_images, cpu_texts = data
    batch_size = cpu_images.size(0)
    image = cpu_images.to(device)

    text, length = converter.encode(cpu_texts)
    # utils.loadData(text, t)
    # utils.loadData(length, l)

    preds = net(image)  # seqLength x batchSize x alphabet_size
    preds_size = Variable(torch.IntTensor([preds.size(0)] * batch_size))  # seqLength x batchSize
    cost = criterion(preds.log_softmax(2).cpu(), text, preds_size, length) / batch_size
    if torch.isnan(cost):
        print(batch_size,cpu_texts)
    else:
        net.zero_grad()
        cost.backward()
        optimizer.step()
    return cost 

def trainBatch(net, criterion, optimizer):
    data = train_iter.next()
    cpu_images, cpu_texts = data
    batch_size = cpu_images.size(0)
    image = cpu_images.to(device)

    text, length = converter.encode(cpu_texts)
    # utils.loadData(text, t)
    # utils.loadData(length, l)

    preds = net(image)  # seqLength x batchSize x alphabet_size
    preds_size = Variable(torch.IntTensor([preds.size(0)] * batch_size))  # seqLength x batchSize
    cost = criterion(preds, text, preds_size, length) / batch_size
    if torch.isnan(cost):
        print(batch_size,cpu_texts)
    else:
        net.zero_grad()
        cost.backward()
        optimizer.step()
    return cost 

def trainBatch(net, criterion, optimizer):
    data = train_iter.next()
    cpu_images, cpu_texts = data
    batch_size = cpu_images.size(0)
    image = cpu_images.to(device)

    text, length = converter.encode(cpu_texts)
    # utils.loadData(text, t)
    # utils.loadData(length, l)

    preds = net(image)  # seqLength x batchSize x alphabet_size
    preds_size = Variable(torch.IntTensor([preds.size(0)] * batch_size))  # seqLength x batchSize
    cost = criterion(preds, text, preds_size, length) / batch_size
    if torch.isnan(cost):
        print(batch_size,cpu_texts)
    else:
        net.zero_grad()
        cost.backward()
        optimizer.step()
    return cost 

def trainBatch(net, criterion, optimizer):
    data = train_iter.next()
    cpu_images, cpu_texts = data
    batch_size = cpu_images.size(0)
    utils.loadData(image, cpu_images)
    t, l = converter.encode(cpu_texts)
    utils.loadData(text, t)
    utils.loadData(length, l)
    
    optimizer.zero_grad()
    preds = crnn(image)
    preds = preds.log_softmax(2)
    preds_size = Variable(torch.IntTensor([preds.size(0)] * batch_size))
    cost = criterion(preds, text, preds_size, length)
    # crnn.zero_grad()
    cost.backward()
    optimizer.step()
    return cost 

def train(net, criterion, optimizer, train_iter):
    for p in crnn.parameters():
        p.requires_grad = True
    crnn.train()

    data = train_iter.next()
    cpu_images, cpu_texts = data
    batch_size = cpu_images.size(0)
    utils.loadData(image, cpu_images)
    t, l = converter.encode(cpu_texts)
    utils.loadData(text, t)
    utils.loadData(length, l)
    
    optimizer.zero_grad()
    preds = crnn(image)
    preds_size = Variable(torch.LongTensor([preds.size(0)] * batch_size))
    cost = criterion(preds, text, preds_size, length) / batch_size
    # crnn.zero_grad()
    cost.backward()
    optimizer.step()
    return cost 

def trainBatch(net, criterion, optimizer):
    data = train_iter.next()
    cpu_images, cpu_texts = data
    batch_size = cpu_images.size(0)
    utils.loadData(image, cpu_images)
    t, l = converter.encode(cpu_texts)
    utils.loadData(text, t)
    utils.loadData(length, l)

    preds = crnn(image)
    preds_size = Variable(torch.IntTensor([preds.size(0)] * batch_size))
    cost = criterion(preds, text, preds_size, length) / batch_size
    crnn.zero_grad()
    cost.backward()
    optimizer.step()
    return cost 

def trainBatch(net, criterion, optimizer,flage=False):
    n_correct = 0
    train_distance=0

    data = train_iter.next()
    cpu_images, cpu_texts = data##decode utf-8 to unicode
    if ifUnicode:
        cpu_texts = [ clean_txt(tx.decode('utf-8'))  for tx in cpu_texts]
        
    batch_size = cpu_images.size(0)
    utils.loadData(image, cpu_images)
    t, l = converter.encode(cpu_texts)
    utils.loadData(text, t)
    utils.loadData(length, l)

    preds = crnn(image)
    preds_size = Variable(torch.IntTensor([preds.size(0)] * batch_size))
    cost = criterion(preds, text, preds_size, length) / batch_size
    crnn.zero_grad()
    cost.backward()


    _, preds = preds.max(2)
    preds = preds.transpose(1, 0).contiguous().view(-1)
    sim_preds = converter.decode(preds.data, preds_size.data, raw=False)
    for pred, target in zip(sim_preds, cpu_texts):
        if pred.strip() == target.strip():
            n_correct += 1
        train_distance +=distance.nlevenshtein(pred.strip(),target.strip(),method=2)
    train_accuracy = n_correct / float(batch_size)
    train_distance=train_distance/float(batch_size)


    if flage:
        lr = 0.0001
        optimizer = optim.Adadelta(crnn.parameters(), lr=lr)
    optimizer.step()
    return cost,train_accuracy,train_distance 

def val(net, dataset, criterion, max_iter=100):
    print('Start val')

    for p in crnn.parameters():
        p.requires_grad = False

    net.eval()
    data_loader = torch.utils.data.DataLoader(
        dataset, shuffle=True, batch_size=opt.batchSize, num_workers=int(opt.workers))
    val_iter = iter(data_loader)

    i = 0
    n_correct = 0
    loss_avg = utils.averager()

    max_iter = min(max_iter, len(data_loader))
    for i in range(max_iter):
        data = val_iter.next()
        i += 1
        cpu_images, cpu_texts = data
        batch_size = cpu_images.size(0)
        utils.loadData(image, cpu_images)
        t, l = converter.encode(cpu_texts)
        utils.loadData(text, t)
        utils.loadData(length, l)

        preds = crnn(image)
        preds_size = Variable(torch.IntTensor([preds.size(0)] * batch_size))
        cost = criterion(preds, text, preds_size, length) / batch_size
        loss_avg.add(cost)

        _, preds = preds.max(2)
        preds = preds.squeeze(2)
        preds = preds.transpose(1, 0).contiguous().view(-1)
        sim_preds = converter.decode(preds.data, preds_size.data, raw=False)
        for pred, target in zip(sim_preds, cpu_texts):
            if pred == target.lower():
                n_correct += 1

    raw_preds = converter.decode(preds.data, preds_size.data, raw=True)[:opt.n_test_disp]
    for raw_pred, pred, gt in zip(raw_preds, sim_preds, cpu_texts):
        print('%-20s => %-20s, gt: %-20s' % (raw_pred, pred, gt))

    accuracy = n_correct / float(max_iter * opt.batchSize)
    print('Test loss: %f, accuray: %f' % (loss_avg.val(), accuracy)) 

def val(net, dataset, criterion, max_iter=100):
    print('Start val')

    for p in crnn.parameters():
        p.requires_grad = False

    net.eval()
    data_loader = torch.utils.data.DataLoader(
        dataset, shuffle=True, batch_size=opt.batchSize, num_workers=int(opt.workers))
    val_iter = iter(data_loader)

    i = 0
    n_correct = 0
    loss_avg = utils.averager()

    max_iter = min(max_iter, len(data_loader))
    for i in range(max_iter):
        data = val_iter.next()
        i += 1
        cpu_images, cpu_texts = data
        batch_size = cpu_images.size(0)
        utils.loadData(image, cpu_images)
        t, l = converter.encode(cpu_texts)
        utils.loadData(text, t)
        utils.loadData(length, l)

        preds = crnn(image) # size = 26, 64, 96
        # print(preds.size())
        preds_size = Variable(torch.IntTensor([preds.size(0)] * batch_size))
        cost = criterion(preds, text, preds_size, length) / batch_size
        loss_avg.add(cost)

        _, preds = preds.max(2) # size = 26, 64
        # print(preds.size())
        # preds = preds.squeeze(2)
        preds = preds.transpose(1, 0).contiguous().view(-1)
        sim_preds = converter.decode(preds.data, preds_size.data, raw=False)
        for pred, target in zip(sim_preds, cpu_texts):
            if pred == target.lower():
                n_correct += 1

    raw_preds = converter.decode(preds.data, preds_size.data, raw=True)[:opt.n_test_disp]
    for raw_pred, pred, gt in zip(raw_preds, sim_preds, cpu_texts):
        print('%-30s => %-30s, gt: %-30s' % (raw_pred, pred, gt))

    accuracy = n_correct / float(max_iter * opt.batchSize)
    print('Test loss: %f, accuray: %f' % (loss_avg.val(), accuracy)) 

def val(net, test_dataset, criterion, max_iter=2):
    print('Start val')

    for p in crnn.parameters():
        p.requires_grad = False

    net.eval()
    data_loader = torch.utils.data.DataLoader(
        test_dataset,  batch_size=opt.batchSize, num_workers=int(opt.workers),
        sampler=dataset.randomSequentialSampler(test_dataset, opt.batchSize),
        collate_fn=dataset.alignCollate(imgH=opt.imgH, imgW=opt.imgW, keep_ratio=opt.keep_ratio))
    val_iter = iter(data_loader)

    i = 0
    n_correct = 0
    loss_avg = utils.averager()
    test_distance=0
    max_iter = min(max_iter, len(data_loader))
    for i in range(max_iter):
        data = val_iter.next()
        i += 1
        cpu_images, cpu_texts = data
        batch_size = cpu_images.size(0)
        utils.loadData(image, cpu_images)
        if ifUnicode:
             cpu_texts = [ clean_txt(tx.decode('utf-8'))  for tx in cpu_texts]
        t, l = converter.encode(cpu_texts)
        utils.loadData(text, t)
        utils.loadData(length, l)

        preds = crnn(image)
        preds_size = Variable(torch.IntTensor([preds.size(0)] * batch_size))
        cost = criterion(preds, text, preds_size, length) / batch_size
        loss_avg.add(cost)

        _, preds = preds.max(2)
       # preds = preds.squeeze(2)
        preds = preds.transpose(1, 0).contiguous().view(-1)
        sim_preds = converter.decode(preds.data, preds_size.data, raw=False)
        for pred, target in zip(sim_preds, cpu_texts):
            if pred.strip() == target.strip():
                n_correct += 1
            # print(distance.levenshtein(pred.strip(), target.strip()))
            test_distance +=distance.nlevenshtein(pred.strip(), target.strip(),method=2)
    raw_preds = converter.decode(preds.data, preds_size.data, raw=True)[:opt.n_test_disp]
    for raw_pred, pred, gt in zip(raw_preds, sim_preds, cpu_texts):

        print('%-20s => %-20s, gt: %-20s' % (raw_pred, pred, gt))
    accuracy = n_correct / float(max_iter * opt.batchSize)
    test_distance=test_distance/float(max_iter * opt.batchSize)
    testLoss = loss_avg.val()
    #print('Test loss: %f, accuray: %f' % (testLoss, accuracy))
    return testLoss,accuracy,test_distance 

def val(net, dataset, criterion, max_iter=100):
    print('Start val')

    for p in crnn.parameters():
        p.requires_grad = False

    net.eval()
    data_loader = torch.utils.data.DataLoader(
        dataset, shuffle=True, batch_size=opt.batchSize, num_workers=int(opt.workers))
    val_iter = iter(data_loader)

    i = 0
    n_correct = 0
    loss_avg = utils.averager()

    max_iter = min(max_iter, len(data_loader))
    for i in range(max_iter):
        data = val_iter.next()
        i += 1
        cpu_images, cpu_texts = data
        batch_size = cpu_images.size(0)
        utils.loadData(image, cpu_images)
        t, l = converter.encode(cpu_texts)
        utils.loadData(text, t)
        utils.loadData(length, l)

        preds = crnn(image)
        preds_size = Variable(torch.IntTensor([preds.size(0)] * batch_size))
        cost = criterion(preds, text, preds_size, length) / batch_size
        loss_avg.add(cost)

        _, preds = preds.max(2)
        preds = preds.squeeze(2)
        preds = preds.transpose(1, 0).contiguous().view(-1)
        sim_preds = converter.decode(preds.data, preds_size.data, raw=False)
        for pred, target in zip(sim_preds, cpu_texts):
            if pred == target:
                n_correct += 1

    raw_preds = converter.decode(preds.data, preds_size.data, raw=True)[:opt.n_test_disp]
    for raw_pred, pred, gt in zip(raw_preds, sim_preds, cpu_texts):
        
        print('%-20s => %-20s, gt: %-20s' % (raw_pred.encode('utf-8'), pred.encode('utf-8'), gt.encode('utf-8')))

    accuracy = n_correct / float(max_iter * opt.batchSize)
    print('Test loss: %f, accuray: %f' % (loss_avg.val(), accuracy)) 

def val(net, dataset, criterion, max_iter=100):
    #print('Start val')

    for p in crnn.parameters():
        p.requires_grad = False

    net.eval()
    data_loader = torch.utils.data.DataLoader(dataset, shuffle=True, batch_size=params.batchSize, num_workers=int(params.workers))
    val_iter = iter(data_loader)

    i = 0
    n_correct = 0
    loss_avg = utils.averager()

    max_iter = min(max_iter, len(data_loader))
    for i in range(max_iter):
        data = val_iter.next()
        i += 1
        cpu_images, cpu_texts = data
        batch_size = cpu_images.size(0)
        utils.loadData(image, cpu_images)
        t, l = converter.encode(cpu_texts)
        utils.loadData(text, t)
        utils.loadData(length, l)

        preds = crnn(image)
        preds_size = Variable(torch.IntTensor([preds.size(0)] * batch_size))
        cost = criterion(preds, text, preds_size, length)
        loss_avg.add(cost)

        _, preds = preds.max(2)
        preds = preds.transpose(1, 0).contiguous().view(-1)
        sim_preds = converter.decode(preds.data, preds_size.data, raw=False)
        #cpu_texts_decode = []
        #for i in cpu_texts:
        #    cpu_texts_decode.append(i.decode('utf-8', 'strict'))
        for pred, target in zip(sim_preds, cpu_texts):
            if pred == target:
                n_correct += 1

    raw_preds = converter.decode(preds.data, preds_size.data, raw=True)[:params.n_test_disp]
    for raw_pred, pred, gt in zip(raw_preds, sim_preds, cpu_texts):
        print('%-20s => %-20s, gt: %-20s' % (raw_pred, pred, gt))

    accuracy = n_correct / float(max_iter * params.batchSize)
    print('loss: %f, accuray: %f' % (loss_avg.val(), accuracy))
    return loss_avg.val(), accuracy 

def val(net, dataset, criterion, max_iter=100):
    print('Start val')
    for p in crnn.parameters():
        p.requires_grad = False
    net.eval()
    data_loader = torch.utils.data.DataLoader(
        dataset, shuffle=True, batch_size=params.batchSize, num_workers=int(params.workers))
    val_iter = iter(data_loader)
    i = 0
    n_correct = 0
    loss_avg = utils.averager()

    max_iter = min(max_iter, len(data_loader))
    for i in range(max_iter):
        data = val_iter.next()
        i += 1
        cpu_images, cpu_texts = data
        batch_size = cpu_images.size(0)
        utils.loadData(image, cpu_images)
        t, l = converter.encode(cpu_texts)
        utils.loadData(text, t)
        utils.loadData(length, l)
        preds = crnn(image)
        # print('-----preds-----')
        # print(preds)
        preds_size = Variable(torch.IntTensor([preds.size(0)] * batch_size))
        # print('-----preds_size-----')
        # print(preds_size)
        cost = criterion(preds, text, preds_size, length) / batch_size
        loss_avg.add(cost)
        _, preds = preds.max(2)
        # print('-----preds.max(2)-----')
        # print(preds)
        preds = preds.transpose(1, 0).contiguous().view(-1)
        # print('-----preds.transpose(1, 0)-----')
        # print(preds)
        sim_preds = converter.decode(preds.data, preds_size.data, raw=False)

        list_1 = []
        for m in cpu_texts:
            list_1.append(m.decode('utf-8', 'strict'))

        # if (i - 1) % 10 == 0:
        # print('-----sim_preds-----list_1-----')
        # print(sim_preds, list_1)
        for pred, target in zip(sim_preds, list_1):
            if pred == target:
                n_correct += 1
#             else:
#                 print('%-20s, gt: %-20s' % (pred, target))

    raw_preds = converter.decode(preds.data, preds_size.data, raw=True)[:params.n_test_disp]
    for raw_pred, pred, gt in zip(raw_preds, sim_preds, list_1):
        print('%-20s => %-20s, gt: %-20s' % (raw_pred, pred, gt))

    print(n_correct)
    print(max_iter * params.batchSize)
    accuracy = n_correct / float(max_iter * params.batchSize)
    print('Test loss: %f, accuray: %f' % (loss_avg.val(), accuracy)) 

def val(net, dataset, criterion, max_iter=100):
    print('Start val')

    for p in crnn.parameters():
        p.requires_grad = False

    net.eval()
    data_loader = torch.utils.data.DataLoader(
        dataset, shuffle=True, batch_size=opt.batchSize, num_workers=int(opt.workers))
    val_iter = iter(data_loader)

    i = 0
    n_correct = 0
    loss_avg = utils.averager()

    max_iter = min(max_iter, len(data_loader))
    for i in range(max_iter):
        data = val_iter.next()
        i += 1
        cpu_images, cpu_texts = data
        batch_size = cpu_images.size(0)
        utils.loadData(image, cpu_images)
        t, l = converter.encode(cpu_texts)
        utils.loadData(text, t)
        utils.loadData(length, l)

        preds = crnn(image)
        preds_size = Variable(torch.IntTensor([preds.size(0)] * batch_size))
        cost = criterion(preds, text, preds_size, length) / batch_size
        loss_avg.add(cost)

        _, preds = preds.max(2)
        preds = preds.squeeze(2)
        preds = preds.transpose(1, 0).contiguous().view(-1)
        sim_preds = converter.decode(preds.data, preds_size.data, raw=False)
        for pred, target in zip(sim_preds, cpu_texts):
            if pred == target:
                n_correct += 1

    raw_preds = converter.decode(preds.data, preds_size.data, raw=True)[:opt.n_test_disp]
    for raw_pred, pred, gt in zip(raw_preds, sim_preds, cpu_texts):
        
        print('%-20s => %-20s, gt: %-20s' % (raw_pred.encode('utf-8'), pred.encode('utf-8'), gt.encode('utf-8')))

    accuracy = n_correct / float(max_iter * opt.batchSize)
    print('Test loss: %f, accuray: %f' % (loss_avg.val(), accuracy)) 

def val(net, criterion):
    print('Start val')

    for p in crnn.parameters():
        p.requires_grad = False

    net.eval()
    val_iter = iter(val_loader)

    i = 0
    n_correct = 0
    loss_avg = utils.averager() # The blobal loss_avg is used by train

    max_iter = len(val_loader)
    for i in range(max_iter):
        data = val_iter.next()
        i += 1
        cpu_images, cpu_texts = data
        batch_size = cpu_images.size(0)
        utils.loadData(image, cpu_images)
        t, l = converter.encode(cpu_texts)
        utils.loadData(text, t)
        utils.loadData(length, l)

        preds = crnn(image)
        preds_size = Variable(torch.LongTensor([preds.size(0)] * batch_size))
        cost = criterion(preds, text, preds_size, length) / batch_size
        loss_avg.add(cost)

        _, preds = preds.max(2)
        preds = preds.transpose(1, 0).contiguous().view(-1)
        sim_preds = converter.decode(preds.data, preds_size.data, raw=False)
        cpu_texts_decode = []
        for i in cpu_texts:
            cpu_texts_decode.append(i.decode('utf-8', 'strict'))
        for pred, target in zip(sim_preds, cpu_texts_decode):
            if pred == target:
                n_correct += 1

    raw_preds = converter.decode(preds.data, preds_size.data, raw=True)[:params.n_val_disp]
    for raw_pred, pred, gt in zip(raw_preds, sim_preds, cpu_texts_decode):
        print('%-20s => %-20s, gt: %-20s' % (raw_pred, pred, gt))

    accuracy = n_correct / float(max_iter * params.batchSize)
    print('Val loss: %f, accuray: %f' % (loss_avg.val(), accuracy)) 

def val(net, dataset, max_iter=100):
    print('Start val')

    for p in crnn.parameters():
        p.requires_grad = False

    net.eval()
    data_loader = torch.utils.data.DataLoader(
        dataset, shuffle=True, batch_size=opt.batchSize, num_workers=int(opt.workers))
    val_iter = iter(data_loader)

    i = 0
    n_correct = 0
    # loss averager
    avg_h_val = utils.averager()
    avg_cost_val = utils.averager()
    avg_h_cost_val = utils.averager()

    if opt.eval_all:
        max_iter = len(data_loader)
    else:
        max_iter = min(max_iter, len(data_loader))

    for i in range(max_iter):
        data = val_iter.next()
        i += 1
        cpu_images, cpu_texts = data
        batch_size = cpu_images.size(0)
        utils.loadData(image, cpu_images)
        t, l = converter.encode(cpu_texts)
        utils.loadData(text, t)
        utils.loadData(length, l)

        preds = crnn(image)
        preds_size = Variable(torch.IntTensor([preds.size(0)] * batch_size))
        H, cost = seg_ctc_ent_cost(preds, text, preds_size, length, uni_rate=opt.uni_rate)
        h_cost = (1-opt.h_rate)*cost-opt.h_rate*H
        avg_h_val.add(H / batch_size)
        avg_cost_val.add(cost / batch_size)
        avg_h_cost_val.add(h_cost / batch_size)

        _, preds = preds.max(2)
        preds = preds.transpose(1, 0).contiguous().view(-1)
        sim_preds = converter.decode(preds.data, preds_size.data, raw=False)
        for idx, (pred, target) in enumerate(zip(sim_preds, cpu_texts)):
            if pred == target.lower():
                n_correct += 1

    raw_preds = converter.decode(preds.data, preds_size.data, raw=True)[:opt.n_test_disp]
    for raw_pred, pred, gt in zip(raw_preds, sim_preds, cpu_texts):
        print('%-20s => %-20s, gt: %-20s' % (raw_pred, pred, gt))

    accuracy = n_correct / float(max_iter * opt.batchSize)
    print('Test H: %f, Cost: %f, H Cost: %f, accuray: %f' %
            (avg_h_val.val(), avg_cost_val.val(), avg_h_cost_val.val(), accuracy))