Python data.size方法代码示例

# 需要导入模块: import data [as 别名]
# 或者: from data import size [as 别名]
def singletest(data,net,config,splitfun,combinefun,n_per_run,margin = 64,isfeat=False):
    z, h, w = data.size(2), data.size(3), data.size(4)
    print(data.size())
    data = splitfun(data,config['max_stride'],margin)
    data = Variable(data.cuda(async = True), volatile = True,requires_grad=False)
    splitlist = range(0,args.split+1,n_per_run)
    outputlist = []
    featurelist = []
    for i in range(len(splitlist)-1):
        if isfeat:
            output,feature = net(data[splitlist[i]:splitlist[i+1]])
            featurelist.append(feature)
        else:
            output = net(data[splitlist[i]:splitlist[i+1]])
        output = output.data.cpu().numpy()
        outputlist.append(output)
        
    output = np.concatenate(outputlist,0)
    output = combinefun(output, z / config['stride'], h / config['stride'], w / config['stride'])
    if isfeat:
        feature = np.concatenate(featurelist,0).transpose([0,2,3,4,1])
        feature = combinefun(feature, z / config['stride'], h / config['stride'], w / config['stride'])
        return output,feature
    else:
        return output 

# 需要导入模块: import data [as 别名]
# 或者: from data import size [as 别名]
def make_std_mask(tgt):
    """Create a mask to hide padding and future words."""
    tgt_mask = (tgt != pad).unsqueeze(-2)
    tgt_mask = tgt_mask & subsequent_mask(tgt.size(-1)).type_as(tgt_mask)
    return tgt_mask


# get_batch subdivides the source data into chunks of length args.bptt.
# If source is equal to the example output of the batchify function, with
# a bptt-limit of 2, we'd get the following two Variables for i = 0:
# ┌ a g m s ┐ ┌ b h n t ┐
# └ b h n t ┘ └ c i o u ┘
# Note that despite the name of the function, the subdivison of data is not
# done along the batch dimension (i.e. dimension 1), since that was handled
# by the batchify function. The chunks are along dimension 0, corresponding
# to the seq_len dimension in the LSTM. 

# 需要导入模块: import data [as 别名]
# 或者: from data import size [as 别名]
def get_batch(source, i, train):
    if train:
        i = torch.randint(low=0, high=(len(source) - args.bptt), size=(1,)).long().item()
        seq_len = args.bptt
        target = source[i + 1:i + 1 + seq_len].t()
    else:
        seq_len = min(args.bptt, len(source) - 1 - i)
        target = source[i + seq_len, :]

    data = source[i:i + seq_len].t()

    data_mask = (data != pad).unsqueeze(-2)
    target_mask = make_std_mask(data.long())

    # reshape target to match what cross_entropy expects
    target = target.contiguous().view(-1)

    return data, target, data_mask, target_mask 

# 需要导入模块: import data [as 别名]
# 或者: from data import size [as 别名]
def evaluate(data_source):
    # Turn on evaluation mode which disables dropout.
    model.eval()
    total_loss = 0.
    ntokens = len(corpus.dictionary)
    memory = model.module.initial_state(eval_batch_size, trainable=False).to(device)

    with torch.no_grad():
        for i in range(0, data_source.size(0) - 1, args.bptt):
            data, targets = get_batch(data_source, i)
            data = torch.t(data)

            loss, memory = model(data, memory, targets)
            loss = torch.mean(loss)

            # data has shape [T * B, N]
            total_loss += args.bptt * loss.item()

    return total_loss / len(data_source) 

# 需要导入模块: import data [as 别名]
# 或者: from data import size [as 别名]
def evaluate(data_source):
    # Turn on evaluation mode which disables dropout.
    model.eval()
    total_loss = 0.
    ntokens = len(corpus.dictionary)
    hidden = model.init_hidden(eval_batch_size)
    with torch.no_grad():
        for i in range(0, data_source.size(0) - 1, args.bptt):
            data, targets = get_batch(data_source, i)
            output, hidden = model(data, hidden)
            if not args.adaptivesoftmax:
                loss = criterion(output.view(-1, ntokens), targets)
            else:
                _, loss = criterion_adaptive(output.view(-1, args.nhid), targets)
            total_loss += len(data) * loss.item()
            hidden = repackage_hidden(hidden)
    return total_loss / len(data_source) 

# 需要导入模块: import data [as 别名]
# 或者: from data import size [as 别名]
def evaluate(data_source):
    # Turn on evaluation mode which disables dropout.
    model.eval()
    total_loss = 0.
    ntokens = len(corpus.dictionary)
    if args.model != 'Transformer':
        hidden = model.init_hidden(eval_batch_size)
    with torch.no_grad():
        for i in range(0, data_source.size(0) - 1, args.bptt):
            data, targets = get_batch(data_source, i)
            if args.model == 'Transformer':
                output = model(data)
                output = output.view(-1, ntokens)
            else:
                output, hidden = model(data, hidden)
                hidden = repackage_hidden(hidden)
            total_loss += len(data) * criterion(output, targets).item()
    return total_loss / (len(data_source) - 1) 

# 需要导入模块: import data [as 别名]
# 或者: from data import size [as 别名]
def singletest(data, net, config, splitfun, combinefun, n_per_run, margin=64):
    z, h, w = data.size(2), data.size(3), data.size(4)
    print(data.size())
    data = splitfun(data, config['max_stride'], margin)
    data = Variable(data.cuda(async=True), volatile=True, requires_grad=False)
    splitlist = range(0, args.split + 1, n_per_run)
    outputlist = []

    for i in range(len(splitlist) - 1):
        output = net(data[splitlist[i]:splitlist[i + 1]])
        output = output.data.cpu().numpy()
        outputlist.append(output)

    output = np.concatenate(outputlist, 0)
    output = combinefun(output, z / config['stride'], h / config['stride'], w / config['stride'])
    return output 

# 需要导入模块: import data [as 别名]
# 或者: from data import size [as 别名]
def evaluate(data_source):
    # Turn on evaluation mode which disables dropout.
    model.eval()
    total_loss = 0.
    ntokens = len(corpus.dictionary)
    if args.model != 'Transformer':
        hidden = model.init_hidden(eval_batch_size)
    with torch.no_grad():
        for i in range(0, data_source.size(0) - 1, args.bptt):
            data, targets = get_batch(data_source, i)
            if args.model == 'Transformer':
                output = model(data)
            else:
                output, hidden = model(data, hidden)
                hidden = repackage_hidden(hidden)
            output_flat = output.view(-1, ntokens)
            total_loss += len(data) * criterion(output_flat, targets).item()
    return total_loss / (len(data_source) - 1) 

# 需要导入模块: import data [as 别名]
# 或者: from data import size [as 别名]
def batchify(data, bsz):
    # Work out how cleanly we can divide the dataset into bsz parts.
    if isinstance(data, tuple):
        nbatch = data[0].size(0) // bsz
        # Trim off any extra elements that wouldn't cleanly fit (remainders).
        tag_data = data[1].narrow(0, 0, nbatch * bsz)
        data = data[0].narrow(0, 0, nbatch * bsz)
        # Evenly divide the data across the bsz batches.
        tag_data = tag_data.view(bsz, -1).t().contiguous()
    else:
        nbatch = data.size(0) // bsz
        # Trim off any extra elements that wouldn't cleanly fit (remainders).
        data = data.narrow(0, 0, nbatch * bsz)
    
    # Evenly divide the data across the bsz batches.
    data = data.view(bsz, -1).t().contiguous()
    # Turning the data over to CUDA at this point may lead to more OOM errors
    #if args.cuda:
     #    data = data.cuda()
    if isinstance(data,tuple):
        return data, tag_data
    return data 

# 需要导入模块: import data [as 别名]
# 或者: from data import size [as 别名]
def evaluate(lm_data_source, ccg_data_source):
    # Turn on evaluation mode which disables dropout.
    model.eval()
    total_loss = 0
    ntokens = len(corpus.dictionary)
    if (not args.single) and (torch.cuda.device_count() > 1):
        #"module" is necessary when using DataParallel
        hidden = model.module.init_hidden(eval_batch_size)
    else:
        hidden = model.init_hidden(eval_batch_size)
    for i in range(0, lm_data_source.size(0) + ccg_data_source.size(0) - 1, args.bptt):
        # TAG
        if i > lm_data_source.size(0):
            data, targets = get_batch(ccg_data_source, i - lm_data_source.size(0), evaluation=True)
        # LM
        else:
            data, targets = get_batch(lm_data_source, i, evaluation=True)
        output, hidden = model(data, hidden)
        output_flat = output.view(-1, ntokens)
        curr_loss = len(data) * criterion(output_flat, targets).data
        total_loss += curr_loss
        hidden = repackage_hidden(hidden)
    if len(ccg_data_source) == 0:
        return total_loss / len(lm_data_source)
    return total_loss[0] / (len(lm_data_source)+len(ccg_data_source)) 

# 需要导入模块: import data [as 别名]
# 或者: from data import size [as 别名]
def batchify(data, batch_size):
    # Work out how cleanly we can divide the dataset into batch_size parts.
    nbatch = data.size(0) // batch_size
    # Trim off any extra elements that wouldn't cleanly fit (remainders).
    data = data.narrow(0, 0, nbatch * batch_size)
    # Evenly divide the data across the batch_size batches.
    data = data.view(batch_size, -1).t().contiguous()
    return data.to(device) 

# 需要导入模块: import data [as 别名]
# 或者: from data import size [as 别名]
def subsequent_mask(size):
    """Mask out subsequent positions."""
    attn_shape = (1, size, size)
    subsequent_mask = np.triu(np.ones(attn_shape), k=1).astype('uint8')
    return torch.from_numpy(subsequent_mask) == 0 

# 需要导入模块: import data [as 别名]
# 或者: from data import size [as 别名]
def evaluate(data_source):
    # Turn on evaluation mode which disables dropout.
    total_loss = AverageMeter()
    model.eval()
    ntokens = len(corpus.dictionary)
    step = 1
    with torch.no_grad():
        for batch, i in enumerate(range(0, data_source.size(0) - 1 - args.bptt, step)):
            data, target, data_mask, target_mask = get_batch(data_source, i, train=False)
            output = model(data, target_mask)
            _, last_loss = model.criterion(output, target)
            total_loss.update(last_loss.item(), data.size(0))
    return total_loss.avg 

# 需要导入模块: import data [as 别名]
# 或者: from data import size [as 别名]
def batchify(data, bsz):
    # Work out how cleanly we can divide the dataset into bsz parts.
    nbatch = data.size(0) // bsz
    # Trim off any extra elements that wouldn't cleanly fit (remainders).
    data = data.narrow(0, 0, nbatch * bsz)
    # Evenly divide the data across the bsz batches.
    data = data.view(bsz, -1).t().contiguous()
    return data.to(device) 

# 需要导入模块: import data [as 别名]
# 或者: from data import size [as 别名]
def evaluate(data_source, batch_size, seq_len):
    # Turn on evaluation mode which disables dropout.
    model.eval()

    total_loss = 0
    tokens = 0
    n = 0
    save_all_losses = []

    ntokens = len(corpus.dictionary)

    hidden = model.init_hidden(batch_size)

    for i in range(0, data_source.size(0) - 1, seq_len):
        tokens += seq_len
        data, targets = get_batch(data_source, i, args, evaluation=True, seq_len=seq_len)
        output, hidden = model(data, hidden)
        output = nn.functional.log_softmax(output.permute(2,1,0)).permute(2,1,0)
        targets = targets.view(data.data.shape[0], batch_size, -1)
        CELoss = torch.gather(output.data, dim=2, index=targets.data).squeeze()
        CELoss = -1*CELoss
        if tokens < args.start_token: continue # We are not ready to accumulate error yet
        elif tokens >= args.start_token and tokens-seq_len < args.start_token:
            data.data = data.data[-(tokens-args.start_token+1):]
            CELoss = CELoss[-(tokens-args.start_token+1):]
            print('First word: %s' % (corpus.dictionary.idx2word[data.data[-(tokens-args.start_token+1),0]]))
        total_loss += torch.sum(CELoss)
        n += data.size(0)
        save_all_losses += CELoss.tolist()
        hidden = repackage_hidden(hidden)
    print('total: %d' % n)
    print('Last word: %s' % (corpus.dictionary.idx2word[data.data[-1,0]]))
    return total_loss / float(n), save_all_losses