Python data.view方法代码示例

# 需要导入模块: import data [as 别名]
# 或者: from data import view [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 view [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 view [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 view [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 view [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 view [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 view [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 view [as 别名]
def get_batch(source, i):
    seq_len = min(args.bptt, len(source) - 1 - i)
    data = source[i:i + seq_len]
    target = source[i + 1:i + 1 + seq_len].view(-1)
    return data, target 

# 需要导入模块: import data [as 别名]
# 或者: from data import view [as 别名]
def export_onnx(path, batch_size, seq_len):
    print('The model is also exported in ONNX format at {}'.
          format(os.path.realpath(args.onnx_export)))
    model.eval()
    dummy_input = torch.LongTensor(seq_len * batch_size).zero_().view(-1, batch_size).to(device)
    hidden = model.init_hidden(batch_size)
    torch.onnx.export(model, (dummy_input, hidden), path)


# Loop over epochs. 

# 需要导入模块: import data [as 别名]
# 或者: from data import view [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()
    if args.cuda:
        data = data.cuda()
    return data 

# 需要导入模块: import data [as 别名]
# 或者: from data import view [as 别名]
def get_batch(source, i, evaluation=False):
    seq_len = min(args.bptt, len(source) - 1 - i)
    data = Variable(source[i:i + seq_len], volatile=evaluation)
    target = Variable(source[i + 1:i + 1 + seq_len].view(-1))
    return data, target 

# 需要导入模块: import data [as 别名]
# 或者: from data import view [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)
    for i in range(0, data_source.size(0) - 1, args.bptt):
        data, targets = get_batch(data_source, i, evaluation=True)
        output, hidden = model(data, hidden)
        output_flat = output.view(-1, ntokens)
        total_loss += len(data) * criterion(output_flat, targets).data
        hidden = repackage_hidden(hidden)
    return total_loss[0] / len(data_source) 

# 需要导入模块: import data [as 别名]
# 或者: from data import view [as 别名]
def train():
    # Turn on training mode which enables dropout.
    model.train()
    total_loss = 0
    start_time = time.time()
    ntokens = len(corpus.dictionary)
    hidden = model.init_hidden(args.batch_size)
    for batch, i in enumerate(range(0, train_data.size(0) - 1, args.bptt)):
        data, targets = get_batch(train_data, i)
        # Starting each batch, we detach the hidden state from how it was previously produced.
        # If we didn't, the model would try backpropagating all the way to start of the dataset.
        hidden = repackage_hidden(hidden)
        model.zero_grad()
        output, hidden = model(data, hidden)
        loss = criterion(output.view(-1, ntokens), targets)
        loss.backward()

        # `clip_grad_norm` helps prevent the exploding gradient problem in RNNs / LSTMs.
        torch.nn.utils.clip_grad_norm(model.parameters(), args.clip)
        for p in model.parameters():
            p.data.add_(-lr, p.grad.data)

        total_loss += loss.data

        if batch % args.log_interval == 0 and batch > 0:
            cur_loss = total_loss[0] / args.log_interval
            elapsed = time.time() - start_time
            print('| epoch {:3d} | {:5d}/{:5d} batches | lr {:02.2f} | ms/batch {:5.2f} | '
                  'loss {:5.2f} | ppl {:8.2f}'.format(
                epoch, batch, len(train_data) // args.bptt, lr,
                              elapsed * 1000 / args.log_interval, cur_loss, math.exp(cur_loss)))
            total_loss = 0
            start_time = time.time()


# Loop over epochs. 

# 需要导入模块: import data [as 别名]
# 或者: from data import view [as 别名]
def batchify(data, bsz, args):
    # 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()
    if args.cuda:
        data = data.cuda()
    return data 

# 需要导入模块: import data [as 别名]
# 或者: from data import view [as 别名]
def get_batch(source, i, args, seq_len=None):
    seq_len = min(seq_len if seq_len else args.bptt, len(source) - 1 - i)
    data = source[i:i+seq_len]
    target = source[i+1:i+1+seq_len].view(-1)
    return data, target