【pytorch学习】《TensorDataset》中的__getitem__ 和《DataLoader》
一、 代码中的例子：
# -*- coding: utf-8 -*-
import torch
import torch.utils.data as Data
torch.manual_seed(1) # reproducible
BATCH_SIZE = 5
x = torch.linspace(1, 10, 10) # this is x data (torch tensor)
y = torch.linspace(10, 1, 10) # this is y data (torch tensor)
'''先转换成 torch 能识别的 Dataset'''
torch_dataset = Data.TensorDataset(x, y)
print(torch_dataset[0]) #输出(tensor(1.), tensor(10.))
print(torch_dataset[1]) #输出(tensor(2.), tensor(9.))
''' 把 dataset 放入 DataLoader'''
loader = Data.DataLoader(
dataset=torch_dataset, # torch TensorDataset format
batch_size=BATCH_SIZE, # mini batch size
shuffle=True, # 要不要打乱数据 (打乱比较好)
#num_workers=2, # subprocesses for loading data
)
for epoch in range(3): # train entire dataset 3 times
for step, (batch_x, batch_y) in enumerate(loader): # for each training step
# train your data...
print('Epoch: ', epoch, '| Step: ', step, '| batch x: ',
batch_x.numpy(), '| batch y: ', batch_y.numpy())
"""
Epoch: 0 | Step: 0 | batch x: [ 6. 7. 2. 3. 1.] | batch y: [ 5. 4. 9. 8. 10.]
Epoch: 0 | Step: 1 | batch x: [ 9. 10. 4. 8. 5.] | batch y: [ 2. 1. 7. 3. 6.]
Epoch: 1 | Step: 0 | batch x: [ 3. 4. 2. 9. 10.] | batch y: [ 8. 7. 9. 2. 1.]
Epoch: 1 | Step: 1 | batch x: [ 1. 7. 8. 5. 6.] | batch y: [ 10. 4. 3. 6. 5.]
Epoch: 2 | Step: 0 | batch x: [ 3. 9. 2. 6. 7.] | batch y: [ 8. 2. 9. 5. 4.]
Epoch: 2 | Step: 1 | batch x: [10. 4. 8. 1. 5.] | batch y: [ 1. 7. 3. 10. 6.]
"""二、 TensorDataset类
每个例子可以通过索引进行索引，如例子中的torch_dataset[0]，则输出(tensor(1.), tensor(10.))
class TensorDataset(Dataset):
"""Dataset wrapping tensors.
Each sample will be retrieved by indexing tensors along the first dimension.
Arguments:
*tensors (Tensor): tensors that have the same size of the first dimension.
"""
def __init__(self, *tensors):
assert all(tensors[0].size(0) == tensor.size(0) for tensor in tensors)
self.tensors = tensors
def __getitem__(self, index):
return tuple(tensor[index] for tensor in self.tensors)
def __len__(self):
return self.tensors[0].size(0)传入参数*tensors变为一个元组，如：
def makepizza(*a):
print(a)
for x in a:
print(x)
makepizza('a','b','c')
#输出：
('a', 'b', 'c')
a
b
c则原函数中：
print(torch_dataset.tensors)
#输出：
(tensor([ 1., 2., 3., 4., 5., 6., 7., 8., 9., 10.]),
tensor([ 10., 9., 8., 7., 6., 5., 4., 3., 2., 1.]))
print(torch_dataset[0])
#输出：
(tensor(1.), tensor(10.))三、pytorch书上构造【自定义数据集类】的例子
class myDataset(Dataset):
def __init__(self, csv_file, txt_file, root_dir, other_file):
self.csv_data = pd.read_csv(csv_file)
with open(txt_file, 'r') as f:
data_list = f.readlines()
self.txt_data = data_list
self.root_dir = root_dir
def __len__(self):
return len(self.csv_data)
def __getitem__(self, idx):
data = (self.csv_data[idx], self.txt_data[idx])
return data
dataiter = DataLoader(myDataset, batch_size=32, shuffle=True)四、__getitem__()方法理解
如果在类中定义了__getitem__()方法，那么他的实例对象（假设为P）就可以这样P[key]取值。当实例对象做P[key]运算时，就会调用类中的__getitem__()方法。
class DataTest:
def __init__(self,id,address):
self.id=id
self.address=address
self.d={self.id:1,
self.address:"192.168.1.1"
}
def __getitem__(self,key):
return "hello"
data=DataTest(1,"192.168.2.11")
print(data.__getitem__(2))
#hello
print(data[2])
#hello五、DataLoader类
class DataLoader(object):
r"""
Data loader. Combines a dataset and a sampler, and provides
single- or multi-process iterators over the dataset.
Arguments:
dataset (Dataset): dataset from which to load the data.
batch_size (int, optional): how many samples per batch to load
(default: 1).
shuffle (bool, optional): set to ``True`` to have the data reshuffled
at every epoch (default: False).
sampler (Sampler, optional): defines the strategy to draw samples from
the dataset. If specified, ``shuffle`` must be False.
batch_sampler (Sampler, optional): like sampler, but returns a batch of
indices at a time. Mutually exclusive with batch_size, shuffle,
sampler, and drop_last.
num_workers (int, optional): how many subprocesses to use for data
loading. 0 means that the data will be loaded in the main process.
(default: 0)
collate_fn (callable, optional): merges a list of samples to form a mini-batch.
pin_memory (bool, optional): If ``True``, the data loader will copy tensors
into CUDA pinned memory before returning them.
drop_last (bool, optional): set to ``True`` to drop the last incomplete batch,
if the dataset size is not divisible by the batch size. If ``False`` and
the size of dataset is not divisible by the batch size, then the last batch
will be smaller. (default: False)
timeout (numeric, optional): if positive, the timeout value for collecting a batch
from workers. Should always be non-negative. (default: 0)
worker_init_fn (callable, optional): If not None, this will be called on each
worker subprocess with the worker id (an int in ``[0, num_workers - 1]``) as
input, after seeding and before data loading. (default: None)
.. note:: By default, each worker will have its PyTorch seed set to
``base_seed + worker_id``, where ``base_seed`` is a long generated
by main process using its RNG. However, seeds for other libraies
may be duplicated upon initializing workers (w.g., NumPy), causing
each worker to return identical random numbers. (See
:ref:`dataloader-workers-random-seed` section in FAQ.) You may
use ``torch.initial_seed()`` to access the PyTorch seed for each
worker in :attr:`worker_init_fn`, and use it to set other seeds
before data loading.
.. warning:: If ``spawn`` start method is used, :attr:`worker_init_fn` cannot be an
unpicklable object, e.g., a lambda function.
"""
__initialized = False
def __init__(self, dataset, batch_size=1, shuffle=False, sampler=None, batch_sampler=None,
num_workers=0, collate_fn=default_collate, pin_memory=False, drop_last=False,
timeout=0, worker_init_fn=None):
self.dataset = dataset
self.batch_size = batch_size
self.num_workers = num_workers
self.collate_fn = collate_fn
self.pin_memory = pin_memory
self.drop_last = drop_last
self.timeout = timeout
self.worker_init_fn = worker_init_fn
if timeout < 0:
raise ValueError('timeout option should be non-negative')
if batch_sampler is not None:
if batch_size > 1 or shuffle or sampler is not None or drop_last:
raise ValueError('batch_sampler option is mutually exclusive '
'with batch_size, shuffle, sampler, and '
'drop_last')
self.batch_size = None
self.drop_last = None
if sampler is not None and shuffle:
raise ValueError('sampler option is mutually exclusive with '
'shuffle')
if self.num_workers < 0:
raise ValueError('num_workers option cannot be negative; '
'use num_workers=0 to disable multiprocessing.')
if batch_sampler is None:
if sampler is None:
if shuffle:
sampler = RandomSampler(dataset)
else:
sampler = SequentialSampler(dataset)
batch_sampler = BatchSampler(sampler, batch_size, drop_last)
self.sampler = sampler
self.batch_sampler = batch_sampler
self.__initialized = True
def __setattr__(self, attr, val):
if self.__initialized and attr in ('batch_size', 'sampler', 'drop_last'):
raise ValueError('{} attribute should not be set after {} is '
'initialized'.format(attr, self.__class__.__name__))
super(DataLoader, self).__setattr__(attr, val)
def __iter__(self):
return _DataLoaderIter(self)
def __len__(self):
return len(self.batch_sampler)