问题描述
我正在 PyTorch
中从 DataSet
制作一个 DataLoader
.
I am making a DataLoader
from DataSet
in PyTorch
.
从加载所有 dtype 作为 DataFrame
开始代码>np.float64
Start from loading the DataFrame
with all dtype as an np.float64
result = pd.read_csv('dummy.csv', header=0, dtype=DTYPE_CLEANED_DF)
这是我的数据集类.
from torch.utils.data import Dataset, DataLoader
class MyDataset(Dataset):
def __init__(self, result):
headers = list(result)
headers.remove('classes')
self.x_data = result[headers]
self.y_data = result['classes']
self.len = self.x_data.shape[0]
def __getitem__(self, index):
x = torch.tensor(self.x_data.iloc[index].values, dtype=torch.float)
y = torch.tensor(self.y_data.iloc[index], dtype=torch.float)
return (x, y)
def __len__(self):
return self.len
准备train_loader和test_loader
train_size = int(0.5 * len(full_dataset))
test_size = len(full_dataset) - train_size
train_dataset, test_dataset = torch.utils.data.random_split(full_dataset, [train_size, test_size])
train_loader = DataLoader(dataset=train_dataset, batch_size=16, shuffle=True, num_workers=1)
test_loader = DataLoader(dataset=train_dataset)
这是我的 csv
文件
当我尝试迭代 train_loader
时.它引发了错误
When I try to iterate over the train_loader
. It raises the error
for i , (data, target) in enumerate(train_loader):
print(i)
TypeError Traceback (most recent call last)
<ipython-input-32-0b4921c3fe8c> in <module>
----> 1 for i , (data, target) in enumerate(train_loader):
2 print(i)
/opt/conda/lib/python3.6/site-packages/torch/utils/data/dataloader.py in __next__(self)
635 self.reorder_dict[idx] = batch
636 continue
--> 637 return self._process_next_batch(batch)
638
639 next = __next__ # Python 2 compatibility
/opt/conda/lib/python3.6/site-packages/torch/utils/data/dataloader.py in _process_next_batch(self, batch)
656 self._put_indices()
657 if isinstance(batch, ExceptionWrapper):
--> 658 raise batch.exc_type(batch.exc_msg)
659 return batch
660
TypeError: Traceback (most recent call last):
File "/opt/conda/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 138, in _worker_loop
samples = collate_fn([dataset[i] for i in batch_indices])
File "/opt/conda/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 138, in <listcomp>
samples = collate_fn([dataset[i] for i in batch_indices])
File "/opt/conda/lib/python3.6/site-packages/torch/utils/data/dataset.py", line 103, in __getitem__
return self.dataset[self.indices[idx]]
File "<ipython-input-27-107e03bc3c6a>", line 12, in __getitem__
x = torch.tensor(self.x_data.iloc[index].values, dtype=torch.float)
File "/opt/conda/lib/python3.6/site-packages/pandas/core/indexing.py", line 1478, in __getitem__
return self._getitem_axis(maybe_callable, axis=axis)
File "/opt/conda/lib/python3.6/site-packages/pandas/core/indexing.py", line 2091, in _getitem_axis
return self._get_list_axis(key, axis=axis)
File "/opt/conda/lib/python3.6/site-packages/pandas/core/indexing.py", line 2070, in _get_list_axis
return self.obj._take(key, axis=axis)
File "/opt/conda/lib/python3.6/site-packages/pandas/core/generic.py", line 2789, in _take
verify=True)
File "/opt/conda/lib/python3.6/site-packages/pandas/core/internals.py", line 4537, in take
new_labels = self.axes[axis].take(indexer)
File "/opt/conda/lib/python3.6/site-packages/pandas/core/indexes/base.py", line 2195, in take
return self._shallow_copy(taken)
File "/opt/conda/lib/python3.6/site-packages/pandas/core/indexes/range.py", line 267, in _shallow_copy
return self._int64index._shallow_copy(values, **kwargs)
File "/opt/conda/lib/python3.6/site-packages/pandas/core/indexes/numeric.py", line 68, in _shallow_copy
return self._shallow_copy_with_infer(values=values, **kwargs)
File "/opt/conda/lib/python3.6/site-packages/pandas/core/indexes/base.py", line 538, in _shallow_copy_with_infer
if not len(values) and 'dtype' not in kwargs:
TypeError: object of type 'numpy.int64' has no len()
相关问题:
https://github.com/pytorch/pytorch/issues/10165
https://github.com/pytorch/pytorch/pull/9237
https://github.com/pandas-dev/pandas/issues/21946
问题:
如何在此处解决 pandas
问题?
推荐答案
参考:
https://github.com/pytorch/pytorch/issues/9211
只需将 .tolist()
添加到 indices
行.
Just add .tolist()
to indices
line.
def random_split(dataset, lengths):
"""
Randomly split a dataset into non-overlapping new datasets of given lengths.
Arguments:
dataset (Dataset): Dataset to be split
lengths (sequence): lengths of splits to be produced
"""
if sum(lengths) != len(dataset):
raise ValueError("Sum of input lengths does not equal the length of the input dataset!")
indices = randperm(sum(lengths)).tolist()
return [Subset(dataset, indices[offset - length:offset]) for offset, length in zip(_accumulate(lengths), lengths)]
这篇关于TypeError:“numpy.int64"类型的对象没有 len()的文章就介绍到这了,希望我们推荐的答案对大家有所帮助,也希望大家多多支持跟版网!