[FIXED] Pytorch datasets.UDPOS.splits throwing error

Issue

I want to split the UDPOS dataset into train, valid, and test by fields. Below is my code-

import torch
import torch.nn as nn
import torch.optim as optim

from torchtext.legacy import data
from torchtext import datasets

SEED = 1234

random.seed(SEED)
np.random.seed(SEED)
torch.manual_seed(SEED)
torch.backends.cudnn.deterministic = True

TEXT = data.Field(lower = True)
UD_TAGS = data.Field(unk_token = None)
PTB_TAGS = data.Field(unk_token = None)

fields = (("text", TEXT), ("udtags", UD_TAGS), ("ptbtags", PTB_TAGS))

train_data, valid_data, test_data = datasets.UDPOS.splits(fields)

This code give me following error-

I am using Pytorch version - '1.10.2'.

How do I split the UDPOS dataset using fileds in the current version.

Solution

I solved the same problem by changing the code

from torchtext import datasets

to

from torchtext.legacy import datasets

Answered By - cottonlove