stable-diffusion-finetune/ldm/data/base.py

41 lines
1.2 KiB
Python
Raw Normal View History

2022-07-24 13:23:50 +02:00
import os
import numpy as np
2021-12-21 03:23:41 +01:00
from abc import abstractmethod
from torch.utils.data import Dataset, ConcatDataset, ChainDataset, IterableDataset
class Txt2ImgIterableBaseDataset(IterableDataset):
'''
Define an interface to make the IterableDatasets for text2img data chainable
'''
def __init__(self, num_records=0, valid_ids=None, size=256):
super().__init__()
self.num_records = num_records
self.valid_ids = valid_ids
self.sample_ids = valid_ids
self.size = size
print(f'{self.__class__.__name__} dataset contains {self.__len__()} examples.')
def __len__(self):
return self.num_records
@abstractmethod
def __iter__(self):
2022-07-24 13:23:50 +02:00
pass
class PRNGMixin(object):
"""
Adds a prng property which is a numpy RandomState which gets
reinitialized whenever the pid changes to avoid synchronized sampling
behavior when used in conjunction with multiprocessing.
"""
@property
def prng(self):
currentpid = os.getpid()
if getattr(self, "_initpid", None) != currentpid:
self._initpid = currentpid
self._prng = np.random.RandomState()
return self._prng