File size: 6,386 Bytes
fb238e8 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 |
# -*- encoding: utf-8 -*-
'''
Copyright 2022 The International Digital Economy Academy (IDEA). CCNL team. All rights reserved.
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
@File : dreambooth_datasets.py
@Time : 2022/11/10 00:20
@Author : Gan Ruyi
@Version : 1.0
@Contact : ganruyi@idea.edu.cn
@License : (C)Copyright 2022-2023, CCNL-IDEA
'''
from torch.utils.data import Dataset
from torchvision import transforms
from PIL import Image
from pathlib import Path
def add_data_args(parent_args):
parser = parent_args.add_argument_group('taiyi stable diffusion data args')
parser.add_argument(
"--instance_data_dir",
type=str,
default=None,
required=True,
help="A folder containing the training data of instance images.",
)
parser.add_argument(
"--class_data_dir",
type=str,
default=None,
required=False,
help="A folder containing the training data of class images.",
)
parser.add_argument(
"--instance_prompt",
type=str,
default=None,
help="The prompt with identifier specifying the instance",
)
parser.add_argument(
"--class_prompt",
type=str,
default=None,
help="The prompt to specify images in the same class as provided instance images.",
)
parser.add_argument(
"--with_prior_preservation",
default=False,
action="store_true",
help="Flag to add prior preservation loss.",
)
parser.add_argument("--prior_loss_weight", type=float, default=1.0, help="The weight of prior preservation loss.")
parser.add_argument(
"--num_class_images",
type=int,
default=100,
help=(
"Minimal class images for prior preservation loss. If not have enough images, additional images will be"
" sampled with class_prompt."
),
)
parser.add_argument(
"--resolution", type=int, default=512,
help=(
"The resolution for input images, all the images in the train/validation dataset will be resized to this"
" resolution"
),
)
parser.add_argument(
"--center_crop", action="store_true", default=False,
help="Whether to center crop images before resizing to resolution"
)
parser.add_argument(
"--sample_batch_size", type=int, default=4, help="Batch size (per device) for sampling images."
)
return parent_args
class DreamBoothDataset(Dataset):
"""
A dataset to prepare the instance and class images with the prompts for fine-tuning the model.
It pre-processes the images and the tokenizes prompts.
"""
def __init__(
self,
instance_data_dir,
instance_prompt,
tokenizer,
class_data_dir=None,
class_prompt=None,
size=512,
center_crop=False,
):
self.size = size
self.center_crop = center_crop
self.tokenizer = tokenizer
self.instance_data_dir = Path(instance_data_dir)
if not self.instance_data_dir.exists():
raise ValueError("Instance images root doesn't exists.")
self.instance_images_path = list(Path(instance_data_dir).iterdir())
print(self.instance_images_path)
self.num_instance_images = len(self.instance_images_path)
self.instance_prompt = instance_prompt
self._length = self.num_instance_images
if class_data_dir is not None:
self.class_data_dir = Path(class_data_dir)
self.class_data_dir.mkdir(parents=True, exist_ok=True)
self.class_images_path = list(self.class_data_dir.iterdir())
self.num_class_images = len(self.class_images_path)
self._length = max(self.num_class_images, self.num_instance_images)
self.class_prompt = class_prompt
else:
self.class_data_dir = None
self.image_transforms = transforms.Compose(
[
transforms.Resize(size, interpolation=transforms.InterpolationMode.BILINEAR),
transforms.CenterCrop(size) if center_crop else transforms.RandomCrop(size),
transforms.ToTensor(),
transforms.Normalize([0.5], [0.5]),
]
)
def __len__(self):
return self._length
def __getitem__(self, index):
example = {}
instance_image = Image.open(self.instance_images_path[index % self.num_instance_images])
if not instance_image.mode == "RGB":
instance_image = instance_image.convert("RGB")
example["instance_images"] = self.image_transforms(instance_image)
example["instance_prompt_ids"] = self.tokenizer(
self.instance_prompt,
padding="do_not_pad",
truncation=True,
max_length=64,
# max_length=self.tokenizer.model_max_length,
).input_ids
if self.class_data_dir:
class_image = Image.open(self.class_images_path[index % self.num_class_images])
if not class_image.mode == "RGB":
class_image = class_image.convert("RGB")
example["class_images"] = self.image_transforms(class_image)
example["class_prompt_ids"] = self.tokenizer(
self.class_prompt,
padding="do_not_pad",
truncation=True,
# max_length=self.tokenizer.model_max_length,
max_length=64,
).input_ids
return example
class PromptDataset(Dataset):
"A simple dataset to prepare the prompts to generate class images on multiple GPUs."
def __init__(self, prompt, num_samples):
self.prompt = prompt
self.num_samples = num_samples
def __len__(self):
return self.num_samples
def __getitem__(self, index):
example = {}
example["prompt"] = self.prompt
example["index"] = index
return example
|