-
Notifications
You must be signed in to change notification settings - Fork 50
/
edit_dataset.py
131 lines (105 loc) · 4.52 KB
/
edit_dataset.py
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
from __future__ import annotations
import json
import math
from pathlib import Path
from typing import Any
import numpy as np
import torch
import torchvision
from einops import rearrange
from PIL import Image
from torch.utils.data import Dataset
from fnmatch import fnmatch
class EditDataset(Dataset):
def __init__(
self,
path: str,
split: str = "train",
splits: tuple[float, float, float] = (0.9, 0.05, 0.05),
min_resize_res: int = 256,
max_resize_res: int = 256,
crop_res: int = 256,
flip_prob: float = 0.0,
):
assert split in ("train", "val", "test")
assert sum(splits) == 1
self.path = path
self.min_resize_res = min_resize_res
self.max_resize_res = max_resize_res
self.crop_res = crop_res
self.flip_prob = flip_prob
with open(Path(self.path, "seeds.json")) as f:
self.seeds = json.load(f)
split_0, split_1 = {
"train": (0.0, splits[0]),
"val": (splits[0], splits[0] + splits[1]),
"test": (splits[0] + splits[1], 1.0),
}[split]
idx_0 = math.floor(split_0 * len(self.seeds))
idx_1 = math.floor(split_1 * len(self.seeds))
self.seeds = self.seeds[idx_0:idx_1]
def __len__(self) -> int:
return len(self.seeds)
def __getitem__(self, i: int) -> dict[str, Any]:
'''
Modified by Yulu Gan, Apr 10 ,2023
enable different postfix for image_0 and image_1. png for depes/seg label, jpg for else
'''
name, seeds = self.seeds[i]
propt_dir = Path(self.path, name)
seed = seeds[torch.randint(0, len(seeds), ()).item()]
with open(propt_dir.joinpath("prompt.json"),'r') as fp:
prompt = json.load(fp)["edit"]
if fnmatch(seed, "*det*") or fnmatch(seed, "*cls*"):
image_0 = Image.open(propt_dir.joinpath(f"{seed}_0.jpg"))
image_1 = Image.open(propt_dir.joinpath(f"{seed}_1.jpg"))
else:
image_0 = Image.open(propt_dir.joinpath(f"{seed}_0.jpg"))
image_1 = Image.open(propt_dir.joinpath(f"{seed}_1.png"))
reize_res = torch.randint(self.min_resize_res, self.max_resize_res + 1, ()).item()
image_0 = image_0.resize((reize_res, reize_res), Image.Resampling.LANCZOS)
image_1 = image_1.resize((reize_res, reize_res), Image.Resampling.LANCZOS)
image_0 = rearrange(2 * torch.tensor(np.array(image_0)).float() / 255 - 1, "h w c -> c h w")
image_1 = rearrange(2 * torch.tensor(np.array(image_1)).float() / 255 - 1, "h w c -> c h w")
crop = torchvision.transforms.RandomCrop(self.crop_res)
flip = torchvision.transforms.RandomHorizontalFlip(float(self.flip_prob))
image_0, image_1 = flip(crop(torch.cat((image_0, image_1)))).chunk(2)
return dict(edited=image_1, edit=dict(c_concat=image_0, c_crossattn=prompt))
class EditDatasetEval(Dataset):
def __init__(
self,
path: str,
split: str = "train",
splits: tuple[float, float, float] = (0.9, 0.05, 0.05),
res: int = 256,
):
assert split in ("train", "val", "test")
assert sum(splits) == 1
self.path = path
self.res = res
with open(Path(self.path, "seeds.json")) as f:
self.seeds = json.load(f)
split_0, split_1 = {
"train": (0.0, splits[0]),
"val": (splits[0], splits[0] + splits[1]),
"test": (splits[0] + splits[1], 1.0),
}[split]
idx_0 = math.floor(split_0 * len(self.seeds))
idx_1 = math.floor(split_1 * len(self.seeds))
self.seeds = self.seeds[idx_0:idx_1]
def __len__(self) -> int:
return len(self.seeds)
def __getitem__(self, i: int) -> dict[str, Any]:
name, seeds = self.seeds[i]
propt_dir = Path(self.path, name)
seed = seeds[torch.randint(0, len(seeds), ()).item()]
with open(propt_dir.joinpath("prompt.json")) as fp:
prompt = json.load(fp)
edit = prompt["edit"]
input_prompt = prompt["input"]
output_prompt = prompt["output"]
image_0 = Image.open(propt_dir.joinpath(f"{seed}_0.jpg"))
reize_res = torch.randint(self.res, self.res + 1, ()).item()
image_0 = image_0.resize((reize_res, reize_res), Image.Resampling.LANCZOS)
image_0 = rearrange(2 * torch.tensor(np.array(image_0)).float() / 255 - 1, "h w c -> c h w")
return dict(image_0=image_0, input_prompt=input_prompt, edit=edit, output_prompt=output_prompt)