File size: 7,018 Bytes
e551dda |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 |
import torch.utils.data as data
import os
import os.path
import torch
import numpy as np
import pandas as pd
import sys
import pickle
import time
import torchvision.datasets as datasets
import torchvision.transforms as transforms
from PIL import Image
from typing import Any, Callable, cast, Dict, List, Optional, Tuple, Union
from torchvision.datasets import VisionDataset
from torch.utils.data import Dataset
from datetime import date, timedelta,datetime
import random
import pickle as pkl
import string
valid_chars = 'EFHILOTUYZ'
alphabetic_labels = [char1 + char2 for char1 in valid_chars for char2 in valid_chars]
alphabetic_labels.sort()
label_mapping = {label: idx for idx, label in enumerate(alphabetic_labels)} # to number
reverse_label_mapping = {v: k for k, v in label_mapping.items()} # to alphabetic
single_alphabetic_labels=[char1 for char1 in valid_chars]
single_alphabetic_labels.sort()
single_label_mapping = {label: idx for idx, label in enumerate(single_alphabetic_labels)}
single_reverse_label_mapping = {v: k for k, v in single_label_mapping.items()}
def get_mnist_dataset(data_dir='data/multi_mnist.pkl',Seed=0,test_ratio=0.2):
random.seed(Seed)
torch.manual_seed(Seed)
np.random.seed(Seed)
with open(data_dir, 'rb') as f:
dataset = pkl.load(f)
for entry in dataset:
entry.y -= 10
np.random.shuffle(dataset)
val_test_split = int(np.around( test_ratio * len(dataset) ))
train_val_split = int(len(dataset)-2*val_test_split)
train_ds = dataset[:train_val_split]
val_ds = dataset[train_val_split:train_val_split+val_test_split]
test_ds = dataset[train_val_split+val_test_split:]
print(data_dir)
print('Train: ' +str(len(train_ds)))
print('Val : ' +str(len(val_ds)))
print('Test : ' +str(len(test_ds)))
return train_ds,val_ds,test_ds
def get_building_dataset(data_dir='data/building_with_index.pkl',Seed=0,test_ratio=0.2):
random.seed(Seed)
torch.manual_seed(Seed)
np.random.seed(Seed)
with open(data_dir, 'rb') as f:
dataset = pkl.load(f)
for entry in dataset:
entry.y = label_mapping[entry.y]
np.random.shuffle(dataset)
val_test_split = int(np.around( test_ratio * len(dataset) ))
train_val_split = int(len(dataset)-2*val_test_split)
train_ds = dataset[:train_val_split]
val_ds = dataset[train_val_split:train_val_split+val_test_split]
test_ds = dataset[train_val_split+val_test_split:]
print(data_dir)
print('Train: ' +str(len(train_ds)))
print('Val : ' +str(len(val_ds)))
print('Test : ' +str(len(test_ds)))
return train_ds,val_ds,test_ds
def get_mbuilding_dataset(data_dir='data/mp_building.pkl',Seed=0,test_ratio=0.2):
random.seed(Seed)
torch.manual_seed(Seed)
np.random.seed(Seed)
with open(data_dir, 'rb') as f:
dataset = pkl.load(f)
for entry in dataset:
entry.y = label_mapping[entry.y]
np.random.shuffle(dataset)
val_test_split = int(np.around( test_ratio * len(dataset) ))
train_val_split = int(len(dataset)-2*val_test_split)
train_ds = dataset[:train_val_split]
val_ds = dataset[train_val_split:train_val_split+val_test_split]
test_ds = dataset[train_val_split+val_test_split:]
print(data_dir)
print('Train: ' +str(len(train_ds)))
print('Val : ' +str(len(val_ds)))
print('Test : ' +str(len(test_ds)))
return train_ds,val_ds,test_ds
def get_sbuilding_dataset(data_dir='data/single_building.pkl',Seed=0,test_ratio=0.2):
random.seed(Seed)
torch.manual_seed(Seed)
np.random.seed(Seed)
with open(data_dir, 'rb') as f:
dataset = pkl.load(f)
for entry in dataset:
entry.y = single_label_mapping[entry.y]
np.random.shuffle(dataset)
val_test_split = int(np.around( test_ratio * len(dataset) ))
train_val_split = int(len(dataset)-2*val_test_split)
train_ds = dataset[:train_val_split]
val_ds = dataset[train_val_split:train_val_split+val_test_split]
test_ds = dataset[train_val_split+val_test_split:]
print(data_dir)
print('Train: ' +str(len(train_ds)))
print('Val : ' +str(len(val_ds)))
print('Test : ' +str(len(test_ds)))
return train_ds,val_ds,test_ds
def get_smnist_dataset(data_dir='data/single_mnist.pkl',Seed=0,test_ratio=0.2):
random.seed(Seed)
torch.manual_seed(Seed)
np.random.seed(Seed)
with open(data_dir, 'rb') as f:
dataset = pkl.load(f)
np.random.shuffle(dataset)
val_test_split = int(np.around( test_ratio * len(dataset) ))
train_val_split = int(len(dataset)-2*val_test_split)
train_ds = dataset[:train_val_split]
val_ds = dataset[train_val_split:train_val_split+val_test_split]
test_ds = dataset[train_val_split+val_test_split:]
print(data_dir)
print('Train: ' +str(len(train_ds)))
print('Val : ' +str(len(val_ds)))
print('Test : ' +str(len(test_ds)))
return train_ds,val_ds,test_ds
def get_dbp_dataset(data_dir='data/triple_building.pkl',Seed=0,test_ratio=0.2):
random.seed(Seed)
torch.manual_seed(Seed)
np.random.seed(Seed)
with open(data_dir, 'rb') as f:
dataset = pkl.load(f)
for entry in dataset:
entry.y = 1 if entry.y>=1 else 0
np.random.shuffle(dataset)
val_test_split = int(np.around( test_ratio * len(dataset) ))
train_val_split = int(len(dataset)-2*val_test_split)
train_ds = dataset[:train_val_split]
val_ds = dataset[train_val_split:train_val_split+val_test_split]
test_ds = dataset[train_val_split+val_test_split:]
print(data_dir)
print('Train: ' +str(len(train_ds)))
print('Val : ' +str(len(val_ds)))
print('Test : ' +str(len(test_ds)))
return train_ds,val_ds,test_ds
def affine_transform_to_range(ds, target_range=(-1, 1)):
# Find the extent (min and max) of coordinates in both x and y directions
for item in ds:
min_x = torch.min(item.pos[:,0])
min_y = torch.min(item.pos[:,1])
max_x = torch.max(item.pos[:,0])
max_y = torch.max(item.pos[:,1])
scale_x = (target_range[1] - target_range[0]) / (max_x - min_x)
scale_y = (target_range[1] - target_range[0]) / (max_y - min_y)
translate_x = target_range[0] - min_x * scale_x
translate_y = target_range[0] - min_y * scale_y
# Apply the affine transformation to
item.pos[:,0] = item.pos[:,0] * scale_x + translate_x
item.pos[:,1] = item.pos[:,1] * scale_y + translate_y
return ds
class CustomDataset(Dataset):
def __init__(self, data_list):
super(CustomDataset, self).__init__()
self.data_list = data_list
def len(self):
return len(self.data_list)
def get(self, idx):
return self.data_list[idx]
if __name__ == '__main__':
a,b,c=get_mnist_dataset()
print("") |