Spaces:
Running
on
Zero
Running
on
Zero
File size: 6,782 Bytes
938e515 |
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 |
#!/usr/bin/env python
# -*- encoding: utf-8 -*-
"""
@Author : Peike Li
@Contact : peike.li@yahoo.com
@File : datasets.py
@Time : 8/4/19 3:35 PM
@Desc :
@License : This source code is licensed under the license found in the
LICENSE file in the root directory of this source tree.
"""
import os
import numpy as np
import random
import torch
import cv2
from torch.utils import data
from utils.transforms import get_affine_transform
class CropDataSet(data.Dataset):
def __init__(self, root, split_name, crop_size=[473, 473], scale_factor=0.25,
rotation_factor=30, ignore_label=255, transform=None):
self.root = root
self.aspect_ratio = crop_size[1] * 1.0 / crop_size[0]
self.crop_size = np.asarray(crop_size)
self.ignore_label = ignore_label
self.scale_factor = scale_factor
self.rotation_factor = rotation_factor
self.flip_prob = 0.5
self.transform = transform
self.split_name = split_name
list_path = os.path.join(self.root, self.split_name + '.txt')
train_list = [i_id.strip() for i_id in open(list_path)]
self.train_list = train_list
self.number_samples = len(self.train_list)
def __len__(self):
return self.number_samples
def _box2cs(self, box):
x, y, w, h = box[:4]
return self._xywh2cs(x, y, w, h)
def _xywh2cs(self, x, y, w, h):
center = np.zeros((2), dtype=np.float32)
center[0] = x + w * 0.5
center[1] = y + h * 0.5
if w > self.aspect_ratio * h:
h = w * 1.0 / self.aspect_ratio
elif w < self.aspect_ratio * h:
w = h * self.aspect_ratio
scale = np.array([w * 1.0, h * 1.0], dtype=np.float32)
return center, scale
def __getitem__(self, index):
train_item = self.train_list[index]
im_path = os.path.join(self.root, self.split_name + '_images', train_item + '.jpg')
parsing_anno_path = os.path.join(self.root, self.split_name + '_segmentations', train_item + '.png')
im = cv2.imread(im_path, cv2.IMREAD_COLOR)
h, w, _ = im.shape
parsing_anno = np.zeros((h, w), dtype=np.long)
# Get person center and scale
person_center, s = self._box2cs([0, 0, w - 1, h - 1])
r = 0
if self.split_name != 'test':
# Get pose annotation
parsing_anno = cv2.imread(parsing_anno_path, cv2.IMREAD_GRAYSCALE)
sf = self.scale_factor
rf = self.rotation_factor
s = s * np.clip(np.random.randn() * sf + 1, 1 - sf, 1 + sf)
r = np.clip(np.random.randn() * rf, -rf * 2, rf * 2) if random.random() <= 0.6 else 0
if random.random() <= self.flip_prob:
im = im[:, ::-1, :]
parsing_anno = parsing_anno[:, ::-1]
person_center[0] = im.shape[1] - person_center[0] - 1
right_idx = [15, 17, 19]
left_idx = [14, 16, 18]
for i in range(0, 3):
right_pos = np.where(parsing_anno == right_idx[i])
left_pos = np.where(parsing_anno == left_idx[i])
parsing_anno[right_pos[0], right_pos[1]] = left_idx[i]
parsing_anno[left_pos[0], left_pos[1]] = right_idx[i]
trans = get_affine_transform(person_center, s, r, self.crop_size)
input = cv2.warpAffine(
im,
trans,
(int(self.crop_size[1]), int(self.crop_size[0])),
flags=cv2.INTER_LINEAR,
borderMode=cv2.BORDER_CONSTANT,
borderValue=(0, 0, 0))
if self.transform:
input = self.transform(input)
meta = {
'name': train_item,
'center': person_center,
'height': h,
'width': w,
'scale': s,
'rotation': r
}
if self.split_name == 'val' or self.split_name == 'test':
return input, meta
else:
label_parsing = cv2.warpAffine(
parsing_anno,
trans,
(int(self.crop_size[1]), int(self.crop_size[0])),
flags=cv2.INTER_NEAREST,
borderMode=cv2.BORDER_CONSTANT,
borderValue=(255))
label_parsing = torch.from_numpy(label_parsing)
return input, label_parsing, meta
class CropDataValSet(data.Dataset):
def __init__(self, root, split_name='crop_pic', crop_size=[473, 473], transform=None, flip=False):
self.root = root
self.crop_size = crop_size
self.transform = transform
self.flip = flip
self.split_name = split_name
self.root = root
self.aspect_ratio = crop_size[1] * 1.0 / crop_size[0]
self.crop_size = np.asarray(crop_size)
list_path = os.path.join(self.root, self.split_name + '.txt')
val_list = [i_id.strip() for i_id in open(list_path)]
self.val_list = val_list
self.number_samples = len(self.val_list)
def __len__(self):
return len(self.val_list)
def _box2cs(self, box):
x, y, w, h = box[:4]
return self._xywh2cs(x, y, w, h)
def _xywh2cs(self, x, y, w, h):
center = np.zeros((2), dtype=np.float32)
center[0] = x + w * 0.5
center[1] = y + h * 0.5
if w > self.aspect_ratio * h:
h = w * 1.0 / self.aspect_ratio
elif w < self.aspect_ratio * h:
w = h * self.aspect_ratio
scale = np.array([w * 1.0, h * 1.0], dtype=np.float32)
return center, scale
def __getitem__(self, index):
val_item = self.val_list[index]
# Load training image
im_path = os.path.join(self.root, self.split_name, val_item + '.jpg')
im = cv2.imread(im_path, cv2.IMREAD_COLOR)
h, w, _ = im.shape
# Get person center and scale
person_center, s = self._box2cs([0, 0, w - 1, h - 1])
r = 0
trans = get_affine_transform(person_center, s, r, self.crop_size)
input = cv2.warpAffine(
im,
trans,
(int(self.crop_size[1]), int(self.crop_size[0])),
flags=cv2.INTER_LINEAR,
borderMode=cv2.BORDER_CONSTANT,
borderValue=(0, 0, 0))
input = self.transform(input)
flip_input = input.flip(dims=[-1])
if self.flip:
batch_input_im = torch.stack([input, flip_input])
else:
batch_input_im = input
meta = {
'name': val_item,
'center': person_center,
'height': h,
'width': w,
'scale': s,
'rotation': r
}
return batch_input_im, meta
|