-
Notifications
You must be signed in to change notification settings - Fork 0
/
make_dataset.py
168 lines (123 loc) · 4.39 KB
/
make_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
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
#!/usr/bin/env python
# coding: utf-8
# In[1]:
import h5py
import scipy.io as io
import PIL.Image as Image
import numpy as np
import os
import glob
from matplotlib import pyplot as plt
from scipy.ndimage.filters import gaussian_filter
import scipy
import json
from matplotlib import cm as CM
from image import *
from model import CSRNet
import torch
import os
import cv2 as cv
os.environ['CUDA_DEVICE_ORDER'] = 'PCI_BUS_ID'
os.environ["CUDA_VISIBLE_DEVICES"] = "0"
#from IPython import get_ipython
#get_ipython().magic(u'matplotlib inline')
# In[ ]:
#this is borrowed from https://github.com/davideverona/deep-crowd-counting_crowdnet
def gaussian_filter_density(gt):
print (gt.shape)
density = np.zeros(gt.shape, dtype=np.float32)
gt_count = np.count_nonzero(gt)
print(gt_count)#me
if gt_count == 0:
return density
pts = np.array(list(zip(np.nonzero(gt)[1], np.nonzero(gt)[0])))
leafsize = 2048
# build kdtree
tree = scipy.spatial.KDTree(pts.copy(), leafsize=leafsize)
# query kdtree
distances, locations = tree.query(pts, k=4)
print ('generate density...')
for i, pt in enumerate(pts):
pt2d = np.zeros(gt.shape, dtype=np.float32)
pt2d[pt[1],pt[0]] = 1.
if gt_count > 1:
sigma = (distances[i][1]+distances[i][2]+distances[i][3])*0.1
else:
sigma = np.average(np.array(gt.shape))/2./2. #case: 1 point
density += scipy.ndimage.filters.gaussian_filter(pt2d, sigma, mode='constant')
print ('done.')
return density
# In[2]:
#set the root to the ShanghaiTech_Crowd_Counting_Dataset dataset you download
root = 'ShanghaiTech_Crowd_Counting_Dataset/'
# In[3]:
#now generate the ShanghaiTech_Crowd_Counting_DatasetA's ground truth
part_A_train = os.path.join(root,'part_A_final/train_data','images')
part_A_test = os.path.join(root,'part_A_final/test_data','images')
part_B_train = os.path.join(root,'part_B_final/train_data','images')
part_B_test = os.path.join(root,'part_B_final/test_data','images')
#path_sets = [part_A_train,part_A_test]
'''
print(os.listdir(root))
# # In[4]:
img_paths = []
for path in path_sets:
for img_path in glob.glob(os.path.join(path, '*.jpg')):
img_paths.append(img_path)
print("hello")
print(root)
# In[ ]:
for img_path in img_paths:
print (img_path)
mat = io.loadmat(img_path.replace('.jpg','.mat').replace('images','ground_truth').replace('IMG_','GT_IMG_'))
img= plt.imread(img_path)
k = np.zeros((img.shape[0],img.shape[1]))
gt = mat["image_info"][0,0][0,0][0]
for i in range(0,len(gt)):
if int(gt[i][1])<img.shape[0] and int(gt[i][0])<img.shape[1]:
k[int(gt[i][1]),int(gt[i][0])]=1
k = gaussian_filter_density(k)
with h5py.File(img_path.replace('.jpg','.h5').replace('images','ground_truth'), 'w') as hf:
hf['density'] = k
print("k",k)
'''
# In[ ]:
#now see a sample from ShanghaiTech_Crowd_Counting_DatasetA
#plt.imshow(Image.open(img_paths[0]))
# In[ ]:
'''
gt_file = h5py.File(img_paths[0].replace('.jpg','.h5').replace('images','ground_truth'),'r')
groundtruth = np.asarray(gt_file['density'])
#plt.imshow(groundtruth,cmap=CM.jet)
print("Sum = " ,np.sum(groundtruth))
# In[ ]:
np.sum(groundtruth)# don't mind this slight variation
# In[ ]:
'''
#now generate the ShanghaiTech_Crowd_Counting_DatasetB's ground truth
path_sets = [part_B_train,part_B_test]
# In[ ]:
img_paths = []
for path in path_sets:
for img_path in glob.glob(os.path.join(path, '*.jpg')):
img_paths.append(img_path)
# In[ ]:
for img_path in img_paths:
#print (img_path)
mat = io.loadmat(img_path.replace('.jpg','.mat').replace('images','ground_truth').replace('IMG_','GT_IMG_'))
img= plt.imread(img_path)
k = np.zeros((img.shape[0],img.shape[1]))
gt = mat["image_info"][0,0][0,0][0]
for i in range(0,len(gt)):
if int(gt[i][1])<img.shape[0] and int(gt[i][0])<img.shape[1]:
k[int(gt[i][1]),int(gt[i][0])]=1
k = gaussian_filter(k,15)
with h5py.File(img_path.replace('.jpg','.h5').replace('images','ground_truth'), 'w') as hf:
hf['density'] = k
gt_file = h5py.File(img_paths[0].replace('.jpg','.h5').replace('images','ground_truth'),'r')
groundtruth = np.asarray(gt_file['density'])
#plt.imshow(groundtruth,cmap=CM.jet)
plt.savefig('save/save.png')
print("Sum = " ,np.sum(groundtruth))
# In[ ]:
np.sum(groundtruth)# don't mind this slight variation