-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathpse_test.py
192 lines (155 loc) · 6.71 KB
/
pse_test.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
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
# -*- coding:utf-8 -*-
#psenet-PyTorch-test
import os
import cv2
import sys
import time
import collections
import torch
import argparse
import numpy as np
import torch.nn as nn
import torch.nn.functional as F
from torch.autograd import Variable
from torch.utils import data
from dataset import XHTestLoader
import models
import util
# c++ version pse based on opencv 3+
from pse import pse
# python pse
#from pypse import pse as pypse
def debug(idx, img_paths, imgs, output_root):
if not os.path.exists(output_root):
os.makedirs(output_root)
col = []
for i in range(len(imgs)):
row = []
for j in range(len(imgs[i])):
row.append(imgs[i][j])
res = np.concatenate(row, axis=1)
col.append(res)
res = np.concatenate(col, axis=0)
img_name = img_paths[idx].split('/')[-1]
print idx, '/', len(img_paths), img_name
cv2.imwrite(output_root + img_name, res)
def write_result_as_txt(image_name, bboxes, path):
filename = util.io.join_path(path, 'res_%s.txt'%(image_name))
lines = []
for b_idx, bbox in enumerate(bboxes):
values = [int(v) for v in bbox]
line = "%d, %d, %d, %d, %d, %d, %d, %d\n"%tuple(values)
lines.append(line)
util.io.write_lines(filename, lines)
def test(args):
data_loader = XHTestLoader(long_size=args.long_size)
test_loader = torch.utils.data.DataLoader(
data_loader,
batch_size=1,
shuffle=False,
num_workers=2,
drop_last=True)
# Setup Model
if args.arch == "resnet50":
model = models.resnet50(pretrained=True, num_classes=7, scale=args.scale)
elif args.arch == "resnet101":
model = models.resnet101(pretrained=True, num_classes=7, scale=args.scale)
elif args.arch == "resnet152":
model = models.resnet152(pretrained=True, num_classes=7, scale=args.scale)
for param in model.parameters():
param.requires_grad = False
model = model.cuda()
if args.resume is not None:
if os.path.isfile(args.resume):
print("Loading model and optimizer from checkpoint '{}'".format(args.resume))
checkpoint = torch.load(args.resume)
# model.load_state_dict(checkpoint['state_dict'])
d = collections.OrderedDict()
for key, value in checkpoint['state_dict'].items():
tmp = key[7:]
d[tmp] = value
model.load_state_dict(d)
print("Loaded checkpoint '{}' (epoch {})"
.format(args.resume, checkpoint['epoch']))
sys.stdout.flush()
else:
print("No checkpoint found at '{}'".format(args.resume))
sys.stdout.flush()
model.eval()
total_frame = 0.0
total_time = 0.0
for idx, (org_img, img) in enumerate(test_loader):
print('progress: %d / %d'%(idx, len(test_loader)))
sys.stdout.flush()
img = Variable(img.cuda(), volatile=True)
org_img = org_img.numpy().astype('uint8')[0]
text_box = org_img.copy()
torch.cuda.synchronize()
t0 = time.time()
outputs = model(img)
t1 = time.time()
score = torch.sigmoid(outputs[:, 0, :, :])
outputs = (torch.sign(outputs - args.binary_th) + 1) / 2
text = outputs[:, 0, :, :]
kernels = outputs[:, 0:args.kernel_num, :, :] * text
score = score.data.cpu().numpy()[0].astype(np.float32)
text = text.data.cpu().numpy()[0].astype(np.uint8)
kernels = kernels.data.cpu().numpy()[0].astype(np.uint8)
# c++ version pse
pred = pse(kernels, args.min_kernel_area / (args.scale * args.scale))
# python version pse
# pred = pypse(kernels, args.min_kernel_area / (args.scale * args.scale))
# scale = (org_img.shape[0] * 1.0 / pred.shape[0], org_img.shape[1] * 1.0 / pred.shape[1])
scale = (org_img.shape[1] * 1.0 / pred.shape[1], org_img.shape[0] * 1.0 / pred.shape[0])
label = pred
label_num = np.max(label) + 1
bboxes = []
for i in range(1, label_num):
points = np.array(np.where(label == i)).transpose((1, 0))[:, ::-1]
if points.shape[0] < args.min_area / (args.scale * args.scale):
continue
score_i = np.mean(score[label == i])
if score_i < args.min_score:
continue
rect = cv2.minAreaRect(points)
bbox = cv2.boxPoints(rect) * scale
bbox = bbox.astype('int32')
bboxes.append(bbox.reshape(-1))
torch.cuda.synchronize()
#end = time.time()
#total_frame += 1
#total_time += (end - start)
#print('fps: %.2f'%(total_frame / total_time))
#sys.stdout.flush()
#print(bboxes)
for bbox in bboxes:
cv2.drawContours(text_box, [bbox.reshape(4, 2)], -1, (0, 255, 0), 2)
image_name = data_loader.img_paths[idx].split('/')[-1].split('.')[0]
write_result_as_txt(image_name, bboxes, 'testdata_results/submit_txt/')
text_box = cv2.resize(text_box, (text.shape[1], text.shape[0]))
debug(idx, data_loader.img_paths, [[text_box]], 'testdata_results/vis_img/')
cmd = 'cd %s;zip -j %s %s/*'%('./testdata_results/', 'submit_txt.zip', 'submit_txt');
print(cmd)
sys.stdout.flush()
util.cmd.cmd(cmd)
if __name__ == '__main__':
parser = argparse.ArgumentParser(description='Hyperparams')
parser.add_argument('--arch', nargs='?', type=str, default='resnet50')
parser.add_argument('--resume', nargs='?', type=str, default="./checkpoints_1108_best/XH_resnet50_bs_8_ep_50/checkpoint.pth.tar",
help='Path to previous saved model to restart from')
parser.add_argument('--binary_th', nargs='?', type=float, default=1.0,
help='Path to previous saved model to restart from')
parser.add_argument('--kernel_num', nargs='?', type=int, default=7,
help='Path to previous saved model to restart from')
parser.add_argument('--scale', nargs='?', type=int, default=1,
help='Path to previous saved model to restart from')
parser.add_argument('--long_size', nargs='?', type=int, default=960,
help='Path to previous saved model to restart from')
parser.add_argument('--min_kernel_area', nargs='?', type=float, default=5.0,
help='min kernel area')
parser.add_argument('--min_area', nargs='?', type=float, default=800.0,
help='min area')
parser.add_argument('--min_score', nargs='?', type=float, default=0.93,
help='min score')
args = parser.parse_args()
test(args)