-
Notifications
You must be signed in to change notification settings - Fork 0
/
det_batch.py
175 lines (150 loc) · 6.85 KB
/
det_batch.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
# Licensed to the Apache Software Foundation (ASF) under one
# or more contributor license agreements. See the NOTICE file
# distributed with this work for additional information
# regarding copyright ownership. The ASF licenses this file
# to you under the Apache License, Version 2.0 (the
# "License"); you may not use this file except in compliance
# with the License. You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing,
# software distributed under the License is distributed on an
# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
# KIND, either express or implied. See the License for the
# specific language governing permissions and limitations
# under the License.
import argparse
import os
import cv2
import mxnet as mx
import numpy as np
from rcnn.logger import logger
from rcnn.config import config
from rcnn.symbol import get_vgg_test
from rcnn.io.image import resize, transform
from rcnn.core.tester import Predictor, im_detect, im_proposal, vis_all_detection, draw_all_detection
from rcnn.utils.load_model import load_param
from rcnn.processing.nms import py_nms_wrapper, cpu_nms_wrapper, gpu_nms_wrapper
CLASSES = ('__background__','face')
config.TEST.HAS_RPN = True
SHORT_SIDE = config.SCALES[0][0]
LONG_SIDE = config.SCALES[0][1]
PIXEL_MEANS = config.PIXEL_MEANS
DATA_NAMES = ['data', 'im_info']
LABEL_NAMES = None
DATA_SHAPES = [('data', (1, 3, LONG_SIDE, SHORT_SIDE)), ('im_info', (1, 3))]
LABEL_SHAPES = None
# visualization
#CONF_THRESH = 0.7
CONF_THRESH = 0.9
NMS_THRESH = 0.3
nms = py_nms_wrapper(NMS_THRESH)
def get_net(symbol, prefix, epoch, ctx):
arg_params, aux_params = load_param(prefix, epoch, convert=True, ctx=ctx, process=True)
# infer shape
data_shape_dict = dict(DATA_SHAPES)
arg_names, aux_names = symbol.list_arguments(), symbol.list_auxiliary_states()
arg_shape, _, aux_shape = symbol.infer_shape(**data_shape_dict)
arg_shape_dict = dict(zip(arg_names, arg_shape))
aux_shape_dict = dict(zip(aux_names, aux_shape))
# check shapes
for k in symbol.list_arguments():
if k in data_shape_dict or 'label' in k:
continue
assert k in arg_params, k + ' not initialized'
assert arg_params[k].shape == arg_shape_dict[k], \
'shape inconsistent for ' + k + ' inferred ' + str(arg_shape_dict[k]) + ' provided ' + str(arg_params[k].shape)
for k in symbol.list_auxiliary_states():
assert k in aux_params, k + ' not initialized'
assert aux_params[k].shape == aux_shape_dict[k], \
'shape inconsistent for ' + k + ' inferred ' + str(aux_shape_dict[k]) + ' provided ' + str(aux_params[k].shape)
predictor = Predictor(symbol, DATA_NAMES, LABEL_NAMES, context=ctx,
provide_data=DATA_SHAPES, provide_label=LABEL_SHAPES,
arg_params=arg_params, aux_params=aux_params)
return predictor
def generate_batch(im):
"""
preprocess image, return batch
:param im: cv2.imread returns [height, width, channel] in BGR
:return:
data_batch: MXNet input batch
data_names: names in data_batch
im_scale: float number
"""
im_array, im_scale = resize(im, SHORT_SIDE, LONG_SIDE)
im_array = transform(im_array, PIXEL_MEANS)
im_info = np.array([[im_array.shape[2], im_array.shape[3], im_scale]], dtype=np.float32)
data = [mx.nd.array(im_array), mx.nd.array(im_info)]
data_shapes = [('data', im_array.shape), ('im_info', im_info.shape)]
data_batch = mx.io.DataBatch(data=data, label=None, provide_data=data_shapes, provide_label=None)
return data_batch, DATA_NAMES, im_scale
def demo_net(predictor, image_name, result_txt,vis=False):
"""
generate data_batch -> im_detect -> post process
:param predictor: Predictor
:param image_name: image name
:param vis: will save as a new image if not visualized
:return: None
"""
assert os.path.exists(image_name), image_name + ' not found'
print image_name
im = cv2.imread(image_name)
data_batch, data_names, im_scale = generate_batch(im)
scores, boxes, data_dict = im_detect(predictor, data_batch, data_names, im_scale)
result_txt.write(image_name.split('/')[-2]+'/'+image_name.split('/')[-1]+'\n')
all_boxes = [[] for _ in CLASSES]
for cls in CLASSES:
cls_ind = CLASSES.index(cls)
cls_boxes = boxes[:, 4 * cls_ind:4 * (cls_ind + 1)]
cls_scores = scores[:, cls_ind, np.newaxis]
keep = np.where(cls_scores >= CONF_THRESH)[0]
dets = np.hstack((cls_boxes, cls_scores)).astype(np.float32)[keep, :]
keep = nms(dets)
all_boxes[cls_ind] = dets[keep, :]
boxes_this_image = [[]] + [all_boxes[j] for j in range(1, len(CLASSES))]
# print results
#logger.info('---class---')
#logger.info('[[x1, x2, y1, y2, confidence]]')
for ind, boxes in enumerate(boxes_this_image):
#print ind
if len(boxes) > 0:
logger.info('---%s---' % CLASSES[ind])
logger.info('%s' % boxes)
#print len(boxes)
for iii in range(0,len(boxes)):
result_txt.write(str(boxes[iii][0])+' '+str(boxes[iii][1])+' '+str(boxes[iii][2])+' '+str(boxes[iii][3])+' '+str(boxes[iii][4])+' ')
result_txt.write('\n')
#if vis:
# vis_all_detection(data_dict['data'].asnumpy(), boxes_this_image, CLASSES, im_scale)
#else:
# result_file = image_name.replace('.', '_result.')
# logger.info('results saved to %s' % result_file)
# im = draw_all_detection(data_dict['data'].asnumpy(), boxes_this_image, CLASSES, im_scale)
# cv2.imwrite(result_file, im)
def parse_args():
parser = argparse.ArgumentParser(description='Demonstrate a Faster R-CNN network')
parser.add_argument('--image_path', help='image_path', type=str)
parser.add_argument('--prefix', help='saved model prefix', type=str)
parser.add_argument('--epoch', help='epoch of pretrained model', type=int)
parser.add_argument('--gpu', help='GPU device to use', default=0, type=int)
parser.add_argument('--vis', help='display result', action='store_true')
args = parser.parse_args()
return args
def main():
args = parse_args()
ctx = mx.gpu(args.gpu)
symbol = get_vgg_test(num_classes=config.NUM_CLASSES, num_anchors=config.NUM_ANCHORS)
predictor = get_net(symbol, args.prefix, args.epoch, ctx)
txt_name = args.image_path[:-1]
result_txt = open(txt_name+'.txt','wb')
vis = False
for directory in os.listdir(args.image_path):
print directory[-4:]
if ((directory[-4:]!='.txt')and(directory[-4:]!='json'))and(directory!='cache'):
img_dir = args.image_path+directory
for img in os.listdir(img_dir):
demo_net(predictor, img_dir+'/' + img , result_txt, vis)
result_txt.close()
if __name__ == '__main__':
main()