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
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
| #!/usr/bin/env python
#-*-coding:utf-8-*-
import matplotlib
matplotlib.use('Agg')
import _init_paths
from fast_rcnn.config import cfg
from fast_rcnn.test import im_detect
from fast_rcnn.nms_wrapper import nms
from utils.timer import Timer
import matplotlib.pyplot as plt
import numpy as np
import scipy.io as sio
import caffe, os, sys, cv2
import argparse
CLASSES = ('__background__',
'aeroplane', 'bicycle', 'bird', 'boat',
'bottle', 'bus', 'car', 'cat', 'chair',
'cow', 'diningtable', 'dog', 'horse',
'motorbike', 'person', 'pottedplant',
'sheep', 'sofa', 'train', 'tvmonitor')
NETS = {'vgg16': ('VGG16',
'VGG16_faster_rcnn_final.caffemodel'),
'zf': ('ZF',
'zf_faster_rcnn_iter_2000.caffemodel')}
def vis_detections(im, class_name, dets, thresh=0.5):
"""Draw detected bounding boxes."""
inds = np.where(dets[:, -1] >= thresh)[0]
if len(inds) == 0:
return
im = im[:, :, (2, 1, 0)]
fig, ax = plt.subplots(figsize=(12, 12))
ax.imshow(im, aspect='equal')
for i in inds:
bbox = dets[i, :4]
score = dets[i, -1]
ax.add_patch(
plt.Rectangle((bbox[0], bbox[1]),
bbox[2] - bbox[0],
bbox[3] - bbox[1], fill=False,
edgecolor='red', linewidth=3.5)
)
ax.text(bbox[0], bbox[1] - 2,
'{:s} {:.3f}'.format(class_name, score),
bbox=dict(facecolor='blue', alpha=0.5),
fontsize=14, color='white')
ax.set_title(('{} detections with '
'p({} | box) >= {:.1f}').format(class_name, class_name,
thresh),
fontsize=14)
plt.axis('off')
plt.tight_layout()
plt.draw()
def demo(net, image_name):
"""Detect object classes in an image using pre-computed object proposals."""
# Load the demo image
im_file = os.path.join(cfg.DATA_DIR, 'demo', image_name)
im = cv2.imread(im_file)
# Detect all object classes and regress object bounds
timer = Timer()
timer.tic()
scores, boxes = im_detect(net, im)
timer.toc()
print ('Detection took {:.3f}s for '
'{:d} object proposals').format(timer.total_time, boxes.shape[0])
# Visualize detections for each class
CONF_THRESH = 0.8
NMS_THRESH = 0.3
for cls_ind, cls in enumerate(CLASSES[1:]):
cls_ind += 1 # because we skipped background
cls_boxes = boxes[:, 4*cls_ind:4*(cls_ind + 1)]
cls_scores = scores[:, cls_ind]
dets = np.hstack((cls_boxes,
cls_scores[:, np.newaxis])).astype(np.float32)
keep = nms(dets, NMS_THRESH)
dets = dets[keep, :]
vis_detections(im, cls, dets, thresh=CONF_THRESH)
def parse_args():
"""Parse input arguments."""
parser = argparse.ArgumentParser(description='Faster R-CNN demo')
parser.add_argument('--gpu', dest='gpu_id', help='GPU device id to use [0]',
default=0, type=int)
parser.add_argument('--cpu', dest='cpu_mode',
help='Use CPU mode (overrides --gpu)',
action='store_true')
parser.add_argument('--net', dest='demo_net', help='Network to use [zf]',
choices=NETS.keys(), default='zf')
args = parser.parse_args()
return args
if __name__ == '__main__':
cfg.TEST.HAS_RPN = True # Use RPN for proposals
args = parse_args()
prototxt = os.path.join(cfg.MODELS_DIR, NETS[args.demo_net][0],
'faster_rcnn_alt_opt', 'faster_rcnn_test.pt')
caffemodel = os.path.join(cfg.DATA_DIR, 'faster_rcnn_models',
NETS[args.demo_net][1])
if not os.path.isfile(caffemodel):
raise IOError(('{:s} not found.\nDid you run ./data/script/'
'fetch_faster_rcnn_models.sh?').format(caffemodel))
if args.cpu_mode:
caffe.set_mode_cpu()
else:
caffe.set_mode_gpu()
caffe.set_device(args.gpu_id)
cfg.GPU_ID = args.gpu_id
net = caffe.Net(prototxt, caffemodel, caffe.TEST)
#指定caffe路径，以下是我的caffe路径
caffe_root='/home/ouyang/GitRepository/py-faster-rcnn/caffe-fast-rcnn/'
# import sys
sys.path.insert(0, caffe_root+'python')
# import caffe
# #显示的图表大小为 10,图形的插值是以最近为原则,图像颜色是灰色
plt.rcParams['figure.figsize'] = (10, 10)
plt.rcParams['image.interpolation'] = 'nearest'
plt.rcParams['image.cmap'] = 'gray'
image_file = caffe_root+'examples/images/vehicle_0000015.jpg'
# 载入模型
npload = caffe_root+ 'python/caffe/imagenet/ilsvrc_2012_mean.npy'
transformer = caffe.io.Transformer({'data': net.blobs['data'].data.shape})
transformer.set_transpose('data', (2,0,1))
transformer.set_mean('data', np.load(npload).mean(1).mean(1))
# 参考模型的灰度为0~255，而不是0~1
transformer.set_raw_scale('data', 255)
# 由于参考模型色彩是BGR,需要将其转换为RGB
transformer.set_channel_swap('data', (2,1,0))
im=caffe.io.load_image(image_file)
net.blobs['data'].reshape(1,3,224,224)
net.blobs['data'].data[...] = transformer.preprocess('data',im)
# 显示出各层的参数和形状，第一个是批次，第二个是feature map数目，第三和第四是每个神经元中图片的长和宽
print [(k,v.data.shape) for k,v in net.blobs.items()]
#输出网络参数
print [(k,v[0].data.shape) for k,v in net.params.items()]
def show_image(im):
if im.ndim==3:
m=im[:,:,::-1]
plt.imshow(im)
#显示图片的方法
plt.axis('off') # 不显示坐标轴
plt.show()
# 每个可视化的都是在一个由一个个网格组成
def vis_square(data,padsize=1,padval=0):
data-=data.min()
data/=data.max()
# force the number of filters to be square
n=int(np.ceil(np.sqrt(data.shape[0])))
padding=((0,n**2-data.shape[0]),(0,padsize),(0,padsize))+((0,0),)*(data.ndim-3)
data=np.pad(data,padding,mode='constant',constant_values=(padval,padval))
# 对图像使用滤波器
data=data.reshape((n,n)+data.shape[1:]).transpose((0,2,1,3)+tuple(range( 4,data.ndim+1)))
data=data.reshape((n*data.shape[1],n*data.shape[3])+data.shape[4:])
#show_image(data)
plt.imshow(data)
plt.show()
# 设置图片的保存路径，此处是我的路径
plt.savefig("./tools/Vehicle_2000/fc6.jpg")
out = net.forward()
image=net.blobs['data'].data[4].copy()
image-=image.min()
image/=image.max()
# 显示原始图像
show_image(image.transpose(1,2,0))
#网络提取conv1的卷积核
filters = net.params['conv1'][0].data
vis_square(filters.transpose(0, 2, 3, 1))
#过滤后的输出,96 张 featuremap
feat =net.blobs['conv1'].data[0,:96]
vis_square(feat,padval=1)
#第二个卷积层,显示全部的96个滤波器,每一个滤波器为一行。
filters = net.params['conv2'][0].data
vis_square(filters[:96].reshape(96**2, 5, 5))
# #第二层输出 256 张 featuremap
feat = net.blobs['conv2'].data[0]
vis_square(feat, padval=1)
filters = net.params['conv3'][0].data
vis_square(filters[:256].reshape(256**2, 3, 3))
# 第三个卷积层:全部 384 个 feature map
feat = net.blobs['conv3'].data[0]
vis_square(feat, padval=0.5)
#第四个卷积层,我们只显示前面 48 个滤波器,每一个滤波器为一行。
filters = net.params['conv4'][0].data
vis_square(filters[:384].reshape(384**2, 3, 3))
# 第四个卷积层:全部 384 个 feature map
feat = net.blobs['conv4'].data[0]
vis_square(feat, padval=0.5)
# 第五个卷积层:全部 256 个 feature map
filters = net.params['conv5'][0].data
vis_square(filters[:384].reshape(384**2, 3, 3))
feat = net.blobs['conv5'].data[0]
vis_square(feat, padval=0.5)
#第五个 pooling 层
feat = net.blobs['fc6'].data[0]
vis_square(feat, padval=1)
第六层输出后的直方分布
feat=net.blobs['fc6'].data[0]
plt.subplot(2,1,1)
plt.plot(feat.flat)
plt.subplot(2,1,2)
_=plt.hist(feat.flat[feat.flat>0],bins=100)
# #显示图片的方法
#plt.axis('off') # 不显示坐标轴
plt.show()
plt.savefig("fc6_zhifangtu.jpg")
# 第七层输出后的直方分布
feat=net.blobs['fc7'].data[0]
plt.subplot(2,1,1)
plt.plot(feat.flat)
plt.subplot(2,1,2)
_=plt.hist(feat.flat[feat.flat>0],bins=100)
plt.show()
plt.savefig("fc7_zhifangtu.jpg")
#看标签
#执行测试
image_labels_filename=caffe_root+'data/ilsvrc12/synset_words.txt'
#try:
labels=np.loadtxt(image_labels_filename,str,delimiter='\t')
top_k=net.blobs['prob'].data[0].flatten().argsort()[-1:-6:-1]
#print labels[top_k]
for i in np.arange(top_k.size):
print top_k[i], labels[top_k[i]]
|
