def test_net(sess,
net,
imdb,
weights_filename,
max_per_image=100,
thresh=0.05):
np.random.seed(cfg.RNG_SEED)
"""Test a Fast R-CNN network on an image database."""
num_images = len(imdb.image_index)
# all detections are collected into:
# all_boxes[cls][image] = N x 5 array of detections in
# (x1, y1, x2, y2, score)
all_boxes = [[[] for _ in range(num_images)]
for _ in range(imdb.num_classes)]
output_dir = get_output_dir(imdb, weights_filename)
# timers
_t = {'im_detect': Timer(), 'misc': Timer()}
for i in range(num_images):
im = cv2.imread(imdb.image_path_at(i))
_t['im_detect'].tic()
scores, boxes = im_detect(sess, net, im)
_t['im_detect'].toc()
_t['misc'].tic()
# skip j = 0, because it's the background class
for j in range(1, imdb.num_classes):
inds = np.where(scores[:, j] > thresh)[0]
cls_scores = scores[inds, j]
cls_boxes = boxes[inds, j * 4:(j + 1) * 4]
cls_dets = np.hstack((cls_boxes, cls_scores[:, np.newaxis])) \
.astype(np.float32, copy=False)
keep = nms(cls_dets, cfg.TEST.NMS)
cls_dets = cls_dets[keep, :]
all_boxes[j][i] = cls_dets
# Limit to max_per_image detections *over all classes*
if max_per_image > 0:
image_scores = np.hstack(
[all_boxes[j][i][:, -1] for j in range(1, imdb.num_classes)])
if len(image_scores) > max_per_image:
image_thresh = np.sort(image_scores)[-max_per_image]
for j in range(1, imdb.num_classes):
keep = np.where(all_boxes[j][i][:, -1] >= image_thresh)[0]
all_boxes[j][i] = all_boxes[j][i][keep, :]
_t['misc'].toc()
print('im_detect: {:d}/{:d} {:.3f}s {:.3f}s' \
.format(i + 1, num_images, _t['im_detect'].average_time,
_t['misc'].average_time))
det_file = os.path.join(output_dir, 'detections.pkl')
with open(det_file, 'wb') as f:
pickle.dump(all_boxes, f, pickle.HIGHEST_PROTOCOL)
print('Evaluating detections')
imdb.evaluate_detections(all_boxes, output_dir)
def extract_net(sess,
net,
imdb,
weights_filename,
roidb,
max_per_image=100,
thresh=0.05):
#change from test_net, and this function is used to extract features from conv5 of vgg16
np.random.seed(cfg.RNG_SEED)
"""Test a Fast R-CNN network on an image database."""
num_images = len(imdb.image_index)
# all detections are collected into:
# all_boxes[cls][image] = N x 5 array of detections in
# (x1, y1, x2, y2, score)
all_boxes = [[[] for _ in range(num_images)]
for _ in range(imdb.num_classes)]
output_dir = get_output_dir(imdb, weights_filename)
print("output_dir is:", output_dir)
print("\n")
# timers
_t = {'im_detect': Timer(), 'misc': Timer()}
data_input = []
#N_save is the number of processed images which will be saved into one file
N_save = 100
for i in range(1000):
im = cv2.imread(imdb.image_path_at(i))
_t['im_detect'].tic()
feature_maps = im_extract(sess, net, im)
fea = np.squeeze(feature_maps)
data_temp = {}
data_temp['img_path'] = imdb.image_path_at(i)
data_temp['box'] = roidb[i]['boxes']
data_temp['img_shape'] = np.shape(im)
data_temp['fea'] = fea
data_input.append(data_temp)
if (i + 1) % N_save == 0:
file_name_of_input = '/home/yangxu/project/rd/input/input' + format(
int((i + 1) / N_save), '03') + '.npz'
np.savez(file_name_of_input, data_input=data_input)
data_input = []
_t['im_detect'].toc()
_t['misc'].tic()
print('im_extract: {:d}/{:d} {:.3f}s {:.3f}s' \
.format(i + 1, num_images, _t['im_detect'].average_time,
_t['misc'].average_time))
print(
"i is: {0}, the path of image is {1}, shape of the image is {2}, the shape of the feature map is{3}\n"
.format(i, imdb.image_path_at(i), np.shape(im), np.shape(fea)))
if args.cfg_file is not None:
cfg_from_file(args.cfg_file)
if args.set_cfgs is not None:
cfg_from_list(args.set_cfgs)
print('Using config:')
pprint.pprint(cfg)
np.random.seed(cfg.RNG_SEED)
# train set
imdb, roidb = combined_roidb(args.imdb_name)
print('{:d} roidb entries'.format(len(roidb)))
# output directory where the models are saved
output_dir = get_output_dir(imdb, args.tag)
print('Output will be saved to `{:s}`'.format(output_dir))
# tensorboard directory where the summaries are saved during training
tb_dir = get_output_tb_dir(imdb, args.tag)
print('TensorFlow summaries will be saved to `{:s}`'.format(tb_dir))
# also add the validation set, but with no flipping images
orgflip = cfg.TRAIN.USE_FLIPPED
cfg.TRAIN.USE_FLIPPED = False
_, valroidb = combined_roidb(args.imdbval_name)
print('{:d} validation roidb entries'.format(len(valroidb)))
cfg.TRAIN.USE_FLIPPED = orgflip
# load network
if args.net == 'vgg16':
pre_train_weight = project_path + "/data/pre_train_weight/" + arg_net + ".ckpt"
cfg_from_file(project_path + "/experiments/cfgs/" + arg_net +
".yml") #载入参数配置
cfg_from_list(set_cfgs) #修改参数配置
print('Using config:')
pprint.pprint(cfg)
# roidb：所有训练图片的gt_boxes
# imdb：训练数据集的相关信息：包括类别列表，所有的图片名称的索引，数据集名称等等
imdb, roidb = combined_roidb("gridsum_car_train")
print(roidb[0]['boxes'])
print(roidb[0])
print('{:d} roidb entries'.format(len(roidb)))
# output directory where the models are saved
output_dir = get_output_dir(imdb, "")
print('Output will be saved to `{:s}`'.format(output_dir))
# tensorboard directory where the summaries are saved during training
tb_dir = get_output_tb_dir(imdb, "")
# 同样的方法载入val数据集
print('TensorFlow summaries will be saved to `{:s}`'.format(tb_dir))
_, valroidb = combined_roidb("gridsum_car_train")
print('{:d} validation roidb entries'.format(len(valroidb)))
if arg_net == 'vgg16':
net = vgg16()
elif arg_net == 'res50':
net = resnetv1(num_layers=50)
elif arg_net == 'res101':
net = resnetv1(num_layers=101)
elif arg_net == 'res152':
# train set
imdb, roidb = get_roidb('voc_2007_trainval') #训练集
#print('{:d} roidb entries'.format(len(roidb)))
pretrained_model = 'E:/fasterwrite/data/imagenet_weights/vgg16.ckpt'
'''
print(len(roidb))
print (type(roidb[0]['image']))
im=cv2.imread(roidb[0]['image'])
print(im)
im=cv2.imread(roidb[6000]['image'])
print(im)
'''
weights_filename = 'default'
output_dir = get_output_dir(imdb, weights_filename)
print('Output will be saved to `{:s}`'.format(output_dir))
# tb_dir = get_output_tb_dir(imdb,weights_filename)
net = vgg16()
orgflip = cfg.TRAIN.USE_FLIPPED
cfg.TRAIN.USE_FLIPPED = False
valimdb, valroidb = get_roidb('voc_2007_test') #获取测试集数据
#测试验证集数据
#im=cv2.imread(valroidb[6000]['image']
#print(im)
print('{:d} validatio n roidb entries'.format(len(valroidb)))
cfg.TRAIN.USE_FLIPPED = orgflip
#截止目前测试均通过