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':
net = vgg16()
elif args.net == 'res50':
net = resnetv1(num_layers=50)
elif args.net == 'res101':
net = resnetv1(num_layers=101)
elif args.net == 'res152':
net = resnetv1(num_layers=152)
elif args.net == 'mobile':
net = mobilenetv1()
else:
raise NotImplementedError
# some statistic record
al_num = 0
ss_num = 0
initial_num = len(imdb[imdb.item_name(0)].roidb)
print ('All VOC2007 images use for initial train after flipped, imagenumbers:%d'%(initial_num))
for i in range(initialnum):
bitmapImdb.set(i)
train_roidb = imdb[imdb.item_name(0)].roidb
# pretrained-model
pretrained_model_name = args.weight
# some parameters
tao = args.max_iters
tfconfig = tf.ConfigProto(allow_soft_placement=True)
tfconfig.gpu_options.allow_growth=True
# init session
sess = tf.Session(config=tfconfig)
# load network
if args.net == 'vgg16':
net = vgg16()
elif args.net == 'res50':
net = resnetv1(num_layers=50)
elif args.net == 'res101':
net = resnetv1(num_layers=101)
elif args.net == 'res152':
net = resnetv1(num_layers=152)
elif args.net == 'mobile':
net = mobilenetv1()
else:
raise NotImplementedError
# load model
net.create_architecture("TEST", imdb.num_classes, tag='default',
anchor_scales=cfg.ANCHOR_SCALES,
anchor_ratios=cfg.ANCHOR_RATIOS)
if args.model:
print(('Loading model check point from {:s}').format(args.model))
saver = tf.train.Saver()
saver.restore(sess, args.model)
print('Loaded.')
else:
print(('Loading initial weights from {:s}').format(args.weight))
def __init__(self,
net_name,
model_path,
cfg_file,
num_classes=2,
max_object_per_image=15,
conf_thresh=0.3,
nms_thresh=0.5,
iou_thresh=0.5):
self.net_name = net_name
# self.sess = sess
self.model_path = model_path
self.cfg_file = cfg_file
self.num_images = 1
self.num_classes = num_classes
self.conf_thresh = conf_thresh
self.nms_thresh = nms_thresh
self.iou_thresh = iou_thresh
self.max_object_per_image = max_object_per_image
# set config
tfconfig = tf.ConfigProto(allow_soft_placement=True)
tfconfig.gpu_options.allow_growth = True
# tfconfig=tf.ConfigProto(log_device_placement=False,allow_soft_placement=True)
# init session
self.sess = tf.Session(config=tfconfig)
if not os.path.isfile(self.model_path + '.meta'):
raise IOError((
'{:s} not found.\nDid you download the proper networks from '
'our server and place them properly?').format(self.model_path +
'.meta'))
# load network configuration
cfg_from_file(self.cfg_file)
# pprint.pprint(cfg)
# load network
if self.net_name == 'vgg16':
self.net = vgg16(batch_size=1)
elif self.net_name == 'res50':
self.net = resnetv1(batch_size=1, num_layers=50)
elif self.net_name == 'res101':
self.net = resnetv1(batch_size=1, num_layers=101)
elif self.net_name == 'res152':
self.net = resnetv1(batch_size=1, num_layers=152)
elif self.net_name == 'mobile':
self.net = mobilenetv1(batch_size=1)
else:
raise NotImplementedError
with self.sess.as_default():
self.net.create_architecture(self.sess,
"TEST",
self.num_classes,
tag='default',
anchor_scales=cfg.ANCHOR_SCALES,
anchor_ratios=cfg.ANCHOR_RATIOS)
saver = tf.train.Saver()
saver.restore(self.sess, self.model_path)
# 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':
net = vgg16(batch_size=cfg.TRAIN.IMS_PER_BATCH)
elif args.net == 'res50':
net = resnetv1(batch_size=cfg.TRAIN.IMS_PER_BATCH, num_layers=50)
elif args.net == 'res101':
net = resnetv1(batch_size=cfg.TRAIN.IMS_PER_BATCH, num_layers=101)
elif args.net == 'res152':
net = resnetv1(batch_size=cfg.TRAIN.IMS_PER_BATCH, num_layers=152)
elif args.net == 'mobile':
net = mobilenetv1(batch_size=cfg.TRAIN.IMS_PER_BATCH)
else:
raise NotImplementedError
train_net(net,
imdb,
roidb,
valroidb,
output_dir,
tb_dir,
pretrained_model=args.weight,
max_iters=args.max_iters)
def __init__(self, dir_model, network, gpu_id):
self.net = None
if network == 'res101':
self.CLASSES = ('__background__', 'aeroplane', 'bicycle', 'bird',
'boat', 'bottle', 'bus', 'car', 'cat', 'chair',
'cow', 'diningtable', 'dog', 'horse', 'motorbike',
'person', 'pottedplant', 'sheep', 'sofa', 'train',
'tvmonitor')
if network == 'mobilenet':
self.CLASSES = (
'background', 'person', 'bicycle', 'car', 'motorcycle',
'airplane', 'bus', 'train', 'truck', 'boat', 'traffic light',
'fire hydrant', 'stop sign', 'parking meter', 'bench', 'bird',
'cat', 'dog', 'horse', 'sheep', 'cow', 'elephant', 'bear',
'zebra', 'giraffe', 'backpack', 'umbrella', 'handbag', 'tie',
'suitcase', 'frisbee', 'skis', 'snowboard', 'sports ball',
'kite', 'baseball bat', 'baseball glove', 'skateboard',
'surfboard', 'tennis racket', 'bottle', 'wine glass', 'cup',
'fork', 'knife', 'spoon', 'bowl', 'banana', 'apple',
'sandwich', 'orange', 'broccoli', 'carrot', 'hot dog', 'pizza',
'donut', 'cake', 'chair', 'couch', 'potted plant', 'bed',
'dining table', 'toilet', 'tv', 'laptop', 'mouse', 'remote',
'keyboard', 'cell phone', 'microwave', 'oven', 'toaster',
'sink', 'refrigerator', 'book', 'clock', 'vase', 'scissors',
'teddy bear', 'hair drier', 'toothbrush')
NETS = {
'mobilenet': ('mobile_faster_rcnn_iter_1190000.ckpt', ),
'vgg16': ('vgg16_faster_rcnn_iter_70000.ckpt', ),
'res101': ('res101_faster_rcnn_iter_110000.ckpt', )
}
os.environ["CUDA_VISIBLE_DEVICES"] = gpu_id
# demonet = 'mobilenet'#'res101'
tfmodel = os.path.join(dir_model, 'person_detection/faster_rcnn',
NETS[network][0])
if not os.path.isfile(tfmodel + '.meta'):
raise IOError(
('{:s} not found.\nDid you download the proper networks from '
'our server and place them properly?').format(tfmodel +
'.meta'))
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=0.8)
# config.gpu_options.per_process_gpu_memory_fraction = 0.8
self.sess = tf.Session(config=tf.ConfigProto(
gpu_options=gpu_options, allow_soft_placement=True))
# tfconfig = tf.ConfigProto(allow_soft_placement=True)
# tfconfig.gpu_options.allow_growth = True
#
# # init session
# sess = tf.Session(config=tfconfig)
if network == 'vgg16':
self.net = vgg16()
elif network == 'res101':
self.net = resnetv1(num_layers=101)
elif network == 'mobilenet':
self.net = mobilenetv1()
else:
raise NotImplementedError
if network == 'mobilenet':
self.net.create_architecture("TEST",
81,
tag='default',
anchor_scales=[4, 8, 16, 32])
if network == 'res101':
self.net.create_architecture("TEST",
21,
tag='default',
anchor_scales=[8, 16, 32])
saver = tf.train.Saver()
saver.restore(self.sess, tfmodel)
print('Loaded network {:s}'.format(tfmodel))
self.CONF_THRESH = 0.8
self.NMS_THRESH = 0.3
tfconfig = tf.ConfigProto(allow_soft_placement=True)
tfconfig.gpu_options.allow_growth=True
# init session
sess = tf.Session(config=tfconfig)
# load network
if args.net == 'vgg16':
net = vgg16(batch_size=1)
elif args.net == 'res50':
net = resnetv1(batch_size=1, num_layers=50)
elif args.net == 'res101':
net = resnetv1(batch_size=1, num_layers=101)
elif args.net == 'res152':
net = resnetv1(batch_size=1, num_layers=152)
elif args.net == 'mobile':
net = mobilenetv1(batch_size=1)
else:
raise NotImplementedError
# load model
net.create_architecture("TEST", imdb.num_classes, tag='default',
anchor_scales=cfg.ANCHOR_SCALES,
anchor_ratios=cfg.ANCHOR_RATIOS)
if args.model:
print(('Loading model check point from {:s}').format(args.model))
saver = tf.train.Saver()
saver.restore(sess, args.model)
print('Loaded.')
else:
print(('Loading initial weights from {:s}').format(args.weight))
tfconfig = tf.ConfigProto(allow_soft_placement=True)
tfconfig.gpu_options.allow_growth=True
# init session
sess = tf.Session(config=tfconfig)
# load network
if args.net == 'vgg16':
net = vgg16(batch_size=1)
elif args.net == 'res50':
net = resnetv1(batch_size=1, num_layers=50)
elif args.net == 'res101':
net = resnetv1(batch_size=1, num_layers=101)
elif args.net == 'res152':
net = resnetv1(batch_size=1, num_layers=152)
elif args.net == 'mobile':
net = mobilenetv1(batch_size=1)
else:
raise NotImplementedError
# load model
net.create_architecture(sess, "TEST", imdb.num_classes, tag='default',
anchor_scales=cfg.ANCHOR_SCALES,
anchor_ratios=cfg.ANCHOR_RATIOS)
if args.model:
print(('Loading model check point from {:s}').format(args.model))
saver = tf.train.Saver()
saver.restore(sess, args.model)
print('Loaded.')
else:
print(('Loading initial weights from {:s}').format(args.weight))
def launch_train(self, conf):
'''
'''
args = {}
args['cfg_file'] = conf.frcnn_cfg
args['weight'] = conf.starting_weights
args['imdb_name'] = conf.train_set
args['imdbval_name'] = conf.valid_set
args['max_iters'] = conf.iters
args['tag'] = conf.frcnn_tag
args['net'] = conf.frcnn_net
args['set_cfgs'] = None
print('Called with args:')
print(args)
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'], conf)
print('{:d} roidb entries'.format(len(roidb)))
# output directory where the models are saved
output_dir = conf.backup_folder #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 = conf.backup_folder # 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'], conf)
print('{:d} validation roidb entries'.format(len(valroidb)))
cfg.TRAIN.USE_FLIPPED = orgflip
if args['net'] == 'vgg16':
net = vgg16(batch_size=cfg.TRAIN.IMS_PER_BATCH)
elif args['net'] == 'res50':
net = resnetv1(batch_size=cfg.TRAIN.IMS_PER_BATCH, num_layers=50)
elif args['net'] == 'res101':
net = resnetv1(batch_size=cfg.TRAIN.IMS_PER_BATCH, num_layers=101)
# load network
elif args['net'] == 'res152':
net = resnetv1(batch_size=cfg.TRAIN.IMS_PER_BATCH, num_layers=152)
elif args['net'] == 'mobile':
net = mobilenetv1(batch_size=cfg.TRAIN.IMS_PER_BATCH)
else:
raise NotImplementedError
train_net(net,
imdb,
roidb,
valroidb,
output_dir,
tb_dir,
pretrained_model=args['weight'],
max_iters=args['max_iters'])
def launch_test(self, conf, hash_model):
'''
'''
args = {}
args['cfg_file'] = conf.frcnn_cfg
args['weight'] = conf.starting_weights
args['model'] = hash_model
args['imdb_name'] = conf.valid_set
args['comp_mode'] = False
args['tag'] = conf.frcnn_tag
args['net'] = conf.frcnn_net
args['set_cfgs'] = None
args['max_per_image'] = 5
print('Called with args:')
print(args)
if args['cfg_file'] is not None:
cfg_from_file(argsargs['cfg_file'])
if args['set_cfgs'] is not None:
cfg_from_list(args['set_cfgs'])
print('Using config:')
pprint.pprint(cfg)
# if has model, get the name from it
# if does not, then just use the inialization weights
if args['model']:
filename = os.path.splitext(os.path.basename(args['model']))[0]
else:
filename = os.path.splitext(os.path.basename(args['weight']))[0]
tag = args['tag']
tag = tag if tag else 'default'
filename = tag + '/' + filename
# TODO This is really bad but it works, I'm sincerely sorry
conf_copy = copy.deepcopy(conf)
conf_copy.train_set = conf_copy.valid_set
imdb = get_imdb(args['imdb_name'], conf_copy)
print(args['imdb_name'])
imdb.competition_mode(args['comp_mode'])
tfconfig = tf.ConfigProto(allow_soft_placement=True)
tfconfig.gpu_options.allow_growth = True
# init session
sess = tf.Session(config=tfconfig)
# load network
if args['net'] == 'vgg16':
net = vgg16(batch_size=1)
elif args['net'] == 'res50':
net = resnetv1(batch_size=1, num_layers=50)
elif args['net'] == 'res101':
net = resnetv1(batch_size=1, num_layers=101)
elif args['net'] == 'res152':
net = resnetv1(batch_size=1, num_layers=152)
elif args['net'] == 'mobile':
net = mobilenetv1(batch_size=1)
else:
raise NotImplementedError
# load model
net.create_architecture(sess,
"TEST",
imdb.num_classes,
tag='default',
anchor_scales=cfg.ANCHOR_SCALES,
anchor_ratios=cfg.ANCHOR_RATIOS)
if args['model']:
print(
('Loading model check point from {:s}').format(args['model']))
saver = tf.train.Saver()
saver.restore(sess, args['model'])
print('Loaded.')
else:
print(('Loading initial weights from {:s}').format(args['weight']))
sess.run(tf.global_variables_initializer())
print('Loaded.')
test_net(sess,
net,
imdb,
filename,
max_per_image=args['max_per_image'])
sess.close()
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':
net = vgg16(batch_size=cfg.TRAIN.IMS_PER_BATCH)
elif args.net == 'res50':
net = resnetv1(batch_size=cfg.TRAIN.IMS_PER_BATCH, num_layers=50)
elif args.net == 'res101':
net = resnetv1(batch_size=cfg.TRAIN.IMS_PER_BATCH, num_layers=101)
elif args.net == 'res152':
net = resnetv1(batch_size=cfg.TRAIN.IMS_PER_BATCH, num_layers=152)
elif args.net == 'mobile':
net = mobilenetv1(batch_size=cfg.TRAIN.IMS_PER_BATCH)
else:
raise NotImplementedError
train_net(net, imdb, roidb, valroidb, output_dir, tb_dir,
pretrained_model=args.weight,
max_iters=args.max_iters)
