def __init__(self, params, result):
self.result = result
#load data
if params['source'][-4:] == '.mat':
self.img_data, self.img_labels = mat2py_imdb(params['source'])
self.img_data = np.rollaxis(self.img_data,2) #swap dims to have Num x height x width
elif os.path.isdir(params['source']): #assume it is lmdb
lmdb_ = lmdbpy()
self.img_data, self.img_labels = lmdb_.read(params['source']) #use read_encoded if the img is encoded
self.img_data = self.img_data.squeeze()
else:
assert 0, 'Invalid format for source {}\n\
need either lmdb or .mat data'.format(params['source'])
if params['mean_file']==0:
self.img_mean = 0
elif params['mean_file'][-4:] == '.mat':
self.img_mean = mat2py_mean(params['mean_file'])
elif params['mean_file'][-12:] == '.binaryproto':
self.img_mean = biproto2py(params['mean_file']).squeeze()
else:
assert 0, 'Invalid format for mean_file {}'.format(params['mean_file'])
self.indexlist = range(len(self.img_labels))
shuffle(self.indexlist)
self._cur = 0 # current image
# this class does some simple data-manipulations
self.img_augment = SimpleAugment(mean=self.img_mean,shape=params['shape'],
scale = params['scale'], rot = params['rot'])
print "\nBatchLoader initialized with {} images".format(
len(self.img_labels))
def __init__(self, params):
self.batch_size = params['batch_size']
self.outshape = params['shape']
self.classes_per_batch = params['classes_per_batch']
self.img_lmdb = lmdbs(params['img_source'])
if params['skt_source'].endswith('.pkl'):
self.skt_lmdb = svgs(params['skt_source'])
else:
self.skt_lmdb = lmdbs(params['skt_source'])
self.img_labels = self.img_lmdb.get_label_list()
self.skt_labels = self.skt_lmdb.get_label_list()
self.img_mean = biproto2py(params['mean_file']).squeeze()
self.num_classes = len(set(self.skt_labels))
assert len(self.skt_labels)%self.num_classes==0, \
'Unequal sketch training samples for each class'
self.skt_per_class = len(self.skt_labels) / self.num_classes
if 'hard_pos' in params:
self.hard_sel = 'hard_pos'
self.hard_sel_file = params['hard_pos']
elif 'hard_neg' in params:
self.hard_sel = 'hard_neg'
self.hard_sel_file = params['hard_neg']
elif 'hard_pn' in params:
self.hard_sel = 'hard_pn'
self.hard_sel_file = params['hard_pn']
else:
assert False, 'Hard selection must be on'
self.watchChange = WatchDog(
self.hard_sel_file) #check if file has been updated
self.hardsel_tab = np.load(self.hard_sel_file)
self.hard_pos = self.hardsel_tab['pos']
self.hard_neg = self.hardsel_tab['neg']
self.img_labels_dict, self.classes = vec2dic(self.img_labels)
self.NSKTS = len(self.skt_labels)
self.indexlist = range(self.NSKTS)
self.shuffle_keeping_min_classes_per_batch()
self._cur = 0 # current image
# this class does some simple data-manipulations
self.img_augment = SimpleAugment(mean=self.img_mean,
shape=params['shape'],
scale=params['scale'],
rot=params['rot'])
if 'verbose' not in params:
print "BatchLoader initialized with {} sketches, {} images of {} classes".format(
len(self.skt_labels), len(self.img_labels), self.num_classes)
print('Hard selection: {}'.format(self.hard_sel))
#create threadpools for parallel augmentation
self.pool = ThreadPool() #4
def __init__(self, params):
#load data
self.batch_size = params['batch_size']
self.outshape = params['shape']
if params['source'][-4:] == '.mat':
self.img_data, self.img_labels = mat2py_imdb(params['source'])
self.img_data = self.img_data.transpose(
2, 0, 1) #swap dims to have Num x height x width
elif os.path.isdir(params['source']): #assume it is lmdb
lmdb_ = lmdbpy()
self.img_data, self.img_labels = lmdb_.read(
params['source']) #use read_encoded if the img is encoded
self.img_data = self.img_data.squeeze()
else:
assert 0, 'Invalid format for source {}\n\
need either lmdb or .mat data'.format(params['source'])
label_ids = list(set(self.img_labels))
NCATS = len(label_ids)
if label_ids[0] != 0 or label_ids[-1] != NCATS - 1:
print 'Your data labels are not [0:{}]. Converting label ...'.format(
NCATS - 1)
self.img_labels = [
label_ids.index(label) for label in self.img_labels
]
if params['mean_file'] == 0:
self.img_mean = 0
elif params['mean_file'][-4:] == '.mat':
self.img_mean = mat2py_mean(params['mean_file'])
elif params['mean_file'][-12:] == '.binaryproto':
self.img_mean = biproto2py(params['mean_file']).squeeze()
else:
assert 0, 'Invalid format for mean_file {}'.format(
params['mean_file'])
self.indexlist = range(len(self.img_labels))
shuffle(self.indexlist)
self._cur = 0 # current image
# this class does some simple data-manipulations
self.img_augment = SimpleAugment(mean=self.img_mean,
shape=params['shape'],
scale=params['scale'],
rot=params['rot'])
print "\nBatchLoader initialized with {} images".format(
len(self.img_labels))
self.pool = ThreadPool() #4
def __init__(self, params):
self.batch_size = params['batch_size']
self.outshape = params['shape']
self.lmdb = lmdbs(params['source'])
self.labels = self.lmdb.get_label_list()
self.img_mean = biproto2py(params['mean_file']).squeeze()
self.NIMGS = len(self.labels)
self.num_batches = int(np.ceil(self.NIMGS/float(self.batch_size)))
self._cur = 0 # current batch
# this class does some simple data-manipulations
self.img_augment = SimpleAugment(mean=self.img_mean,shape=params['shape'],
scale = params['scale'])
def __init__(self, params):
self.batch_size = params['batch_size']
self.outshape = params['shape']
self.lmdb = lmdbs(params['source'])
self.labels = self.lmdb.get_label_list()
self.img_mean = biproto2py(params['mean_file']).squeeze()
self.NIMGS = len(self.labels)
assert self.NIMGS%self.batch_size==0,'NIMGS {} not dividible by batchsize {}'.format(
self.NIMGS,self.batch_size)
self.num_batches = self.NIMGS/self.batch_size
self._cur = 0 # current batch
self.labels_tab = self.labels.reshape((self.num_batches,self.batch_size))
# this class does some simple data-manipulations
self.img_augment = SimpleAugment(mean=self.img_mean,shape=params['shape'],
scale = params['scale'])
def __init__(self, params):
self.batch_size = params['batch_size']
self.outshape = params['shape']
self.classes_per_batch = params['classes_per_batch']
self.img_lmdb = lmdbs(params['img_source'])
if params['skt_source'].endswith('.pkl'):
self.skt_lmdb = svgs(params['skt_source'])
else:
self.skt_lmdb = lmdbs(params['skt_source'])
self.img_labels = self.img_lmdb.get_label_list()
self.skt_labels = self.skt_lmdb.get_label_list()
self.img_mean = biproto2py(params['mean_file']).squeeze()
self.num_classes = len(set(self.skt_labels))
assert len(self.skt_labels)%self.num_classes==0, \
'Unequal sketch training samples for each class'
self.skt_per_class = len(self.skt_labels) / self.num_classes
self.hard_sel = 0
self.img_labels_dict, self.classes = vec2dic(self.img_labels)
self.indexlist = range(len(self.skt_labels))
self.shuffle_keeping_min_classes_per_batch()
self._cur = 0 # current image
# this class does some simple data-manipulations
self.img_augment = SimpleAugment(mean=self.img_mean,
shape=params['shape'],
scale=params['scale'],
rot=params['rot'])
if 'verbose' not in params:
print "BatchLoader initialized with {} sketches, {} images of {} classes".format(
len(self.skt_labels), len(self.img_labels), self.num_classes)
#create threadpools for parallel augmentation
self.pool = ThreadPool() #4
def __init__(self, params):
self.batch_size = params['batch_size']
self.img_shape = params['shape']
self.classes_per_batch = params['classes_per_batch']
self.img_lmdb = lmdbs(params['img_source'])
if params['skt_source'].endswith('.pkl'):
self.skt_lmdb = svgs(params['skt_source'])
else:
self.skt_lmdb = lmdbs(params['skt_source'])
self.img_labels = self.img_lmdb.get_label_list()
self.skt_labels = self.skt_lmdb.get_label_list()
label_ids = list(set(self.img_labels))
NCATS = len(label_ids)
if label_ids[0] != 0 or label_ids[-1] != NCATS - 1:
if 'verbose' not in params:
print 'Your data labels are not [0:{}]. Converting label ...'.format(
NCATS - 1)
self.img_labels = [
label_ids.index(label) for label in self.img_labels
]
self.skt_labels = [
label_ids.index(label) for label in self.skt_labels
]
self.img_mean = biproto2py(params['mean_file']).squeeze()
#self.skt_mean = biproto2py(params['skt_mean']).squeeze()
self.num_classes = len(set(self.skt_labels))
assert self.num_classes == NCATS, 'XX!!Sketch & image datasets unequal #categories'
assert len(self.skt_labels)%self.num_classes==0, \
'Unequal sketch training samples for each class'
self.skt_per_class = len(self.skt_labels) / self.num_classes
if 'hard_pos' in params:
self.hard_sel = 1
self.hard_pos = np.load(params['hard_pos'])['pos']
elif 'hard_neg' in params:
self.hard_sel = 2
self.hard_neg = np.load(params['hard_neg'])['neg']
elif 'hard_pn' in params:
self.hard_sel = 3
tmp = np.load(params['hard_pn'])
self.hard_pos = tmp['pos']
self.hard_neg = tmp['neg']
else: #hard selection turn off
self.hard_sel = 0
#self.img_labels_dict, self.classes = vec2dic(self.img_labels)
self.indexlist = range(len(self.skt_labels))
self.indexlist_img = range(len(self.img_labels))
#self.shuffle_keeping_min_classes_per_batch()
shuffle(self.indexlist)
shuffle(self.indexlist_img)
self._cur = 0 # current image
self._cur_img = 0
# this class does some simple data-manipulations
self.img_augment = SimpleAugment(mean=self.img_mean,
shape=self.img_shape,
scale=params['scale'],
rot=params['rot'])
print "BatchLoader initialized with {} sketches, {} images of {} classes".format(
len(self.skt_labels), len(self.img_labels), self.num_classes)
#create threadpools for parallel augmentation
self.pool = ThreadPool() #4
def extractitem(net, image):
"""
extract feature
"""
inblob = net.inputs[0]
outblob = net.blobs.keys()[layer - 1]
net.blobs[inblob].data[...] = image
_ = net.forward()
prediction = net.blobs[outblob].data.squeeze()
return prediction
if __name__ == '__main__':
if domain == 'image':
DEPLOY = 'models/deploy_images.prototxt'
scale_factor = 1.0
else:
DEPLOY = 'models/deploy_sketch.prototxt'
scale_factor = 2.0
net = get_net(WEIGHTS, DEPLOY)
mean_image = biproto2py(MEAN_DB).squeeze()
"""pre-processing"""
img = preprocess(INPUT, mean_image, domain)
"""feat extraction"""
net.blobs[net.inputs[0]].reshape(1, 1, 225, 225)
feat = extractitem(net, img) * scale_factor
print 'Done.'