def __init__(self, net_file=None, meta_file=None):
"""Initializes DecafNet.
Input:
net_file: the trained network file.
meta_file: the meta information for images.
"""
logging.info('Initializing decafnet...')
try:
if not net_file:
# use the internal decafnet file.
net_file = _JEFFNET_FILE
if not meta_file:
# use the internal meta file.
meta_file = _META_FILE
cuda_decafnet = pickle.load(open(net_file))
meta = pickle.load(open(meta_file))
except IOError:
raise RuntimeError('Cannot find DecafNet files.')
# First, translate the network
self._net = translator.translate_cuda_network(
cuda_decafnet, {'data': (INPUT_DIM, INPUT_DIM, 3)})
# Then, get the labels and image means.
self.label_names = meta['label_names']
self._data_mean = translator.img_cudaconv_to_decaf(
meta['data_mean'], 256, 3)
logging.info('Jeffnet initialized.')
return
def __init__(self, net_file=None, meta_file=None):
"""Initializes DecafNet.
Input:
net_file: the trained network file.
meta_file: the meta information for images.
"""
logging.info('Initializing decafnet...')
try:
if not net_file:
# use the internal decafnet file.
net_file = _JEFFNET_FILE
if not meta_file:
# use the internal meta file.
meta_file = _META_FILE
cuda_decafnet = pickle.load(open(net_file))
meta = pickle.load(open(meta_file))
except IOError:
raise RuntimeError('Cannot find DecafNet files.')
# First, translate the network
self._net = translator.translate_cuda_network(
cuda_decafnet, {'data': (INPUT_DIM, INPUT_DIM, 3)})
# Then, get the labels and image means.
self.label_names = meta['label_names']
self._data_mean = translator.img_cudaconv_to_decaf(
meta['data_mean'], 256, 3)
logging.info('Jeffnet initialized.')
return
def load_jeffnet(self,net_opt):
self.jf_opt = net_opt
meta = pickle.load(open(net_opt.meta_file))
self.jf_label_names = meta['label_names']
self.jf_data_mean = translator.img_cudaconv_to_decaf(meta['data_mean'], 256, 3)
FLAGS = gflags.FLAGS
"""
from collections import namedtuple
FLAGS = namedtuple("FLAGS", "net_file meta_file")
FLAGS.net_file = '../scripts/imagenet.decafnet.epoch90'
FLAGS.meta_file = '../scripts/imagenet.decafnet.meta'
from decaf.util import translator, transform
_JEFFNET_FLIP = True
if __name__ == '__main__':
net = imagenet.DecafNet(net_file=FLAGS.net_file, meta_file=FLAGS.meta_file)
import scipy.io
meta = pickle.load(open(FLAGS.meta_file))
data_mean = translator.img_cudaconv_to_decaf(meta['data_mean'], 256, 3)
TT = int(sys.argv[1])
if TT==-1:
fns = ['./test.jpg']
else:
if TT==0:
DD= '/home/Stephen/Desktop/Data/Seg/BSR/BSDS500/data/images/train/'
if TT==1:
DD= '/home/Stephen/Desktop/Data/Seg/BSR/BSDS500/data/images/val/'
elif TT==2:
DD= '/home/Stephen/Desktop/Data/Seg/BSR/BSDS500/data/images/test/'
fns = sorted(glob.glob(DD+'*.jpg'))
patch_id = 3
if patch_id==1:
