def evaluate_net(net, dataset, devkit_path, mean_pixels, data_shape,
model_prefix, epoch, ctx, year=None, sets='test',
batch_size=1, nms_thresh=0.5, force_nms=False):
"""
Evaluate entire dataset, basically simple wrapper for detections
Parameters:
---------
dataset : str
name of dataset to evaluate
devkit_path : str
root directory of dataset
mean_pixels : tuple of float
(R, G, B) mean pixel values
data_shape : int
resize input data shape
model_prefix : str
load model prefix
epoch : int
load model epoch
ctx : mx.ctx
running context, mx.cpu() or mx.gpu(0)...
year : str or None
evaluate on which year's data
sets : str
evaluation set
batch_size : int
using batch_size for evaluation
nms_thresh : float
non-maximum suppression threshold
force_nms : bool
force suppress different categories
"""
# set up logger
logging.basicConfig()
logger = logging.getLogger()
logger.setLevel(logging.INFO)
if dataset == "pascal":
if not year:
year = '2007'
imdb = PascalVoc(sets, year, devkit_path, shuffle=False, is_train=False)
data_iter = DetIter(imdb, batch_size, data_shape, mean_pixels,
rand_samplers=[], rand_mirror=False, is_train=False, shuffle=False)
sys.path.append(os.path.join(cfg.ROOT_DIR, 'symbol'))
net = importlib.import_module("symbol_" + net) \
.get_symbol(imdb.num_classes, nms_thresh, force_nms)
model_prefix += "_" + str(data_shape)
detector = Detector(net, model_prefix, epoch, data_shape, mean_pixels, batch_size, ctx)
logger.info("Start evaluation with {} images, be patient...".format(imdb.num_images))
detections = detector.detect(data_iter)
imdb.evaluate_detections(detections)
else:
raise NotImplementedError, "No support for dataset: " + dataset
def evaluate_net(net, dataset, devkit_path, mean_pixels, data_shape,
model_prefix, epoch, ctx, year=None, sets='test',
batch_size=1, nms_thresh=0.5, force_nms=False):
"""
Evaluate entire dataset, basically simple wrapper for detections
Parameters:
---------
dataset : str
name of dataset to evaluate
devkit_path : str
root directory of dataset
mean_pixels : tuple of float
(R, G, B) mean pixel values
data_shape : int
resize input data shape
model_prefix : str
load model prefix
epoch : int
load model epoch
ctx : mx.ctx
running context, mx.cpu() or mx.gpu(0)...
year : str or None
evaluate on which year's data
sets : str
evaluation set
batch_size : int
using batch_size for evaluation
nms_thresh : float
non-maximum suppression threshold
force_nms : bool
force suppress different categories
"""
# set up logger
logging.basicConfig()
logger = logging.getLogger()
logger.setLevel(logging.INFO)
if dataset == "pascal":
if not year:
year = '2007'
imdb = PascalVoc(sets, year, devkit_path, shuffle=False, is_train=False)
data_iter = DetIter(imdb, batch_size, data_shape, mean_pixels,
rand_samplers=[], rand_mirror=False, is_train=False, shuffle=False)
sys.path.append(os.path.join(cfg.ROOT_DIR, 'symbol'))
net = importlib.import_module("symbol_" + net) \
.get_symbol(imdb.num_classes, nms_thresh, force_nms)
model_prefix += "_" + str(data_shape)
detector = Detector(net, model_prefix, epoch, data_shape, mean_pixels, batch_size, ctx)
logger.info("Start evaluation with {} images, be patient...".format(imdb.num_images))
detections = detector.detect(data_iter)
imdb.evaluate_detections(detections)
else:
raise NotImplementedError("No support for dataset: " + dataset)
def load_pascal(image_set,
year,
devkit_path,
shuffle=False,
class_names=None,
true_negative=None):
"""
wrapper function for loading pascal voc dataset
Parameters:
----------
image_set : str
train, trainval...
year : str
2007, 2012 or combinations splitted by comma
devkit_path : str
root directory of dataset
shuffle : bool
whether to shuffle initial list
Returns:
----------
Imdb
"""
image_set = [y.strip() for y in image_set.split(',')]
assert image_set, "No image_set specified"
year = [y.strip() for y in year.split(',')]
assert year, "No year specified"
# make sure (# sets == # years)
if len(image_set) > 1 and len(year) == 1:
year = year * len(image_set)
if len(image_set) == 1 and len(year) > 1:
image_set = image_set * len(year)
assert len(image_set) == len(year), "Number of sets and year mismatch"
imdbs = []
for s, y in zip(image_set, year):
imdbs.append(
PascalVoc(s,
y,
devkit_path,
shuffle,
is_train=True,
class_names=class_names,
true_negative_images=true_negative))
if len(imdbs) > 1:
return ConcatDB(imdbs, shuffle)
else:
return imdbs[0]
def load_pascal(shuffle=False, is_valid=False):
"""
wrapper function for loading pascal voc dataset
Parameters:
----------
image_set : str
train, trainval...
year : str
2007, 2012 or combinations splitted by comma
devkit_path : str
root directory of dataset
shuffle : bool
whether to shuffle initial list
Returns:
----------
Imdb
"""
root_path = private_config.root_path
if is_valid:
image_set = private_config.valid_image_set
data_path = private_config.valid_data_path
else:
data_path = private_config.data_path
image_set = private_config.image_set
image_set = [y.strip() for y in image_set.split(',')]
assert image_set, "No image_set specified"
imdbs = []
for s in image_set:
imdbs.append(
PascalVoc(s,
data_path=data_path,
root_path=root_path,
shuffle=shuffle,
is_train=True))
if len(imdbs) > 1:
raise NotImplementedError
return ConcatDB(imdbs, shuffle)
else:
return imdbs[0]
RandCropper(min_scale=.3, min_aspect_ratio=.5, max_aspect_ratio=2., min_overlap=.1),
RandCropper(min_scale=.3, min_aspect_ratio=.5, max_aspect_ratio=2., min_overlap=.3),
RandCropper(min_scale=.3, min_aspect_ratio=.5, max_aspect_ratio=2., min_overlap=.5),
RandCropper(min_scale=.3, min_aspect_ratio=.5, max_aspect_ratio=2., min_overlap=.7),
RandPadder(max_scale=2., min_aspect_ratio=.5, max_aspect_ratio=2., min_gt_scale=.05),
RandPadder(max_scale=3., min_aspect_ratio=.5, max_aspect_ratio=2., min_gt_scale=.05),
RandPadder(max_scale=4., min_aspect_ratio=.5, max_aspect_ratio=2., min_gt_scale=.05)
],
"random_flip": True,
"shuffle": True,
"random_seed": None
}
# # validation
# cfg.VALID = edict()
# cfg.VALID.RAND_SAMPLERS = []
# cfg.VALID.RAND_MIRROR = False
# cfg.VALID.INIT_SHUFFLE = False
# cfg.VALID.EPOCH_SHUFFLE = False
# cfg.VALID.RAND_SEED = None
ssd_prov = DetIter(
imdb=PascalVoc("trainval", "2007", "/unsullied/sharefs/yugang/Dataset/VOC", is_train=True),
batch_size=32,
data_shape=(300, 300),
mean_pixels=[104, 117, 123],
rand_samplers=train_cfg['random_samplers'],
rand_flip=train_cfg['random_flip'],
shuffle=train_cfg['shuffle'],
rand_seed=train_cfg['random_seed']
)