def absolute_path_to_relative_path(files):
for f in files:
annotations = al.parse(f)
for img in annotations:
if img.imageName[0] == '/':
img.imageName = '/'.join(img.imageName.split('/')[-2:])
al.save(f, annotations)
def create_tracking_files():
# files = glob.glob('/scail/group/deeplearning/driving_data/andriluka/IMAGES/driving_data_q50_data/all_extracted/*.al')
# files = [f for f in files if f.find('edit') == -1 and f.find('track') == -1]
files = glob.glob('/scail/group/deeplearning/driving_data/andriluka/IMAGES/driving_data_q50_data/all_extracted/benchmark_seq*_cleanup_trackid_every20.pal')
absolute_path_to_relative_path(files)
all_args = []
for f in files:
all_args.append(('-a %s -o ./ ' % f).split(' '))
pool = multiprocessing.Pool(processes=9)
for i, result in enumerate( pool.imap_unordered(m.main, all_args) ):
print "done %0.1f%%" % (float(i+1) * 100 / len(all_args))
pool.close()
pool.join()
# remove partials
partials = glob.glob('*partial.pal')
for p in partials:
os.remove(p)
# change paths
for f in files:
tracked_file = os.path.basename(f).replace('.pal','-track.pal')
imgs = al.parse(tracked_file)
for img in imgs:
if img.imageName[0] == '/':
img.imageName = '/'.join(img.imageName.split('/')[-2:])
al.save(tracked_file, imgs)
def eval(self, weights, test_boxes, min_conf, tau, show_suppressed, expname):
self.H["grid_width"] = self.H["image_width"] / self.H["region_size"]
self.H["grid_height"] = self.H["image_height"] / self.H["region_size"]
x_in = tf.placeholder(tf.float32, name='x_in', shape=[self.H['image_height'], self.H['image_width'], 3])
if self.H['use_rezoom']:
pred_boxes, pred_logits, pred_confidences, pred_confs_deltas, pred_boxes_deltas = self.build_forward(tf.expand_dims(x_in, 0), 'test', reuse=None)
grid_area = self.H['grid_height'] * self.H['grid_width']
pred_confidences = tf.reshape(tf.nn.softmax(tf.reshape(pred_confs_deltas, [grid_area * self.H['rnn_len'], 2])),
[grid_area, self.H['rnn_len'], 2])
if self.H['reregress']:
pred_boxes = pred_boxes + pred_boxes_deltas
else:
pred_boxes, pred_logits, pred_confidences = self.build_forward(tf.expand_dims(x_in, 0), 'test', reuse=None)
saver = tf.train.Saver()
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
saver.restore(sess, weights)
pred_annolist = al.AnnoList()
true_annolist = al.parse(test_boxes)
data_dir = os.path.dirname(test_boxes)
image_dir = self.get_image_dir(weights, expname, test_boxes)
subprocess.call('mkdir -p %s' % image_dir, shell=True)
for i in range(len(true_annolist)):
true_anno = true_annolist[i]
orig_img = imread('%s/%s' % (data_dir, true_anno.imageName))[:,:,:3]
img = imresize(orig_img, (self.H["image_height"], self.H["image_width"]), interp='cubic')
feed = {x_in: img}
(np_pred_boxes, np_pred_confidences) = sess.run([pred_boxes, pred_confidences], feed_dict=feed)
pred_anno = al.Annotation()
pred_anno.imageName = true_anno.imageName
new_img, rects = add_rectangles(self.H, [img], np_pred_confidences, np_pred_boxes,
use_stitching=True, rnn_len=self.H['rnn_len'], min_conf=min_conf, tau=tau, show_suppressed=show_suppressed)
pred_anno.rects = rects
pred_anno.imagePath = os.path.abspath(data_dir)
pred_anno = rescale_boxes((self.H["image_height"], self.H["image_width"]), pred_anno, orig_img.shape[0], orig_img.shape[1])
pred_annolist.append(pred_anno)
imname = '%s/%s' % (image_dir, os.path.basename(true_anno.imageName))
misc.imsave(imname, new_img)
if i % 25 == 0:
print(i)
return pred_annolist, true_annolist
def load_idl_tf(idlfile, H, jitter):
"""Take the idlfile and net configuration and create a generator
that outputs a jittered version of a random image from the annolist
that is mean corrected."""
annolist = al.parse(idlfile)
annos = []
for anno in annolist:
anno.imageName = os.path.join(
os.path.dirname(os.path.realpath(idlfile)), anno.imageName)
annos.append(anno)
random.seed(0)
if H['data']['truncate_data']:
annos = annos[:10]
for epoch in itertools.count():
random.shuffle(annos)
for origin_anno in annos:
tiles = preprocess_image(deepcopy(origin_anno), H)
for I, anno in tiles:
if jitter:
jitter_scale_min = 0.9
jitter_scale_max = 1.1
jitter_offset = 16
I, anno = annotation_jitter(
I,
anno,
target_width=H["image_width"],
target_height=H["image_height"],
jitter_scale_min=jitter_scale_min,
jitter_scale_max=jitter_scale_max,
jitter_offset=jitter_offset)
boxes, flags = annotation_to_h5(H, anno)
yield {"image": I, "boxes": boxes, "flags": flags}
parser = argparse.ArgumentParser()
parser.add_argument(
"hit_dir", help="hit directory for storing mturk related data (eg. hit id's and worker results)"
)
parser.add_argument(
"annolist_filename",
help="annotation list in idl/al/pal format, object bounding boxes in the annotation list will be pre-loaded to mturk",
)
args = parser.parse_args()
print "hit_dir: ", args.hit_dir
print "annolist_filename: ", args.annolist_filename
annolist = al.parse(args.annolist_filename)
print "generating hits for {0} images".format(len(annolist))
# load hit-specific parameters
if not os.path.isdir(args.hit_dir):
print args.hit_dir, "does not exist, exiting..."
sys.exit()
else:
hit_params_filename = args.hit_dir + "/hit_params.sh"
print "loading hit parameters from: ", hit_params_filename
if not os.path.isfile(hit_params_filename):
print hit_params_filename, "does not exist, exiting..."
sys.exit()
def __init__(self, al_file):
self.anns = al.parse(al_file)
parser.add_argument(
"annolist_filename",
help=
"annotation list in idl/al/pal format, object bounding boxes in the annotation list will be pre-loaded to mturk"
)
parser.add_argument("--empty_only",
action="store_true",
help="only add images without annotations")
args = parser.parse_args()
print "hit_dir: ", args.hit_dir
print "annolist_filename: ", args.annolist_filename
annolist = al.parse(args.annolist_filename)
print "generating hits for {0} images".format(len(annolist))
# load hit-specific parameters
if not os.path.isdir(args.hit_dir):
print args.hit_dir, "does not exist, exiting..."
sys.exit()
else:
hit_params_filename = args.hit_dir + "/hit_params.sh"
print "loading hit parameters from: ", hit_params_filename
if not os.path.isfile(hit_params_filename):
print hit_params_filename, "does not exist, exiting..."
sys.exit()
def __init__(self, al_file):
self.anns = al.parse(al_file)
