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 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)
rect.x1 = vatic_boxes[bidx].xtl;
rect.y1 = vatic_boxes[bidx].ytl;
rect.x2 = vatic_boxes[bidx].xbr;
rect.y2 = vatic_boxes[bidx].ybr
cur_frame = vatic_boxes[bidx].frame;
annolist[cur_frame].rects.append(rect);
# save annolist
fname_ext = os.path.basename(opts.vatic_filename);
fname = os.path.splitext(fname_ext)[0];
pal_filename = opts.output_dir + "/" + fname + ".pal";
print "saving ", pal_filename;
AnnotationLib.save(pal_filename, annolist);
# if not os.path.exists(opts.output_dir):
# print "creating ", opts.output_dir;
# os.makedirs(opts.output_dir);
# imglist = glob.glob(opts.input_dir + "/*.jpeg");
# imglist.sort();
# idxlist = range(0, len(imglist), opts.imgstep);
# print idxlist;
rect.id = tidx
rect.x1 = vatic_boxes[bidx].xtl
rect.y1 = vatic_boxes[bidx].ytl
rect.x2 = vatic_boxes[bidx].xbr
rect.y2 = vatic_boxes[bidx].ybr
cur_frame = vatic_boxes[bidx].frame
annolist[cur_frame].rects.append(rect)
# save annolist
fname_ext = os.path.basename(opts.vatic_filename)
fname = os.path.splitext(fname_ext)[0]
pal_filename = opts.output_dir + "/" + fname + ".pal"
print "saving ", pal_filename
AnnotationLib.save(pal_filename, annolist)
# if not os.path.exists(opts.output_dir):
# print "creating ", opts.output_dir;
# os.makedirs(opts.output_dir);
# imglist = glob.glob(opts.input_dir + "/*.jpeg");
# imglist.sort();
# idxlist = range(0, len(imglist), opts.imgstep);
# print idxlist;
# if idxlist[-1] != len(imglist) - 1:
# idxlist.append(len(imglist) - 1);
def main():
parser = argparse.ArgumentParser()
parser.add_argument("hits_dir", help="hit directory")
parser.add_argument("--print_empty", action="store_true", help="print info on empty hits");
parser.add_argument("--save_worker_results", action="store_true", help="save results for each individual worker");
#parser.add_argument("output_ext", default=".al", help="output format .idl/.al/.pal")
#parser.add_argument("--url_prefix", help="path on S3 that should be removed when converting to annolist")
args = parser.parse_args()
#url_prefix = bash_var_to_py("./data_utils_init.sh", "S3_HOST_DIR")
url_prefix = bash_var_to_py(args.hits_dir + "/hit_params.sh", "S3_HOST_DIR")
args.output_ext = ".pal"
if url_prefix[-1] != os.sep:
url_prefix += os.sep;
hit_name = get_hit_name(args.hits_dir)
#pal_name = args.hits_dir + '/' + hit_name + '.pal'
pal_name = args.hits_dir + '/' + hit_name + args.output_ext
results_filename = args.hits_dir + '/' + hit_name + '.results'
results_by_worker_dir = '%s/results_by_worker_%s' % (args.hits_dir, hit_name)
subprocess.call(['mkdir', '-p', results_by_worker_dir])
try:
with open(args.hits_dir + '/bad_workers.txt', 'r') as f:
bad_workerids = set(x.strip() for x in f.readlines())
except IOError:
bad_workerids = set()
with open(results_filename, 'r') as results_file:
results_list = list(csv.reader(results_file, delimiter='\t'))
invert = lambda d: {v:k for k,v in d.iteritems()}
columns = invert(dict(enumerate(results_list[0])))
annotation_list = AnnotationLib.AnnoList();
hit_type = "";
for each in results_list[1:]:
if each[columns['hitstatus']] == 'Reviewable' and each[columns['workerid']] not in bad_workerids:
cur_hit_type = each[columns['Answer.results']].split(',')[0];
if not hit_type:
hit_type = cur_hit_type;
else:
assert(hit_type == cur_hit_type);
a = annotation_from_result(each, columns, url_prefix);
annotation_list.append(a);
# MA: some hit types require special post-processing
if hit_type == "label_act":
annotation_list = merge_labelact_annolist(annotation_list);
annotation_list.add_attribute("gender", int);
annotation_list.add_attribute("ptype", int);
annotation_list.add_attribute("act", int);
annotation_list.add_attribute_val("gender", "male", ATTR_VAL_GENDER_MALE);
annotation_list.add_attribute_val("gender", "female", ATTR_VAL_GENDER_FEMALE);
annotation_list.add_attribute_val("ptype", "sales", ATTR_VAL_PTYPE_SALES);
annotation_list.add_attribute_val("ptype", "customer", ATTR_VAL_PTYPE_CUST);
annotation_list.add_attribute_val("act", "interact_with_customer", ATTR_VAL_ACT_SALES_INT);
annotation_list.add_attribute_val("act", "clean", ATTR_VAL_ACT_SALES_CLEAN);
annotation_list.add_attribute_val("act", "other_sales", ATTR_VAL_ACT_SALES_OTHER);
annotation_list.add_attribute_val("act", "queue", ATTR_VAL_ACT_CUST_QUEUE);
annotation_list.add_attribute_val("act", "interact_with_sales", ATTR_VAL_ACT_CUST_INT);
annotation_list.add_attribute_val("act", "browse", ATTR_VAL_ACT_CUST_BROWSE);
annotation_list.add_attribute_val("act", "other_customer", ATTR_VAL_ACT_CUST_OTHER);
AnnotationLib.save(pal_name, annotation_list)
if args.save_worker_results:
for workerid in set(x[columns['workerid']] for x in results_list[1:]):
if workerid == '':
print '%s missing entries' % sum(1 for each in results_list[1:]
if each[columns['workerid']] == '')
continue
annotation_list = AnnotationLib.AnnoList([annotation_from_result(each, columns, url_prefix)
for each in results_list[1:]
if each[columns['hitstatus']] == 'Reviewable'
and each[columns['workerid']] == workerid]);
output_filename = '%s/%s.pal' % (results_by_worker_dir, workerid);
#print "saving ", output_filename;
print "worker: {}, number of annotations: {}".format(workerid, len(annotation_list));
AnnotationLib.save(output_filename, annotation_list)
if args.print_empty:
for res in results_list[1:]:
if res[columns['Answer.results']] == "":
print "empty hit: ", res
# show statistics on empty results (happens due to unknown bug in javascript tool)
empty_res_workers = [each[columns['workerid']] for each in results_list[1:] if each[columns['Answer.results']] == ""];
print "empty output by workerid: "
for workerid, worker_empty_count in collections.Counter(empty_res_workers).items():
print workerid, worker_empty_count
num_empty = sum((1 for each in results_list[1:] if each[columns['Answer.results']] == ""));
print "number of empty results: ", num_empty
