def main(gt_fp: str):
gt = OBBAnns(gt_fp)
gt.load_annotations()
root = split(gt_fp)[0]
# First make perfect proposals
bboxes = gt.ann_info[['bbox', 'cat_id', 'img_id']]
proposals = {'proposals': bboxes.to_dict('records')}
with open(join(root, 'proposals_perfect.json'), 'w') as prop_file:
json.dump(proposals, prop_file)
# Now randomly "forget" certain proposals
selector = [
True if random() > 0.2 else False for _ in range(len(gt.ann_info))
]
bboxes = gt.ann_info[['bbox', 'cat_id',
'img_id']][selector].apply(fudge_bboxes,
1,
result_type='expand')
proposals = {'proposals': bboxes.to_dict('records')}
with open(join(root, 'proposals.json'), 'w') as prop_file:
json.dump(proposals, prop_file)
def load_annotations(self, ann_file):
self.obb = OBBAnns(ann_file)
self.obb.load_annotations()
self.obb.set_annotation_set_filter(['deepscores'])
# self.obb.set_class_blacklist(["staff"])
self.cat_ids = list(self.obb.get_cats().keys())
self.cat2label = {cat_id: i for i, cat_id in enumerate(self.cat_ids)}
self.label2cat = {v: k for k, v in self.cat2label.items()}
self.CLASSES = tuple(
[v["name"] for (k, v) in self.obb.get_cats().items()])
self.img_ids = [id['id'] for id in self.obb.img_info]
return self.obb.img_info
def __init__(self, image_set, year, devkit_path=None):
imdb.__init__(self, 'DeepScoresV2' + year + '_' + image_set)
self._year = year
self._devkit_path = self._get_default_path() if devkit_path is None \
else devkit_path
self._image_set = image_set
self._data_path = self._devkit_path + "/images"
self.blacklist = ["staff", 'legerLine']
self.o = OBBAnns(self._devkit_path+'/deepscores_'+image_set+'.json')
self.o.load_annotations()
print(self.o.annotation_sets)
self.o.set_annotation_set_filter(['deepscores'])
self.o.set_class_blacklist(self.blacklist)
self._classes = [v["name"] for (k, v) in self.o.get_cats().items()]
self._class_ids = [k for (k, v) in self.o.get_cats().items()]
self._class_to_ind = dict(list(zip(self.classes, list(range(self.num_classes)))))
self._class_ids_to_ind = dict(list(zip(self._class_ids, list(range(self.num_classes)))))
self._ind_to_class_ids = {v: k for k, v in self._class_ids_to_ind.items()}
self._image_index = self._load_image_set_index()
# self.cat_ids = list(self.o.get_cats().keys())
# self.cat2label = {
# cat_id: i
# for i, cat_id in enumerate(self.cat_ids)
# }
# self.label2cat = {v: k for k, v in self.cat2label.items()}
# self.CLASSES = tuple([v["name"] for (k, v) in self.o.get_cats().items()])
# self.img_ids = [id['id'] for id in self.o.img_info]
self._image_ext = '.png'
# Default to roidb handler
self._roidb_handler = self.gt_roidb
self._salt = str(uuid.uuid4())
self._comp_id = 'comp4'
# PASCAL specific config options
self.config = {'cleanup': True,
'use_salt': True,
'use_diff': False,
'matlab_eval': False,
'rpn_file': None}
import shutil
import json
import numpy as np
from obb_anns import OBBAnns
from pathlib import Path
ann_in_1 = OBBAnns('data/deep_scores_dense/deepscores_test.json')
ann_in_2 = OBBAnns('../ili_subset/scores.json')
SUFFIX = '_scn'
ann_out_path = Path('..', 'ds_test_ili', 'deepscores_test.json')
ann_in_1.load_annotations()
ann_in_2.load_annotations()
target_ds_root = ann_out_path.parent
assert target_ds_root.exists(), f"Directory of the target dataset ({str(target_ds_root)}) must exist!"
# Make dirs
images_path = Path('images')
segmentation_path = Path('segmentation')
instance_path = Path('instance')
for subdir in [images_path, segmentation_path, instance_path]:
(target_ds_root / subdir).mkdir(exist_ok=True)
print("Copying image files")
def copy_images(ann: OBBAnns, suffix: str = ''):
ds_root = Path(ann.ann_file).parent
for img_info in ann.img_info:
img_path = Path(img_info['filename'])
img_path_new = img_path.with_name(img_path.with_suffix('').name + suffix + img_path.suffix)
parser.add_argument('PROPOSAL',
type=str,
nargs='?',
help='name of the proposals json')
return parser.parse_args()
def extract_bbox_list():
all_bboxes = []
return all_bboxes
if __name__ == '__main__':
args = parse_args()
a = OBBAnns(join(args.ROOT, args.ANNS))
a.load_annotations()
a.set_annotation_set_filter(['deepscores'])
np_annotations = np.stack(a.ann_info['a_bbox'])
height = np_annotations[:, 3] - np_annotations[:, 1]
width = np_annotations[:, 2] - np_annotations[:, 0]
aspect_ratio = height / width
area = a.ann_info['area']
d = {
'height': height,
'width': width,
'aspect_ratio': aspect_ratio,
'area': area
}
parser = ArgumentParser(description='runs the obb_anns.py file')
parser.add_argument('ROOT',
type=str,
help='path to the root of the dataset directory')
return parser.parse_args()
if __name__ == '__main__':
args = parse_args()
root_dir = Path(args.ROOT)
file_names_in_annotations = []
num_ann_files = len(list(root_dir.glob("*.json")))
for i, dataset_ann_fp in enumerate(root_dir.glob("*.json")):
print(f'Checking file {i + 1} of {num_ann_files}...')
a = OBBAnns(join(args.ROOT, dataset_ann_fp))
a.load_annotations()
a.set_annotation_set_filter(['deepscores'])
for img in tqdm(a.img_info, unit='imgs'):
file_names_in_annotations.append(img['filename'])
try:
b = a.get_anns(img_id=img['id'])
except:
print(f'{img["id"]} caused an exception')
file_names_in_annotations = set(file_names_in_annotations)
images_dir = root_dir / 'images_png'
print("Checking if every image has its annotation in the dataset...")
class deep_scoresV2(imdb):
def __init__(self, image_set, year, devkit_path=None):
imdb.__init__(self, 'DeepScoresV2' + year + '_' + image_set)
self._year = year
self._devkit_path = self._get_default_path() if devkit_path is None \
else devkit_path
self._image_set = image_set
self._data_path = self._devkit_path + "/images"
self.blacklist = ["staff", 'legerLine']
self.o = OBBAnns(self._devkit_path+'/deepscores_'+image_set+'.json')
self.o.load_annotations()
print(self.o.annotation_sets)
self.o.set_annotation_set_filter(['deepscores'])
self.o.set_class_blacklist(self.blacklist)
self._classes = [v["name"] for (k, v) in self.o.get_cats().items()]
self._class_ids = [k for (k, v) in self.o.get_cats().items()]
self._class_to_ind = dict(list(zip(self.classes, list(range(self.num_classes)))))
self._class_ids_to_ind = dict(list(zip(self._class_ids, list(range(self.num_classes)))))
self._ind_to_class_ids = {v: k for k, v in self._class_ids_to_ind.items()}
self._image_index = self._load_image_set_index()
# self.cat_ids = list(self.o.get_cats().keys())
# self.cat2label = {
# cat_id: i
# for i, cat_id in enumerate(self.cat_ids)
# }
# self.label2cat = {v: k for k, v in self.cat2label.items()}
# self.CLASSES = tuple([v["name"] for (k, v) in self.o.get_cats().items()])
# self.img_ids = [id['id'] for id in self.o.img_info]
self._image_ext = '.png'
# Default to roidb handler
self._roidb_handler = self.gt_roidb
self._salt = str(uuid.uuid4())
self._comp_id = 'comp4'
# PASCAL specific config options
self.config = {'cleanup': True,
'use_salt': True,
'use_diff': False,
'matlab_eval': False,
'rpn_file': None}
def image_path_at(self, i):
"""
Return the absolute path to image i in the image sequence.
"""
return self.image_path_from_index(self._image_index[i])
def image_path_from_index(self, index):
"""
Construct an image path from the image's "index" identifier.
"""
image_path = os.path.join(self._data_path, self.o.get_imgs(ids=[index])[0]["filename"])
assert os.path.exists(image_path), \
'Path does not exist: {}'.format(image_path)
return image_path
def _load_image_set_index(self):
"""
Load the indexes listed in this dataset's image set file.
"""
# Example path to image set file:
image_index = [x["id"] for x in self.o.img_info]
return image_index
def _get_default_path(self):
"""
Return the default path where PASCAL VOC is expected to be installed.
"""
return os.path.join(cfg.DATA_DIR, 'DeepScores_' + self._year)
def gt_roidb(self):
"""
Return the database of ground-truth regions of interest.
This function loads/saves from/to a cache file to speed up future calls.
"""
cache_file = os.path.join(self.cache_path, self.name + '_gt_roidb.pkl')
# if os.path.exists(cache_file):
# with open(cache_file, 'rb') as fid:
# try:
# roidb = pickle.load(fid)
# except:
# roidb = pickle.load(fid, encoding='bytes')
# print('{} gt roidb loaded from {}'.format(self.name, cache_file))
# return roidb
gt_roidb = [self._load_musical_annotation(index)
for index in self.image_index]
with open(cache_file, 'wb') as fid:
pickle.dump(gt_roidb, fid, pickle.HIGHEST_PROTOCOL)
print('wrote gt roidb to {}'.format(cache_file))
return gt_roidb
def rpn_roidb(self):
if int(self._year) == 2017 or self._image_set != 'debug':
gt_roidb = self.gt_roidb()
rpn_roidb = self._load_rpn_roidb(gt_roidb)
roidb = imdb.merge_roidbs(gt_roidb, rpn_roidb)
else:
roidb = self._load_rpn_roidb(None)
return roidb
def _load_rpn_roidb(self, gt_roidb):
filename = self.config['rpn_file']
print('loading {}'.format(filename))
assert os.path.exists(filename), \
'rpn data not found at: {}'.format(filename)
with open(filename, 'rb') as f:
box_list = pickle.load(f)
return self.create_roidb_from_box_list(box_list, gt_roidb)
def _load_musical_annotation(self, index):
"""
Load annotation info from obb_anns in the PASCAL VOC
format.
"""
anns = self.o.get_anns(img_id=index)
boxes = anns['a_bbox']
boxes = np.round(np.stack(boxes.to_numpy())).astype(np.uint16)
gt_classes = np.squeeze(np.stack(anns['cat_id'].to_numpy()).astype(np.int32))
gt_classes = np.array(list(map(self._class_ids_to_ind.get, gt_classes)))
#blacklisted_anns = [x not in self.blacklist_index for x in gt_classes]
#boxes = boxes[blacklisted_anns]
#gt_classes = gt_classes[blacklisted_anns]
num_objs = boxes.shape[0]
overlaps = np.zeros((num_objs, self.num_classes), dtype=np.float32)
# "Seg" area for pascal is just the box area
seg_areas = np.zeros((num_objs), dtype=np.float32)
for ind in range(boxes.shape[0]):
seg_areas = (boxes[ind,2]-boxes[ind,0]+1) *(boxes[ind,3]-boxes[ind,1]+1)
overlaps[ind, gt_classes[ind]] = 1.0
overlaps = scipy.sparse.csr_matrix(overlaps)
max(gt_classes)
return {'boxes': boxes,
'gt_classes': gt_classes,
'gt_overlaps': overlaps,
'flipped': False,
'seg_areas': seg_areas}
def _get_comp_id(self):
comp_id = (self._comp_id + '_' + self._salt if self.config['use_salt']
else self._comp_id)
return comp_id
def _get_voc_results_file_template(self):
filename = self._get_comp_id() + '_det_' + self._image_set + '_{:s}.txt'
path = os.path.join(
self._devkit_path,
'results',
'musical' + self._year,
filename)
return path
def _write_voc_results_file(self, all_boxes):
for cls_ind, cls in enumerate(self.classes):
if cls == '__background__':
continue
print('Writing {} VOC results file'.format(cls))
filename = self._get_voc_results_file_template().format(cls)
with open(filename, 'wt') as f:
for im_ind, index in enumerate(self.image_index):
dets = all_boxes[cls_ind][im_ind]
if dets == []:
continue
# the VOCdevkit expects 1-based indices
for k in range(dets.shape[0]):
f.write('{:s} {:.3f} {:.1f} {:.1f} {:.1f} {:.1f}\n'.
format(str(index), dets[k, -1],
dets[k, 0] + 1, dets[k, 1] + 1,
dets[k, 2] + 1, dets[k, 3] + 1))
def _do_python_eval(self, output_dir='output', path=None):
annopath = os.path.join(
self._devkit_path,
'segmentation_detection',
'xml_annotations',
'{:s}.xml')
imagesetfile = os.path.join(
self._devkit_path,
'train_val_test',
self._image_set + '.txt')
cachedir = os.path.join(self._devkit_path, 'annotations_cache')
aps = []
# The PASCAL VOC metric changed in 2010
use_07_metric = True if int(self._year) < 2010 else False
print('VOC07 metric? ' + ('Yes' if use_07_metric else 'No'))
if not os.path.isdir(output_dir):
os.mkdir(output_dir)
for i, cls in enumerate(self._classes):
if cls == '__background__':
continue
filename = self._get_voc_results_file_template().format(cls)
rec, prec, ap = voc_eval(
filename, annopath, imagesetfile, cls, cachedir, ovthresh=0.5,
use_07_metric=use_07_metric)
aps += [ap]
print(('AP for {} = {:.4f}'.format(cls, ap)))
with open(os.path.join(output_dir, cls + '_pr.pkl'), 'wb') as f:
pickle.dump({'rec': rec, 'prec': prec, 'ap': ap}, f)
print(('Mean AP = {:.4f}'.format(np.mean(aps))))
print('~~~~~~~~')
print('Results:')
# open the file where we want to save the results
if path is not None:
res_file = open(os.path.join('/DeepWatershedDetection' + path, 'res.txt'),"w+")
len_ap = len(aps)
sum_aps = 0
present = 0
for i in range(len_ap):
print(('{:.3f}'.format(aps[i])))
if i not in [26, 32, 35, 36, 39, 45, 48, 67, 68, 74, 89, 99, 102, 118]:
if math.isnan(aps[i]):
res_file.write(str(0) + "\n")
else:
res_file.write(('{:.3f}'.format(aps[i])) + "\n")
sum_aps += aps[i]
present += 1
res_file.write('\n\n\n')
res_file.write("Mean Average Precision: " + str(sum_aps / float(present)))
res_file.close()
print(('{:.3f}'.format(np.mean(aps))))
print('~~~~~~~~')
print('')
print('--------------------------------------------------------------')
print('Results computed with the **unofficial** Python eval code.')
print('Results should be very close to the official MATLAB eval code.')
print('Recompute with `./tools/reval.py --matlab ...` for your paper.')
print('-- Thanks, The Management')
print('--------------------------------------------------------------')
def _do_matlab_eval(self, output_dir='output'):
print('-----------------------------------------------------')
print('Computing results with the official MATLAB eval code.')
print('-----------------------------------------------------')
path = os.path.join(cfg.ROOT_DIR, 'lib', 'datasets',
'VOCdevkit-matlab-wrapper')
cmd = 'cd {} && '.format(path)
cmd += '{:s} -nodisplay -nodesktop '.format(cfg.MATLAB)
cmd += '-r "dbstop if error; '
cmd += 'voc_eval(\'{:s}\',\'{:s}\',\'{:s}\',\'{:s}\'); quit;"' \
.format(self._devkit_path, self._get_comp_id(),
self._image_set, output_dir)
print(('Running:\n{}'.format(cmd)))
status = subprocess.call(cmd, shell=True)
def evaluate_detections(self, all_boxes, output_dir, path=None):
self._write_voc_results_file(all_boxes)
self._do_python_eval(output_dir, path)
if self.config['matlab_eval']:
self._do_matlab_eval(output_dir)
if self.config['cleanup']:
for cls in self._classes:
if cls == '__background__':
continue
filename = self._get_voc_results_file_template().format(cls)
os.remove(filename)
def competition_mode(self, on):
if on:
self.config['use_salt'] = False
self.config['cleanup'] = False
else:
self.config['use_salt'] = True
self.config['cleanup'] = True
def prepare_json_dict(self, results):
json_results = {"annotation_set": "deepscores", "proposals": []}
for idx in range(len(results)):
img_id = self._image_index[idx]
result = results[idx]
for label in range(len(result)):
bboxes = result[label]
for i in range(bboxes.shape[0]):
data = dict()
data['img_id'] = img_id
data['bbox'] = [str(nr) for nr in bboxes[i][0:-1]]
data['score'] = str(bboxes[i][-1])
data['cat_id'] = self._ind_to_class_ids[label]
json_results["proposals"].append(data)
return json_results
def write_results_json(self, results, filename=None):
if filename is None:
filename = "deepscores_results.json"
json_results = self.prepare_json_dict(results)
with open(filename, "w") as fo:
json.dump(json_results, fo)
return filename
def evaluate(self,
results,
metric='bbox',
logger=None,
jsonfile_prefix=None,
classwise=True,
proposal_nums=(100, 300, 1000),
iou_thrs=np.arange(0.5, 0.96, 0.05),
average_thrs=False,
store_pickle=True):
"""Evaluation in COCO protocol.
Args:
results (list): Testing results of the dataset.
metric (str | list[str]): Metrics to be evaluated.
logger (logging.Logger | str | None): Logger used for printing
related information during evaluation. Default: None.
jsonfile_prefix (str | None): The prefix of json files. It includes
the file path and the prefix of filename, e.g., "a/b/prefix".
If not specified, a temp file will be created. Default: None.
classwise (bool): Whether to evaluating the AP for each class.
proposal_nums (Sequence[int]): Proposal number used for evaluating
recalls, such as recall@100, recall@1000.
Default: (100, 300, 1000).
iou_thrs (Sequence[float]): IoU threshold used for evaluating
recalls. If set to a list, the average recall of all IoUs will
also be computed. Default: 0.5.
Returns:
dict[str: float]
"""
metrics = metric if isinstance(metric, list) else [metric]
allowed_metrics = ['bbox']
for metric in metrics:
if metric not in allowed_metrics:
raise KeyError(f'metric {metric} is not supported')
filename = self.write_results_json(results)
self.o.load_proposals(filename)
metric_results = self.o.calculate_metrics(iou_thrs=iou_thrs, classwise=classwise, average_thrs=average_thrs)
# import pickle
# with open('evaluation.pickle', 'rb') as input_file:
# metric_results = pickle.load(input_file)
# add Name
metric_results = {self._classes[self._class_ids_to_ind[key]]: value for (key, value) in metric_results.items()}
# add occurences
occurences_by_class = self.o.get_class_occurences()
for (key, value) in metric_results.items():
value.update(no_occurences=occurences_by_class[key])
if store_pickle:
import pickle
pickle.dump(metric_results, open('evaluation_renamed.pickle', 'wb'))
return metric_results
from PIL.PngImagePlugin import PngImageFile
from obb_anns import OBBAnns
from pathlib import Path
# source_images = Path('..', 'ili_subset', 'images')
# source_images = Path('..', 'scanned_deepscore_images_png')
source_images = Path('..', 'scanned_deepscore_images_clean')
# source_index = Path('..', 'clean_scans')
# source_index = Path('..', 'scanned_deepscore_images_png')
source_index = Path('..', 'scanned_deepscore_images_clean')
# target_ds = Path('..', 'ili_subset')
target_ds = Path('..', 'deepscores_scanned')
target_ds_file = target_ds / 'deepscores.json'
orig_ann_root = Path('data', 'deep_scores_dense')
orig_ann_train = OBBAnns(str(orig_ann_root / 'deepscores_train.json'))
orig_ann_train.load_annotations()
orig_ann_test = OBBAnns(str(orig_ann_root / 'deepscores_test.json'))
orig_ann_test.load_annotations()
def construct_reverse_lookup(ann: OBBAnns) -> dict:
reverse_lookup = {}
for entry in ann.img_info:
reverse_lookup[entry['filename']] = entry
return reverse_lookup
reverse_lookup_train = construct_reverse_lookup(orig_ann_train)
reverse_lookup_test = construct_reverse_lookup(orig_ann_test)
from obb_anns import OBBAnns
from argparse import ArgumentParser
def parse_args():
parser = ArgumentParser(description='runs the obb_anns.py file')
parser.add_argument('ROOT', type=str,
help='path to the root of the dataset directory')
parser.add_argument('ANNS', type=str,
help='name of the annotation file to use')
parser.add_argument('PROPOSAL', type=str, nargs='?',
help='name of the proposals json')
return parser.parse_args()
if __name__ == '__main__':
args = parse_args()
a = OBBAnns(join(args.ROOT, args.ANNS))
a.load_annotations()
a.set_annotation_set_filter(['deepscores'])
if args.PROPOSAL:
a.load_proposals(join(args.ROOT, args.PROPOSAL))
for i in range(len(a)):
a.visualize(img_idx=i)
# a.visualize(img_idx=i, img_dir='images_png')
response = input('Press q to quit or enter to continue.')
if response == 'q':
break
def main(image_set, single_scale=False):
# (1)
if image_set == 'train':
#dir_txt = os.path.join(dir_dataset, 'labelTxt', image_set)
out_dir_json = os.path.join(dir_dataset, 'annotations', image_set)
os.makedirs(out_dir_json, exist_ok=True)
#txt2json(dir_txt, out_dir_json)
o = OBBAnns(dir_dataset + 'deepscores_train.json')
o.load_annotations()
#print(o)
cats = o.get_cats()
img_idxs = [i for i in range(len(o.img_info))]
imgs, anns = o.get_img_ann_pair(idxs=img_idxs,
ann_set_filter="deepscores")
filenames = []
for img in anns:
objs = []
img_np = np.array(img)
for object_instance in img_np:
obj = dict()
coord = np.array(object_instance[1],
dtype=np.float32).reshape([4, 2])
bbox = cv.boxPoints(cv.minAreaRect(coord)).astype(
np.int).tolist()
obj['name'] = cats[object_instance[2][0]]['name']
obj['bbox'] = bbox
objs.append(obj)
if objs:
filename = o.get_imgs(ids=[int(img_np[0][4])])[0]['filename']
filenames.append(os.path.splitext(filename)[0])
json_filename = os.path.splitext(filename)[0] + '.json'
json.dump(objs,
open(os.path.join(out_dir_json, json_filename),
'wt'),
indent=2)
# Split images and json annotations in train and val files
out_dir_train = os.path.join(dir_dataset, 'images2', 'train')
out_dir_val = os.path.join(dir_dataset, 'images2', 'val')
out_dir_val_json = os.path.join(dir_dataset, 'annotations', 'val')
out_dir_test = os.path.join(dir_dataset, 'images2', 'test')
os.makedirs(out_dir_train, exist_ok=True)
os.makedirs(out_dir_val, exist_ok=True)
os.makedirs(out_dir_test, exist_ok=True)
os.makedirs(out_dir_val_json, exist_ok=True)
filenames_train, filenames_val = train_test_split(filenames,
test_size=272,
random_state=8)
for filename in os.listdir(os.path.join(dir_dataset, 'images')):
if os.path.splitext(filename)[0] in filenames_train:
shutil.move(os.path.join(dir_dataset, 'images', filename),
os.path.join(out_dir_train, filename))
elif os.path.splitext(filename)[0] in filenames_val:
shutil.move(os.path.join(dir_dataset, 'images', filename),
os.path.join(out_dir_val, filename))
shutil.move(
os.path.join(out_dir_json,
os.path.splitext(filename)[0] + '.json'),
os.path.join(out_dir_val_json,
os.path.splitext(filename)[0] + '.json'))
else:
shutil.move(os.path.join(dir_dataset, 'images', filename),
os.path.join(out_dir_test, filename))
os.rmdir(os.path.join(dir_dataset, 'images'))
os.rename(os.path.join(dir_dataset, 'images2'),
os.path.join(dir_dataset, 'images'))
# (2)
pairs = []
for filename in os.listdir(os.path.join(dir_dataset, 'images', image_set)):
anno = os.path.join(dir_dataset, 'annotations', image_set,
filename.replace('png', 'json'))
img = os.path.join(dir_dataset, 'images', image_set, filename)
if not os.path.exists(anno):
anno = None
pairs.append([img, anno])
overlap = 0.25
sizes = [768] if single_scale else [512, 768, 1024, 1536]
save_empty = image_set == 'test'
image_set = f"{image_set}-{sizes[0]}" if single_scale else image_set
out_dir_images = os.path.join(dir_dataset, 'images', f'{image_set}-crop')
out_dir_annos = os.path.join(dir_dataset, 'annotations',
f'{image_set}-crop')
cropper = Cropper(sizes, overlap)
cropper.crop_batch(pairs, out_dir_images, out_dir_annos, save_empty)
# (3)
pairs = []
for filename in os.listdir(out_dir_images):
img = os.path.join('images', f'{image_set}-crop', filename)
anno = None if image_set == 'test' else os.path.join(
'annotations', f'{image_set}-crop', filename.replace(
'jpg', 'json'))
pairs.append([img, anno])
out_dir = os.path.join(dir_dataset, 'image-sets')
os.makedirs(out_dir, exist_ok=True)
json.dump(pairs,
open(os.path.join(out_dir, f'{image_set}.json'), 'wt'),
indent=2)
from mmdet.apis import init_detector, inference_detector
import mmcv
import os
import cv2
from mmdet.core import rotated_box_to_poly_np
from mmcv.visualization import imshow_det_bboxes
import numpy as np
from obb_anns import OBBAnns
annotations_file = "data/deep_scores_dense/deepscores_test.json"
obb = OBBAnns(annotations_file)
obb.load_annotations()
obb.set_annotation_set_filter(['deepscores'])
CLASSES = tuple([v["name"] for (k, v) in obb.get_cats().items()])
config_file = 'DeepScoresV2_s2anet/fullrez_crop/s2anet_r50_fpn_1x_deepscoresv2_tugg_lowrez.py'
checkpoint_file = 'DeepScoresV2_s2anet/fullrez_crop/epoch_500.pth'
model_name = "s2anet_fullrez_crop"
images_folder = "/home/tugg/Documents/RealScores/Realworld_Test"
resize = 1.0
model = init_detector(config_file, checkpoint_file, device='cuda:0')
images = os.listdir(images_folder)
os.makedirs(os.path.join(images_folder, model_name), exist_ok=True)
for img in images:
if os.path.isdir(os.path.join(images_folder, img)):
continue
class DeepScoresV2Dataset(CocoDataset):
def __init__(self,
ann_file,
pipeline,
classes=None,
data_root=None,
img_prefix='',
seg_prefix=None,
proposal_file=None,
test_mode=False,
filter_empty_gt=True,
use_oriented_bboxes=True):
self.filter_empty_gt = filter_empty_gt
super(DeepScoresV2Dataset,
self).__init__(ann_file, pipeline, data_root, img_prefix,
seg_prefix, proposal_file, test_mode)
#self.CLASSES = self.get_classes(classes)
self.use_oriented_bboxes = use_oriented_bboxes
@classmethod
def get_classes(cls, classes=None):
"""Get class names of current dataset.
Args:
classes (Sequence[str] | str | None): If classes is None, use
default CLASSES defined by builtin dataset. If classes is a
string, take it as a file name. The file contains the name of
classes where each line contains one class name. If classes is
a tuple or list, override the CLASSES defined by the dataset.
Returns:
tuple[str] or list[str]: Names of categories of the dataset.
"""
if classes is None:
return cls.CLASSES
if isinstance(classes, str):
# take it as a file path
class_names = mmcv.list_from_file(classes)
elif isinstance(classes, (tuple, list)):
class_names = classes
else:
raise ValueError(f'Unsupported type {type(classes)} of classes.')
return class_names
def load_annotations(self, ann_file):
self.obb = OBBAnns(ann_file)
self.obb.load_annotations()
self.obb.set_annotation_set_filter(['deepscores'])
# self.obb.set_class_blacklist(["staff"])
self.cat_ids = list(self.obb.get_cats().keys())
self.cat2label = {cat_id: i for i, cat_id in enumerate(self.cat_ids)}
self.label2cat = {v: k for k, v in self.cat2label.items()}
self.CLASSES = tuple(
[v["name"] for (k, v) in self.obb.get_cats().items()])
self.img_ids = [id['id'] for id in self.obb.img_info]
return self.obb.img_info
def get_ann_info(self, idx):
return self._parse_ann_info(*self.obb.get_img_ann_pair(idxs=[idx]))
def _filter_imgs(self, min_size=32):
valid_inds = []
for i, img_info in enumerate(self.obb.img_info):
if self.filter_empty_gt and len(img_info['ann_ids']) == 0:
continue
if min(img_info['width'], img_info['height']) >= min_size:
valid_inds.append(i)
return valid_inds
def _parse_ann_info(self, img_info, ann_info):
img_info, ann_info = img_info[0], ann_info[0]
gt_bboxes = []
gt_labels = []
gt_bboxes_ignore = np.zeros((0, 8 if self.use_oriented_bboxes else 4),
dtype=np.float32)
for i, ann in ann_info.iterrows():
# we have no ignore feature
if ann['area'] <= 0:
continue
bbox = ann['o_bbox' if self.use_oriented_bboxes else 'a_bbox']
gt_bboxes.append(bbox)
gt_labels.append(self.cat2label[ann['cat_id'][0]])
gt_bboxes = np.array(gt_bboxes, dtype=np.float32)
gt_labels = np.array(gt_labels, dtype=np.int64)
ann = dict(bboxes=gt_bboxes,
labels=gt_labels,
bboxes_ignore=gt_bboxes_ignore,
masks=None,
seg_map=None)
return ann
def prepare_json_dict(self, results):
json_results = {"annotation_set": "deepscores", "proposals": []}
for idx in range(len(self)):
img_id = self.img_ids[idx]
result = results[idx]
for label in range(len(result)):
bboxes = result[label]
for i in range(bboxes.shape[0]):
data = dict()
data['img_id'] = img_id
if len(bboxes[i]) == 8:
data['bbox'] = [str(nr) for nr in bboxes[i]]
data['score'] = 1
else:
data['bbox'] = [str(nr) for nr in bboxes[i][0:-1]]
data['score'] = str(bboxes[i][-1])
data['cat_id'] = self.label2cat[label]
json_results["proposals"].append(data)
return json_results
def write_results_json(self, results, filename=None):
if filename is None:
filename = "deepscores_results.json"
json_results = self.prepare_json_dict(results)
with open(filename, "w") as fo:
json.dump(json_results, fo)
return filename
def evaluate(self,
results,
metric='bbox',
logger=None,
jsonfile_prefix=None,
classwise=True,
proposal_nums=(100, 300, 1000),
iou_thrs=np.arange(0.5, 0.96, 0.05),
average_thrs=False,
work_dir=None):
"""Evaluation in COCO protocol.
Args:
results (list): Testing results of the dataset.
metric (str | list[str]): Metrics to be evaluated.
logger (logging.Logger | str | None): Logger used for printing
related information during evaluation. Default: None.
jsonfile_prefix (str | None): The prefix of json files. It includes
the file path and the prefix of filename, e.g., "a/b/prefix".
If not specified, a temp file will be created. Default: None.
classwise (bool): Whether to evaluating the AP for each class.
proposal_nums (Sequence[int]): Proposal number used for evaluating
recalls, such as recall@100, recall@1000.
Default: (100, 300, 1000).
iou_thrs (Sequence[float]): IoU threshold used for evaluating
recalls. If set to a list, the average recall of all IoUs will
also be computed. Default: 0.5.
Returns:
dict[str: float]
"""
metrics = metric if isinstance(metric, list) else [metric]
allowed_metrics = ['bbox']
for metric in metrics:
if metric not in allowed_metrics:
raise KeyError(f'metric {metric} is not supported')
filename = self.write_results_json(results)
self.obb.load_proposals(filename)
metric_results = self.obb.calculate_metrics(iou_thrs=iou_thrs,
classwise=classwise,
average_thrs=average_thrs)
categories = self.obb.get_cats()
metric_results = {
categories[key]['name']: value
for (key, value) in metric_results.items()
}
# add occurences
occurences_by_class = self.obb.get_class_occurences()
for (key, value) in metric_results.items():
value.update(no_occurences=occurences_by_class[key])
if work_dir is not None:
import pickle
import os
out_file = os.path.join(work_dir, "dsv2_metrics.pkl")
pickle.dump(metric_results, open(out_file, 'wb'))
print(metric_results)
return metric_results
class DeepScoresV2Dataset(CocoDataset):
def load_annotations(self, ann_file):
self.obb = OBBAnns(ann_file)
self.obb.load_annotations()
self.obb.set_annotation_set_filter(['deepscores'])
self.obb.set_class_blacklist(["staff"])
self.cat_ids = list(self.obb.get_cats().keys())
self.cat2label = {cat_id: i for i, cat_id in enumerate(self.cat_ids)}
self.label2cat = {v: k for k, v in self.cat2label.items()}
self.CLASSES = tuple(
[v["name"] for (k, v) in self.obb.get_cats().items()])
self.img_ids = [id['id'] for id in self.obb.img_info]
return self.obb.img_info
def get_ann_info(self, idx):
return self._parse_ann_info(*self.obb.get_img_ann_pair(idxs=[idx]))
def _filter_imgs(self, min_size=32):
valid_inds = []
for i, img_info in enumerate(self.obb.img_info):
if self.filter_empty_gt and len(img_info['ann_ids']) == 0:
continue
if min(img_info['width'], img_info['height']) >= min_size:
valid_inds.append(i)
return valid_inds
def _parse_ann_info(self, img_info, ann_info):
img_info, ann_info = img_info[0], ann_info[0]
gt_bboxes = []
gt_labels = []
gt_bboxes_ignore = np.zeros((0, 4), dtype=np.float32)
for i, ann in ann_info.iterrows():
# we have no ignore feature
if ann['area'] <= 0:
continue
bbox = ann['a_bbox']
gt_bboxes.append(bbox)
gt_labels.append(self.cat2label[ann['cat_id'][0]])
gt_bboxes = np.array(gt_bboxes, dtype=np.float32)
gt_labels = np.array(gt_labels, dtype=np.int64)
ann = dict(bboxes=gt_bboxes,
labels=gt_labels,
bboxes_ignore=gt_bboxes_ignore,
masks=None,
seg_map=None)
return ann
def prepare_json_dict(self, results):
json_results = {"annotation_set": "deepscores", "proposals": []}
for idx in range(len(self)):
img_id = self.img_ids[idx]
result = results[idx]
for label in range(len(result)):
bboxes = result[label]
for i in range(bboxes.shape[0]):
data = dict()
data['img_id'] = img_id
data['bbox'] = [str(nr) for nr in bboxes[i][0:-1]]
data['score'] = str(bboxes[i][-1])
data['cat_id'] = self.label2cat[label]
json_results["proposals"].append(data)
return json_results
def write_results_json(self, results, filename=None):
if filename is None:
filename = "deepscores_results.json"
json_results = self.prepare_json_dict(results)
with open(filename, "w") as fo:
json.dump(json_results, fo)
return filename
def evaluate(self,
results,
metric='bbox',
logger=None,
jsonfile_prefix=None,
classwise=True,
proposal_nums=(100, 300, 1000),
iou_thrs=np.arange(0.5, 0.96, 0.05),
average_thrs=False):
"""Evaluation in COCO protocol.
Args:
results (list): Testing results of the dataset.
metric (str | list[str]): Metrics to be evaluated.
logger (logging.Logger | str | None): Logger used for printing
related information during evaluation. Default: None.
jsonfile_prefix (str | None): The prefix of json files. It includes
the file path and the prefix of filename, e.g., "a/b/prefix".
If not specified, a temp file will be created. Default: None.
classwise (bool): Whether to evaluating the AP for each class.
proposal_nums (Sequence[int]): Proposal number used for evaluating
recalls, such as recall@100, recall@1000.
Default: (100, 300, 1000).
iou_thrs (Sequence[float]): IoU threshold used for evaluating
recalls. If set to a list, the average recall of all IoUs will
also be computed. Default: 0.5.
Returns:
dict[str: float]
"""
metrics = metric if isinstance(metric, list) else [metric]
allowed_metrics = ['bbox']
for metric in metrics:
if metric not in allowed_metrics:
raise KeyError(f'metric {metric} is not supported')
filename = self.write_results_json(results)
self.obb.load_proposals(filename)
metric_results = self.obb.calculate_metrics(iou_thrs=iou_thrs,
classwise=classwise,
average_thrs=average_thrs)
metric_results = {
self.CLASSES[self.cat2label[key]]: value
for (key, value) in metric_results.items()
}
# add occurences
occurences_by_class = self.obb.get_class_occurences()
for (key, value) in metric_results.items():
value.update(no_occurences=occurences_by_class[key])
if True:
import pickle
pickle.dump(metric_results,
open('evaluation_renamed_rcnn.pickle', 'wb'))
print(metric_results)
return metric_results
def draw_bbox(self,
draw,
ann,
color,
oriented,
annotation_set=None,
print_label=False,
print_staff_pos=False,
print_onset=False,
instances=False):
"""Draws the bounding box onto an image with a given color.
:param ImageDraw.ImageDraw draw: ImageDraw object to draw with.
:param dict ann: Annotation information dictionary of the current
bounding box to draw.
:param str color: Color to draw the bounding box in as a hex string,
e.g. '#00ff00'
:param bool oriented: Choose between drawing oriented or aligned
bounding box.
:param Optional[int] annotation_set: Index of the annotation set to be
drawn. If None is given, the first one available will be drawn.
:param Optional[bool] print_label: Determines if the class labels
are printed on the visualization
:param Optional[bool] print_staff_pos: Determines if the staff positions
are printed on the visualization
:param Optional[bool] print_onset: Determines if the onsets are
printed on the visualization
:return: The drawn object.
:rtype: ImageDraw.ImageDraw
"""
annotation_set = 0 if annotation_set is None else annotation_set
cat_id = ann['cat_id']
if isinstance(cat_id, list):
cat_id = int(cat_id[annotation_set])
parsed_comments = OBBAnns.parse_comments(ann['comments'])
if oriented:
bbox = ann['o_bbox']
draw.line(bbox + bbox[:2], fill=color, width=3)
else:
bbox = ann['a_bbox']
draw.rectangle(bbox, outline=color, width=2)
# Now draw the label below the bbox
x0 = min(bbox[::2])
y0 = max(bbox[1::2])
pos = (x0, y0)
def print_text_label(position, text, color_text, color_box):
x1, y1 = ImageFont.load_default().getsize(text)
x1 += position[0] + 4
y1 += position[1] + 4
draw.rectangle((position[0], position[1], x1, y1), fill=color_box)
draw.text((position[0] + 2, position[1] + 2), text, color_text)
return x1, position[1]
if instances:
label = str(int(parsed_comments['instance'].lstrip('#'), 16))
print_text_label(pos, label, '#ffffff', '#303030')
else:
label = self.cat_info[cat_id]['name']
if print_label:
pos = print_text_label(pos, label, '#ffffff', '#303030')
if print_onset and 'onset' in parsed_comments.keys():
pos = print_text_label(pos, parsed_comments['onset'], '#ffffff',
'#091e94')
if print_staff_pos and 'rel_position' in parsed_comments.keys():
print_text_label(pos, parsed_comments['rel_position'], '#ffffff',
'#0a7313')
return draw
else:
label = self.cat_info[cat_id]['name']
if print_label:
pos = print_text_label(pos, label, '#ffffff', '#303030')
if print_onset and 'onset' in parsed_comments.keys():
pos = print_text_label(pos, parsed_comments['onset'], '#ffffff',
'#091e94')
if print_staff_pos and 'rel_position' in parsed_comments.keys():
print_text_label(pos, parsed_comments['rel_position'], '#ffffff',
'#0a7313')
return draw
ann = OBBAnns('../scanned_ds/ili_scores.json')
ann.load_annotations()
data_root = '../scanned_ds'
out_dir = 'out_ili'
annotation_set = 'deepscores'
annotation_set = ann.annotation_sets.index(annotation_set)
ann.chosen_ann_set = ann.chosen_ann_set[annotation_set]
for img_info in ann.img_info:
img_id = img_info['id']
ann.visualize(img_id=img_id, data_root=data_root, out_dir=out_dir)
# img_info, ann_info = ann.get_img_ann_pair(ids=[img_id])
# img_info, ann_info = img_info[0], ann_info[0]
#
# # Get the data_root from the ann_file path if it doesn't exist
# if data_root is None:
# data_root = osp.split(ann.ann_file)[0]