def get_meta_from_filename(self, filename, name):
coco = self.get_entry_from_filename(filename)
imid = int(filename.split('_')[-1])
catid = coco.getCatIds(catNms=name)[0]
return OrderedDict([
('id', str(filename)),
('imid', imid),
('category_id', catid),
('category', str(name)),
('supercategory', coco.cats[catid]['supercategory']),
# ('filename', os.path.join(self.home(self.SUBDIR, self.IMAGEDIR),
# filename + '.jpg'))
])
def coco(writer, name_index, profile, row, verify=False):
root = os.path.expanduser(os.path.expandvars(row['root']))
year = str(row['year'])
name = profile + year
path = os.path.join(root, 'annotations', 'instances_%s.json' % name)
if not os.path.exists(path):
tf.logging.warn(path + ' not exists')
return False
import pycocotools.coco
coco = pycocotools.coco.COCO(path)
catIds = coco.getCatIds(catNms=list(name_index.keys()))
cats = coco.loadCats(catIds)
id_index = dict((cat['id'], name_index[cat['name']]) for cat in cats)
imgIds = coco.getImgIds()
path = os.path.join(root, name)
imgs = coco.loadImgs(imgIds)
_imgs = list(filter(lambda img: os.path.exists(os.path.join(path, img['file_name'])), imgs))
if len(imgs) > len(_imgs):
tf.logging.warn('%d of %d images not exists' % (len(imgs) - len(_imgs), len(imgs)))
cnt_noobj = 0
for img in tqdm.tqdm(_imgs):
annIds = coco.getAnnIds(imgIds=img['id'], catIds=catIds, iscrowd=None)
anns = coco.loadAnns(annIds)
if len(anns) <= 0:
cnt_noobj += 1
continue
imagepath = os.path.join(path, img['file_name'])
width, height = img['width'], img['height']
imageshape = [height, width, 3]
objects_class = np.array([id_index[ann['category_id']] for ann in anns], dtype=np.int64)
objects_coord = [ann['bbox'] for ann in anns]
objects_coord = [(x, y, x + w, y + h) for x, y, w, h in objects_coord]
objects_coord = np.array(objects_coord, dtype=np.float32)
if verify:
if not verify_coords(objects_coord, imageshape):
tf.logging.error('failed to verify coordinates of ' + imagepath)
continue
if not verify_image_jpeg(imagepath, imageshape):
tf.logging.error('failed to decode ' + imagepath)
continue
assert len(objects_class) == len(objects_coord)
example = tf.train.Example(features=tf.train.Features(feature={
'imagepath': tf.train.Feature(bytes_list=tf.train.BytesList(value=[tf.compat.as_bytes(imagepath)])),
'imageshape': tf.train.Feature(int64_list=tf.train.Int64List(value=imageshape)),
'objects': tf.train.Feature(bytes_list=tf.train.BytesList(value=[objects_class.tostring(), objects_coord.tostring()])),
}))
writer.write(example.SerializeToString())
if cnt_noobj > 0:
tf.logging.warn('%d of %d images have no object' % (cnt_noobj, len(_imgs)))
return True
def get_category_info(category_names, coco):
"""
Get the coco category info and image ids for given category names.
:param category_names: List of category names.
:param coco: Pycocotools COCO instance.
:return: Dict with:
category_info['person'] = (id, [image_ids, ...])
"""
category_ids = zip(category_names, coco.getCatIds(catNms=category_names))
info = {}
for category_name, category_id in category_ids:
image_ids = coco.getImgIds(catIds=category_id)
info[category_name] = (category_id, image_ids)
return info
def get_keypoint_names(parameters):
"""
Return the keypoint names for persons category.
:param parameters: Dict with:
parameters = {
'coco-data-dir': pathlib.Path(...),
'annotations': Path to annotations file with keypoints
}
:return: List of keypoint names.
"""
coco = pycocotools.coco.COCO(
str(parameters['coco-data-dir'] / parameters['annotations']))
category_id = coco.getCatIds('person')
category_info = coco.loadCats(category_id)[0]
keypoint_names = category_info['keypoints']
return keypoint_names
dataType = 'val2014'
dirImg = '%s/%s' % (dataDir, dataType)
if not os.path.isdir(dirImg):
raise Exception('Cant find directory with images [%s]' % dirImg)
dirOut = '%s/%s-food2' % (dataDir, dataType)
makeDirIfNotExists(pathToDir=dirOut, isCleanIfExists=False)
#
annFile = '%s/annotations/instances_%s.json' % (dataDir, dataType)
imgDir = '%s/%s' % (dataDir, dataType)
if not os.path.isdir(imgDir):
raise Exception('Cant find directory with MS-COCO images [%s]' %
dataDir)
#
coco = COCO(annFile)
#
listCatsFoodIdx = coco.getCatIds(supNms=['food'])
assert (set(listCatsFoodIdx) == set(listSortedFoodIds))
for ii, idx in enumerate(listCatsFoodIdx):
tmpCat = coco.loadCats(ids=idx)[0]
print('%d [%d] : %s (%s)' %
(ii, idx, tmpCat['name'], tmpCat['supercategory']))
#
tmpDictFoodImgIds = {}
for ii, idx in enumerate(listSortedFoodIds):
tmpImgIds = coco.getImgIds(catIds=idx)
for timgId in tmpImgIds:
if tmpDictFoodImgIds.has_key(timgId):
tmpDictFoodImgIds[timgId].append(idx)
else:
tmpDictFoodImgIds[timgId] = [idx]
setAllFoodImgIds = sorted(tmpDictFoodImgIds.keys())
STD = np.array([0.289, 0.274, 0.278]).astype(np.float32)
max_objs = 32
_valid_ids = [1]
class_name = ['__background__', 'person']
_data_rng = np.random.RandomState(123)
_eig_val = np.array([0.2141788, 0.01817699, 0.00341571], dtype=np.float32)
_eig_vec = np.array([[-0.58752847, -0.69563484, 0.41340352],
[-0.5832747, 0.00994535, -0.81221408],
[-0.56089297, 0.71832671, 0.41158938]],
dtype=np.float32)
coco = coco.COCO(anno_path)
images = coco.getImgIds()
catIds = coco.getCatIds(class_name[-1])
assert catIds == _valid_ids
images = coco.getImgIds(images, catIds)
num_samples = len(images)
index = np.random.randint(num_samples)
img_id = images[index]
file_name = coco.loadImgs(ids=[img_id])[0]['file_name']
img_path = os.path.join(img_dir, file_name)
ann_ids = coco.getAnnIds(imgIds=[img_id])
anns = coco.loadAnns(ids=ann_ids)
anns = list(
filter(lambda x: x['category_id'] in _valid_ids and x['iscrowd'] != 1,
anns))
def cache(config, path, category_index):
phase = os.path.splitext(os.path.basename(path))[0]
data = []
for i, row in pd.read_csv(os.path.splitext(__file__)[0] + '.tsv',
sep='\t').iterrows():
logging.info('loading data %d (%s)' %
(i, ', '.join([k + '=' + str(v)
for k, v in row.items()])))
root = os.path.expanduser(os.path.expandvars(row['root']))
year = str(row['year'])
suffix = phase + year
path = os.path.join(root, 'annotations', 'instances_%s.json' % suffix)
if not os.path.exists(path):
logging.warning(path + ' not exists')
continue
coco = pycocotools.coco.COCO(path)
catIds = coco.getCatIds(catNms=list(category_index.keys()))
cats = coco.loadCats(catIds)
id_index = dict(
(cat['id'], category_index[cat['name']]) for cat in cats)
imgIds = coco.getImgIds()
path = os.path.join(root, suffix)
imgs = coco.loadImgs(imgIds)
_imgs = list(
filter(
lambda img: os.path.exists(os.path.join(
path, img['file_name'])), imgs))
if len(imgs) > len(_imgs):
logging.warning('%d of %d images not exists' %
(len(imgs) - len(_imgs), len(imgs)))
for img in tqdm.tqdm(_imgs):
annIds = coco.getAnnIds(imgIds=img['id'],
catIds=catIds,
iscrowd=None)
anns = coco.loadAnns(annIds)
if len(anns) <= 0:
continue
path = os.path.join(path, img['file_name'])
width, height = img['width'], img['height']
bbox = np.array([ann['bbox'] for ann in anns], dtype=np.float32)
yx_min = bbox[:, 1::-1]
hw = bbox[:, -1:1:-1]
yx_max = yx_min + hw
cls = np.array([id_index[ann['category_id']] for ann in anns],
dtype=np.int)
difficult = np.zeros(cls.shape, dtype=np.uint8)
try:
if config.getboolean('cache', 'verify'):
size = (height, width)
image = cv2.imread(path)
assert image is not None
assert image.shape[:2] == size[:2]
utils.cache.verify_coords(yx_min, yx_max, size[:2])
except configparser.NoOptionError:
pass
assert len(yx_min) == len(cls)
assert yx_min.shape == yx_max.shape
assert len(yx_min.shape) == 2 and yx_min.shape[-1] == 2
data.append(
dict(path=path,
yx_min=yx_min,
yx_max=yx_max,
cls=cls,
difficult=difficult))
logging.warning('%d of %d images are saved' % (len(data), len(_imgs)))
return data
def main(input_json: str,
image_dir: str,
coco_output_dir: Optional[str],
tfrecords_output_dir: Optional[str],
detection_output: str,
detection_input: Optional[str],
split_by: str,
exclude_categories: List[str],
detection_threshold: float,
padding_factor: float,
test_fraction: float,
ims_per_record: int) -> None:
"""
Args:
input_json: str, path to JSON file with COCO-style dataset annotations
image_dir: str, path to root folder of images
coco_output_dir: str, path to output directory for a dataset in COCO
format
tfrecords_output_dir: str, path to output directory for a dataset in
TFRecords format
detection_output: str, path to pickle file for saving detections
detection_input: str, path to pickle file of existing detections
generated by this script, used to continue a partially processed
dataset
split_by: str, key in image-level annotations that specifies the
splitting criteria
exclude_categories: list of str, names of categories to ignore during
detection
detection_threshold: float, in [0, 1]
padding_factor: float, padding around detected objects when cropping
test_fraction: float, in [0, 1]
ims_per_record: int
"""
graph = load_frozen_graph(args.frozen_graph)
# Load COCO style annotations from the input dataset
coco = pycocotools.coco.COCO(input_json)
# Get all categories, their names, and create updated ID for the json file
categories = coco.loadCats(coco.getCatIds())
cat_id_to_names = {cat['id']: cat['name'] for cat in categories}
cat_id_to_new_id = {
old_key: idx
for idx, old_key in enumerate(cat_id_to_names.keys())
}
print('All categories:', list(cat_id_to_names.values()))
for ignore_cat in exclude_categories:
if ignore_cat not in cat_id_to_names.values():
raise ValueError(f'Category {ignore_cat} does not exist in dataset')
# Prepare the coco-style json files
train_json = dict(images=[], categories=[], annotations=[])
test_json = dict(images=[], categories=[], annotations=[])
for old_cat_id in cat_id_to_names.keys():
train_json['categories'].append(dict(
id=cat_id_to_new_id[old_cat_id],
name=cat_id_to_names[old_cat_id],
supercategory='entity'))
test_json['categories'] = train_json['categories']
# Split the dataset by locations
random.seed(0)
print('Example of the annotation of a single image:')
print(list(coco.imgs.items())[0])
print('The corresponding category annoation:')
print(coco.imgToAnns[list(coco.imgs.items())[0][0]])
locations = sorted(set(ann[split_by] for ann in coco.imgs.values()))
test_locations = sorted(
random.sample(locations, max(1, int(test_fraction * len(locations)))))
train_locations = sorted(set(locations) - set(test_locations))
print('{} locations in total, {} for training, {} for testing'.format(
len(locations), len(train_locations), len(test_locations)))
print('Training uses locations ', train_locations)
print('Testing uses locations ', test_locations)
# Load detections
if detection_input is not None:
print(f'Loading existing detections from {detection_input}')
with open(detection_input, 'rb') as f:
detections = pickle.load(f)
else:
detections = dict()
train_tfr_writer = None
test_tfr_writer = None
if tfrecords_output_dir is not None:
train_tfr_writer = TFRecordsWriter(
os.path.join(tfrecords_output_dir, 'train-{:05d}'), ims_per_record)
test_tfr_writer = TFRecordsWriter(
os.path.join(tfrecords_output_dir, 'test-{:05d}'), ims_per_record)
with graph.as_default():
with tf.Session() as sess:
run_detection(
sess, coco, cat_id_to_names, cat_id_to_new_id, detections,
train_locations, train_json, test_json, train_tfr_writer,
test_tfr_writer, image_dir, coco_output_dir, split_by,
exclude_categories, detection_threshold, padding_factor)
if tfrecords_output_dir is not None:
train_tfr_writer.close()
test_tfr_writer.close()
label_map = [
'item {{name: "{}" id: {}}}\n'.format(cat['name'], cat['id'])
for cat in train_json['categories']]
pbtxt_path = os.path.join(tfrecords_output_dir, 'label_map.pbtxt')
with open(pbtxt_path, 'w') as f:
f.write(''.join(label_map))
if coco_output_dir is not None:
# Write out COCO-style json files to the output directory
with open(os.path.join(coco_output_dir, 'train.json'), 'wt') as fi:
json.dump(train_json, fi)
with open(os.path.join(coco_output_dir, 'test.json'), 'wt') as fi:
json.dump(test_json, fi)
# Write detections to file with pickle
with open(detection_output, 'wb') as f:
pickle.dump(detections, f, pickle.HIGHEST_PROTOCOL)
def load_coco(self,
dataset_dir,
subset,
year=DEFAULT_DATASET_YEAR,
class_ids=None,
class_map=None,
return_coco=False,
auto_download=False):
"""Load a subset of the COCO dataset.
dataset_dir: The root directory of the COCO dataset.
subset: What to load (train, val, minival, valminusminival)
year: What dataset year to load (2014, 2017) as a string, not an integer
class_ids: If provided, only loads images that have the given classes.
class_map: TODO: Not implemented yet. Supports maping classes from
different datasets to the same class ID.
return_coco: If True, returns the COCO object.
auto_download: Automatically download and unzip MS-COCO images and annotations
"""
if auto_download is True:
self.auto_download(dataset_dir, subset, year)
coco = COCO("{}/annotations/instances_{}{}.json".format(
dataset_dir, subset, year))
if subset == "minival" or subset == "valminusminival":
subset = "val"
image_dir = "{}/{}{}".format(dataset_dir, subset, year)
# Load all classes or a subset?
if not class_ids:
# All classes
class_ids = sorted(coco.getCatIds())
# All images or a subset?
if class_ids:
image_ids = []
for id in class_ids:
image_ids.extend(list(coco.getImgIds(catIds=[id])))
# Remove duplicates
image_ids = list(set(image_ids))
else:
# All images
image_ids = list(coco.imgs.keys())
# Add classes
for i in class_ids:
self.add_class("coco", i, coco.loadCats(i)[0]["name"])
# Add images
for i in image_ids:
self.add_image("coco",
image_id=i,
path=os.path.join(image_dir,
coco.imgs[i]['file_name']),
width=coco.imgs[i]["width"],
height=coco.imgs[i]["height"],
annotations=coco.loadAnns(
coco.getAnnIds(imgIds=[i],
catIds=class_ids,
iscrowd=None)))
if return_coco:
return coco
from pycocotools import coco
import matplotlib.pyplot as plt
import skimage.io as io
import time
time1 = time.time()
annFile = '/media/zhuzhu/ec114170-f406-444f-bee7-a3dc0a86cfa2/dataset/coco/annotations/person_keypoints_val2017.json'
dataDir = '/media/zhuzhu/ec114170-f406-444f-bee7-a3dc0a86cfa2/dataset/coco/images/val2017'
saveDir = '/media/zhuzhu/ec114170-f406-444f-bee7-a3dc0a86cfa2/coco_ground/val2017'
coco = coco.COCO(annFile)
catIds = coco.getCatIds(catNms=['person'])
imgIds = coco.getImgIds(catIds=catIds)
for idx in imgIds:
img = coco.loadImgs(ids=idx)[0]
annIds = coco.getAnnIds(imgIds=idx, catIds=catIds)
anns = coco.loadAnns(ids=annIds)
plt.figure(idx)
I = io.imread('%s/%s' % (dataDir, img['file_name']))
plt.imshow(I)
plt.axis('off')
coco.showAnns(anns=anns)
plt.savefig('%s/%s' % (saveDir, img['file_name']))
plt.close()
time2 = time.time()
print('spent t = %.2f min' % ((time2 - time1) / 60))
]
num_classes = 3
_valid_ids = [3, 6, 8]
_classes = {
ind + 1: cat_id for ind, cat_id in enumerate(_valid_ids)
}
_to_order = {cat_id: ind for ind, cat_id in enumerate(_valid_ids)}
coco = coco.COCO(ANN_PATH)
CAT_NAMES = [coco.loadCats([_classes[i + 1]])[0]['name'] \
for i in range(num_classes)]
COLORS = [((np.random.random((3, )) * 0.6 + 0.4)*255).astype(np.uint8) \
for _ in range(num_classes)]
# self.images = self.coco.getImgIds()
catIds = coco.getCatIds(catNms=['car','bus','truck'])
img_ids = coco.getImgIds(catIds=catIds)
num_samples = len(img_ids)
print(num_samples)
save_dir='/kaggle/working/cnn/exp/ctdet/coco_dla_test/'
dets =coco.loadRes('{}/results.json'.format(save_dir))
imgs=[]
for i, img_id in enumerate(img_ids):
print(img_id)
img_info = coco.loadImgs(ids=[img_id])[0]
img_path = IMG_PATH + img_info['file_name']
img = cv2.imread(img_path)
gt_ids = coco.getAnnIds(imgIds=[img_id],catIds=catIds)
gts = coco.loadAnns(gt_ids)
gt_img = img.copy()
pred_img = img.copy()