def main():
dets = []
# Get img_ids from lvis, instead.
img_ids = coco.getImgIds()
num_images = len(img_ids)
# import pdb; pdb.set_trace()
prog_bar = mmcv.ProgressBar(len(img_ids))
for i, img_id in enumerate(img_ids):
# ipdb.set_trace()
if DEBUG_ is True:
if i > 100: break
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])
gts = coco.loadAnns(gt_ids)
gt_img = img.copy()
for j, pred in enumerate(gts):
bbox = _coco_box_to_bbox(pred['bbox'])
cat_id = pred['category_id']
gt_img = add_box(gt_img, bbox, 1.00, cat_id)
img_name = '{}_gt.jpg'.format(str(img_id).zfill(12))
cv2.imwrite(os.path.join(OUT_PATH, img_name), gt_img)
prog_bar.update()
def show_json_angle():
"""
according json file to visualization
:return:
"""
img_path = '/Dataset/DOTA_TEST/images/'
json_path = '/Dataset/DOTA_TEST/DOTA_DOTA_TEST_angle.json'
save_path = '/Dataset/DOTA_TEST/show/'
import pycocotools.coco as coco
coco = coco.COCO(json_path)
images = coco.getImgIds()
image_num = len(os.listdir(img_path))
for idx in range(image_num):
img_id = images[idx]
file_name = coco.loadImgs(ids=[img_id])[0]['file_name']
pics_path = os.path.join(img_path, file_name)
ann_ids = coco.getAnnIds(imgIds=[img_id])
anns = coco.loadAnns(ids=ann_ids)
num_objs = len(anns)
img = cv2.imread(pics_path)
for k in range(num_objs):
bbox = np.array(anns[k]['bbox'])
# print((bbox[0], bbox[1]), (bbox[2], bbox[3]), bbox[4]/math.pi*180)
bbox8 = cv2.boxPoints(((bbox[0], bbox[1]), (bbox[2], bbox[3]), bbox[4] / math.pi * 180))
# cat = cate[count]
img = add_bbox(img, bbox8, anns[k]['category_id'])
cv2.imwrite(save_path + file_name, img)
print('\r{}/{}'.format(idx, image_num), end='')
def main():
print("\nDATA:{}\nOUT_TYPE:{}\n".format(DATA, OUT_TYPE))
dets = []
img_ids = coco.getImgIds()
num_images = len(img_ids)
# ipdb.set_trace()
for i, img_id in enumerate(img_ids):
if i % 10 == 0: print("{}/{}".format(i, len(img_ids)), end="\r")
# ipdb.set_trace()
if DEBUG_ and i > DEBUG_: break
img_info = coco.loadImgs(ids=[img_id])[0]
if DATA == "lvis":
img_name = img_info['file_name']
elif DATA == "coco":
img_name = "COCO_val2014_" + img_info['file_name']
img_path = IMG_PATH + img_name
img = cv2.imread(img_path)
gt_ids = coco.getAnnIds(imgIds=[img_id])
gts = coco.loadAnns(gt_ids)
gt_img = img.copy()
for j, pred in enumerate(gts):
bbox = _coco_box_to_bbox(pred['bbox'])
gt_img = add_box(gt_img, bbox, 1.00)
img_name = '{}_{}.jpg'.format(str(img_id).zfill(12), OUT_NAME_SUFFIX)
cv2.imwrite(os.path.join(OUT_PATH, img_name), gt_img)
def get_coco_dicts(data_dir):
if 'train' in data_dir:
file_path = '/media/tangyp/Data/coco/train2014'
elif 'val' in data_dir:
file_path = '/media/tangyp/Data/coco/val2014'
json_file = data_dir
coco = COCO(json_file)
catIds = coco.getCatIds(catNms=['person'])
imgIds = coco.getImgIds(catIds=catIds)
imgs = coco.loadImgs(imgIds)
dataset_dicts = []
for img in imgs:
dataset_dict = {}
new_img = {'file_name': os.path.join(file_path, img['file_name']), 'height': img['height'],
'width': img['width'],
'image_id': img['id']}
annId = coco.getAnnIds(imgIds=img['id'])
anns = coco.loadAnns(ids=annId)
annotation = {}
annotation['annotations'] = []
for ann in anns:
new_ann = {'iscrowd': ann['iscrowd'], 'bbox': ann['bbox'], 'category_id': ann['category_id'],
'segmentation': ann['segmentation'], 'bbox_mode': BoxMode(1)}
annotation['annotations'].append(new_ann)
dataset_dict.update(new_img)
dataset_dict.update(annotation)
dataset_dicts.append(dataset_dict)
return dataset_dicts
def main():
img_seq = []
# Get img_ids from lvis, instead.
img_ids = coco.getImgIds()
num_images = len(img_ids)
# import ipdb; ipdb.set_trace()
dets = []
dets.append(coco.loadRes(PRE_PATH))
prog_bar = mmcv.ProgressBar(len(img_ids))
for i, img_id in enumerate(img_ids):
# ipdb.set_trace()
if DEBUG_ is True:
if i == DEBUG_FRAMES: break
img_info = coco.loadImgs(ids=[img_id])[0]
img_path = IMG_PATH + img_info['file_name']
img = cv2.imread(img_path)
# Create a gt labeled img.
gt_ids = coco.getAnnIds(imgIds=[img_id])
gts = coco.loadAnns(gt_ids)
gt_img = img
for j, pred in enumerate(gts):
bbox = _coco_box_to_bbox(pred['bbox'])
cat_id = pred['category_id']
gt_img = add_box(gt_img, bbox, 1.00, cat_id)
gt_img = add_to_canvas(gt_img)
# Create a predictions labeled img.
for k in range(len(dets)):
pred_ids = dets[k].getAnnIds(imgIds=[img_id])
preds = dets[k].loadAnns(pred_ids)
pred_img = img.copy()
for j, pred in enumerate(preds):
bbox = _coco_box_to_bbox(pred['bbox'])
sc = pred['score']
cat_id = pred['category_id']
if sc > VIS_THR:
pred_img = add_box(pred_img, bbox, sc, cat_id)
# ipdb.set_trace()
pred_img = add_to_canvas(pred_img)
# Create a super image and save it.
sup_img = np.concatenate((gt_img, pred_img), axis=1)
sup_img_name = 'pre_{}.jpg'.format(str(img_id).zfill(12))
cv2.imwrite(os.path.join(OUT_PATH, sup_img_name), sup_img)
img_seq.append(sup_img)
prog_bar.update()
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 load_ss_data(coco_dir, data_name, cache_dir, input_size=None):
"""セマンティックセグメンテーションのデータの読み込み。"""
from pycocotools import coco, mask as cocomask
coco_dir = pathlib.Path(coco_dir)
cache_dir = pathlib.Path(cache_dir)
if isinstance(input_size, int):
input_size = (input_size, input_size)
coco = coco.COCO(
str(coco_dir / "annotations" / f"instances_{data_name}.json"))
class_names = [c["name"] for c in coco.loadCats(coco.getCatIds())]
jsonclassid_to_index = {
c["id"]: class_names.index(c["name"])
for c in coco.loadCats(coco.getCatIds())
}
X, y = [], []
for entry in utils.tqdm(coco.loadImgs(coco.getImgIds()),
desc="load_ss_data"):
dirname, filename = entry["coco_url"].split("/")[-2:]
save_path = cache_dir / dirname / (filename + ".npy")
X.append(coco_dir / dirname / filename)
y.append(save_path)
if not save_path.exists():
# 読み込み
objs = coco.loadAnns(
coco.getAnnIds(imgIds=entry["id"], iscrowd=None))
mask = np.zeros(
(entry["height"], entry["width"], len(class_names)),
dtype=np.uint8)
for obj in objs:
if obj.get("ignore", 0) == 1:
continue
rle = cocomask.frPyObjects(obj["segmentation"],
entry["height"], entry["width"])
m = cocomask.decode(rle)
class_id = jsonclassid_to_index[obj["category_id"]]
mask[:, :, class_id] |= m
mask = np.where(mask, np.uint8(255), np.uint8(0))
# リサイズ
if input_size is not None:
mask = ndimage.resize(mask, input_size[1], input_size[0])
# 保存
save_path.parent.mkdir(parents=True, exist_ok=True)
np.save(str(save_path), mask)
return np.array(X), np.array(y), class_names
def load_od_data(coco_dir, data_name, use_crowded):
"""物体検出のデータの読み込み。"""
import pycocotools.coco
coco_dir = pathlib.Path(coco_dir)
coco = pycocotools.coco.COCO(
str(coco_dir / "annotations" / f"instances_{data_name}.json"))
class_names = [c["name"] for c in coco.loadCats(coco.getCatIds())]
jsonclassid_to_index = {
c["id"]: class_names.index(c["name"])
for c in coco.loadCats(coco.getCatIds())
}
labels = []
for entry in coco.loadImgs(coco.getImgIds()):
dirname, filename = entry["coco_url"].split("/")[-2:]
objs = coco.loadAnns(
coco.getAnnIds(imgIds=entry["id"],
iscrowd=None if use_crowded else False))
bboxes, classes, areas, crowdeds = [], [], [], []
width, height = entry["width"], entry["height"]
for obj in objs:
if obj.get("ignore", 0) == 1:
continue
x, y, w, h = obj["bbox"]
bbox = np.array([x, y, x + w, y + h]) / np.array(
[width, height, width, height])
bbox = np.clip(bbox, 0, 1)
if (bbox[:2] < bbox[2:]).all():
bboxes.append(bbox)
classes.append(jsonclassid_to_index[obj["category_id"]])
areas.append(obj["area"])
crowdeds.append(obj["iscrowd"])
labels.append(
tk.od.ObjectsAnnotation(
path=coco_dir / dirname / filename,
width=width,
height=height,
classes=classes,
bboxes=bboxes,
areas=areas,
crowdeds=crowdeds,
))
return tk.od.ObjectsAnnotation.create_dataset(labels,
class_names=class_names)
def main():
img_seq = []
# Get img_ids from lvis, instead.
img_ids = coco.getImgIds()
num_images = len(img_ids)
# import pdb; pdb.set_trace()
prog_bar = mmcv.ProgressBar(len(img_ids))
for i, img_id in enumerate(img_ids):
print(i)
# ipdb.set_trace()
if DEBUG_ is True:
if i==DEBUG_FRAMES: break
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])
#gts = coco.loadAnns(gt_ids)
prop_img = img.copy()
img_props = props[i]
# img_props = img_props[img_props[:,-1]>VIS_THR, :4]
for j, prop in enumerate(img_props):
bbox = _coco_box_to_bbox(prop)
# bbox = np.asarray(prop, dtype=np.int32)
cat_id = 1
prop_img = add_box(prop_img, bbox, VIS_THR, cat_id)
# ipdb.set_trace()
img_name = 'prop_{}.jpg'.format(str(img_id).zfill(12))
prop_img = add_to_canvas(prop_img)
cv2.imwrite(os.path.join(OUT_PATH, img_name), prop_img)
img_seq.append(prop_img)
prog_bar.update()
make_video(img_seq, VID_NAME)
def main():
img_seq = []
# Get img_ids from lvis, instead.
img_ids = coco.getImgIds()
num_images = len(img_ids)
# import pdb; pdb.set_trace()
prog_bar = mmcv.ProgressBar(len(img_ids))
ipdb.set_trace()
if DEBUG_FOR_VIS:
img_ids = random.sample(img_ids, 600)
for i, img_id in enumerate(img_ids):
# ipdb.set_trace()
if DEBUG_ is True:
if i == DEBUG_FRAMES: break
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])
gts = coco.loadAnns(gt_ids)
gt_img = img.copy()
for j, pred in enumerate(gts):
bbox = _coco_box_to_bbox(pred['bbox'])
cat_id = pred['category_id']
gt_img = add_box(gt_img, bbox, 1.00, cat_id)
# ipdb.set_trace()
img_name = 'gt_{}.jpg'.format(str(img_id).zfill(12))
gt_img = add_to_canvas(gt_img)
cv2.imwrite(os.path.join(OUT_PATH, img_name), gt_img)
img_seq.append(gt_img)
prog_bar.update()
ipdb.set_trace()
make_video(img_seq, VID_NAME)
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
thickness=1)
else:
cv2.rectangle(image, (bbox[0], bbox[1] - cat_size[1] - 2),
(bbox[0] + cat_size[0], bbox[1] - 2), color, -1)
cv2.putText(image,
txt, (bbox[0], bbox[1] - 2),
cv2.FONT_HERSHEY_SIMPLEX,
0.5, (0, 0, 0),
thickness=1)
cv2.rectangle(image, (bbox[0], bbox[1]), (bbox[2], bbox[3]), color, 2)
return image
if __name__ == '__main__':
dets = []
img_ids = coco.getImgIds()
num_images = len(img_ids)
for k in range(1, len(sys.argv)):
pred_path = sys.argv[k]
dets.append(coco.loadRes(pred_path))
# import pdb; pdb.set_trace()
for i, img_id in enumerate(img_ids):
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])
gts = coco.loadAnns(gt_ids)
gt_img = img.copy()
for j, pred in enumerate(gts):
bbox = _coco_box_to_bbox(pred['bbox'])
cat_id = pred['category_id']
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())
print('#list/#set = %d' % len(tmpDictFoodImgIds.keys()))
numImages = len(setAllFoodImgIds)
for ii, kk in enumerate(setAllFoodImgIds):
print('[%d/%d]' % (ii, numImages))
timgInfo = coco.loadImgs(kk)[0]
foutImg = '%s/%s' % (dirOut, timgInfo['file_name'])
foutMsk = '%s/%s-mskfood.png' % (dirOut, timgInfo['file_name'])
foutPrv = '%s/%s-preview.jpg' % (dirOut, timgInfo['file_name'])
if os.path.isfile(foutPrv):
def eval(model_arch, model_path, img_dir, gt_annot_path):
output = "output"
if os.path.exists(output):
shutil.rmtree(output)
os.mkdir(output)
os.environ['CUDA_VISIBLE_DEVICES'] = "0"
if LoadImagesAndLabels.num_classes <= 5:
colors = [(55, 55, 250), (255, 155, 50), (128, 0, 0), (255, 0, 255),
(128, 255, 128), (255, 0, 0)]
else:
colors = [(v // 32 * 64 + 64, (v // 8) % 4 * 64, v % 8 * 32)
for v in range(1, LoadImagesAndLabels.num_classes + 1)][::-1]
detector = CtdetDetector(model_arch, model_path)
print('\n/****************** Eval ****************/\n')
import tqdm
import pycocotools.coco as coco
from pycocotools.cocoeval import COCOeval
print("gt path: {}".format(gt_annot_path))
result_file = '../evaluation/instances_det.json'
coco = coco.COCO(gt_annot_path)
images = coco.getImgIds()
num_samples = len(images)
print('find {} samples in {}'.format(num_samples, gt_annot_path))
#------------------------------------------------
coco_res = []
for index in tqdm.tqdm(range(num_samples)):
img_id = images[index]
file_name = coco.loadImgs(ids=[img_id])[0]['file_name']
image_path = os.path.join(img_dir, file_name)
img = cv2.imread(image_path)
results, hm = detector.work(img) # 返回检测结果和置信度图
class_num = {}
for res in results:
cls, conf, bbox = res[0], res[1], res[2]
coco_res.append({
'bbox':
[bbox[0], bbox[1], bbox[2] - bbox[0], bbox[3] - bbox[1]],
'category_id':
LoadImagesAndLabels.class_name.index(cls),
'image_id':
img_id,
'score':
conf
})
if cls in class_num:
class_num[cls] += 1
else:
class_num[cls] = 1
color = colors[LoadImagesAndLabels.class_name.index(cls)]
# 绘制标签&置信度
label_ = '{}:{:.1f}'.format(cls, conf)
plot_one_box(bbox,
img,
color=color,
label=label_,
line_thickness=2)
cv2.imwrite(output + "/" + os.path.basename(image_path), img)
cv2.namedWindow("heatmap", 0)
cv2.imshow("heatmap", np.hstack(hm[0].cpu().numpy()))
cv2.namedWindow("img", 0)
cv2.imshow("img", img)
key = cv2.waitKey(1)
#-------------------------------------------------
with open(result_file, 'w') as f_dump:
json.dump(coco_res, f_dump, cls=NpEncoder)
cocoDt = coco.loadRes(result_file)
cocoEval = COCOeval(coco, cocoDt, 'bbox')
# cocoEval.params.imgIds = imgIds
cocoEval.params.catIds = [1] # 1代表’Hand’类，你可以根据需要增减类别
cocoEval.evaluate()
print('\n/***************************/\n')
cocoEval.accumulate()
print('\n/***************************/\n')
cocoEval.summarize()
draw_pr(cocoEval)
MEAN = np.array([0.408, 0.447, 0.470]).astype(np.float32)
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,
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))
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
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
