def test(test_model, logger):
eval_gt = COCO(cfg.gt_path)
import json
with open(cfg.det_path, 'r') as f:
dets = json.load(f)
test_subset = False
if test_subset:
eval_gt.imgs = dict(list(eval_gt.imgs.items())[:100])
anns = dict()
for i in eval_gt.imgs:
for j in eval_gt.getAnnIds(i):
anns[j] = eval_gt.anns[j]
eval_gt.anns = anns
dets = [i for i in dets if i['image_id'] in eval_gt.imgs]
dets = [i for i in dets if i['category_id'] == 1]
dets.sort(key=lambda x: (x['image_id'], x['score']), reverse=True)
for i in dets:
i['imgpath'] = '/home/dx/data/coco/val2014/COCO_val2014_000000%06d.jpg' % i['image_id']
img_num = len(np.unique([i['image_id'] for i in dets]))
use_gtboxes = False
if use_gtboxes:
d = COCOJoints()
coco_train_data, coco_test_data = d.load_data()
coco_test_data.sort(key=lambda x: x['imgid'])
for i in coco_test_data:
i['image_id'] = i['imgid']
i['score'] = 1.
dets = coco_test_data
from tfflat.mp_utils import MultiProc
img_start = 0
ranges = [0]
images_per_gpu = int(img_num / len(args.gpu_ids.split(','))) + 1
for run_img in range(img_num):
img_end = img_start + 1
while img_end < len(dets) and dets[img_end]['image_id'] == dets[img_start]['image_id']:
img_end += 1
if (run_img + 1) % images_per_gpu == 0 or (run_img + 1) == img_num:
ranges.append(img_end)
img_start = img_end
def func(id):
cfg.set_args(args.gpu_ids.split(',')[id])
tester = Tester(Network(), cfg)
tester.load_weights(test_model)
range = [ranges[id], ranges[id + 1]]
return test_net(tester, logger, dets, range)
MultiGPUFunc = MultiProc(len(args.gpu_ids.split(',')), func)
all_res, dump_results = MultiGPUFunc.work()
# evaluation
result_path = osp.join(cfg.output_dir, 'results.json')
with open(result_path, 'w') as f:
json.dump(dump_results, f)
eval_dt = eval_gt.loadRes(result_path)
cocoEval = COCOeval(eval_gt, eval_dt, iouType='keypoints')
cocoEval.evaluate()
cocoEval.accumulate()
cocoEval.summarize()
def _init_coco(self):
coco = COCO()
# self.anns, self.cats, self.imgs self.dataset, self.imgToAnns, self.catToImgs
# generate each member respectively
det_anno_list = OrderedDict()
images = OrderedDict()
img2anns = OrderedDict()
cat2imgs = defaultdict(list)
for each_anno in self.vg_annotations:
img_id = each_anno['id']
images[img_id] = {
'file_name': each_anno['path'],
'height': each_anno['height'],
'width': each_anno['width'],
'id': img_id
}
# each image contains many annotation
# add sub id in single image
obj_list = []
for each_object in each_anno['objects']:
xywh = xyxy2xywh(each_object['box'])
obj_list.append({
'category_id':
self.obj_cls_ind_q[each_object['class']],
'bbox':
xywh,
'image_id':
img_id,
'area':
xywh[2] * xywh[3],
'iscrowd':
0,
'segmentation': [],
'id':
-1 # left for last step accumulate
})
# accumulate the sub_id to overall id
last_seg_idx = len(det_anno_list.keys())
for indx, each in enumerate(obj_list):
anno_id = last_seg_idx + indx
obj_list[indx]['id'] = anno_id
det_anno_list[anno_id] = each
cat2imgs[each['category_id']].append(img_id)
img2anns[img_id] = obj_list
coco.anns = det_anno_list
coco.imgs = images
coco.imgToAnns = img2anns
coco.catToImgs = cat2imgs
# cats
cats = OrderedDict()
for id_, each_cat in enumerate(self.obj_cls_list):
if id_ == 0:
continue
cats[id_] = {
'id': id_,
'name': each_cat,
}
coco.cats = cats
# other info
coco.dataset['licenses'] = ''
coco.dataset['annotations'] = list(coco.anns.values())
coco.dataset['info'] = {}
coco.dataset['images'] = list(coco.imgs.values())
coco.dataset['categories'] = list(coco.cats.values())
self.coco = coco
self.ids = list(self.coco.imgs.keys())
