def detect_instance(score_map, mask, class_id, max_fragment_size=0):
# converting pixel-wise instance ids into detection form
pred_score = []
pred_label = []
pred_mask = []
for ag_score, ag_mask, ag_class in zip(score_map, mask, class_id):
if np.sum(ag_mask) < 1:
continue
segments = pyutils.to_one_hot(
measure.label(ag_mask, connectivity=1, background=0))[1:]
# connected components analysis
for seg_mask in segments:
if np.sum(seg_mask) < max_fragment_size:
pred_score.append(0)
else:
pred_score.append(np.max(ag_score * seg_mask))
pred_label.append(ag_class)
pred_mask.append(seg_mask)
return {
'score': np.stack(pred_score, 0),
'mask': np.stack(pred_mask, 0),
'class': np.stack(pred_label, 0)
}
def cluster_centroids(centroids, displacement, thres=2.5):
# thres: threshold for grouping centroid (see supp)
dp_strength = np.sqrt(displacement[1]**2 + displacement[0]**2)
height, width = dp_strength.shape
weak_dp_region = dp_strength < thres
dp_label = measure.label(weak_dp_region, connectivity=1, background=0)
dp_label_1d = dp_label.reshape(-1)
centroids_1d = centroids[0] * width + centroids[1]
clusters_1d = dp_label_1d[centroids_1d]
cluster_map = imutils.compress_range(
clusters_1d.reshape(height, width) + 1)
return pyutils.to_one_hot(cluster_map)
def _work_gpu(process_id, model, dataset, args):
n_gpus = torch.cuda.device_count()
databin = dataset[process_id]
data_loader = DataLoader(databin,
shuffle=False,
num_workers=args.num_workers // n_gpus,
pin_memory=False)
with torch.no_grad(), cuda.device(process_id):
model.cuda()
for iter, pack in tqdm(enumerate(data_loader), total=len(databin)):
img_name = pack['name'][0]
path = os.path.join(args.ins_seg_out_dir, img_name + '.npy')
if not os.path.exists(path):
os.makedirs(os.path.dirname(path), exist_ok=True)
size = np.asarray(pack['size'])
edge, dp = model(pack['img'][0].cuda(non_blocking=True))
dp = dp.cpu().numpy()
cam_dict = np.load(args.cam_out_dir + '/' + img_name + '.npy',
allow_pickle=True).item()
cams = cam_dict['cam'].cuda()
keys = cam_dict['keys']
centroids = find_centroids_with_refinement(dp)
instance_map = cluster_centroids(centroids, dp)
instance_cam = separte_score_by_mask(cams, instance_map)
rw = indexing.propagate_to_edge(instance_cam,
edge,
beta=args.beta,
exp_times=args.exp_times,
radius=5)
rw_up = F.interpolate(
rw, scale_factor=4, mode='bilinear',
align_corners=False)[:, 0, :size[0], :size[1]]
rw_up = rw_up / torch.max(rw_up)
rw_up_bg = F.pad(rw_up, (0, 0, 0, 0, 1, 0),
value=args.ins_seg_bg_thres)
num_classes = len(keys)
num_instances = instance_map.shape[0]
instance_shape = torch.argmax(rw_up_bg, 0).cpu().numpy()
instance_shape = pyutils.to_one_hot(
instance_shape,
maximum_val=num_instances * num_classes + 1)[1:]
instance_class_id = np.repeat(keys, num_instances)
detected = detect_instance(rw_up.cpu().numpy(),
instance_shape,
instance_class_id,
max_fragment_size=size[0] *
size[1] * 0.01)
np.save(path, detected)
if process_id == n_gpus - 1 and iter % (len(databin) //
4) == 0:
print("%d " % ((5 * iter + 1) // (len(databin) // 4)),
end='')