def update_metrics(self, pred_color, semseg_gt, timetic):
self.time_meter.update(timetic)
# calculate accuracy
acc, pix = accuracy(pred_color, semseg_gt)
intersection, union = intersectionAndUnion(pred_color, semseg_gt, 150) # 150 nb of class in dataset
self.acc_meter.update(acc, pix)
self.intersection_meter.update(intersection)
self.union_meter.update(union)
def get_eval_res(pred, anno):
acc_meter = AverageMeter()
intersection_meter = AverageMeter()
union_meter = AverageMeter()
acc, pix = accuracy(pred, anno)
intersection, union = intersectionAndUnion(pred, anno, 150)
acc_meter.update(acc, pix)
intersection_meter.update(intersection)
union_meter.update(union)
class_ious = {}
iou = intersection_meter.sum / (union_meter.sum + 1e-10)
for i, _iou in enumerate(iou):
class_ious[i] = _iou
return iou.mean(), acc_meter.average(), class_ious
def evaluate(segmentation_module, loader, cfg, gpu_id, result_queue):
segmentation_module.eval()
for index, batch_data in enumerate(loader):
# process data
batch_data = batch_data[0]
seg_label = as_numpy(batch_data['seg_label'][0])
img_resized_list = batch_data['img_data']
with torch.no_grad():
segSize = (seg_label.shape[0], seg_label.shape[1])
scores = torch.zeros(1, cfg.DATASET.num_class, segSize[0],
segSize[1])
scores = async_copy_to(scores, gpu_id)
for img in img_resized_list:
feed_dict = batch_data.copy()
feed_dict['img_data'] = img
del feed_dict['img_ori']
del feed_dict['info']
feed_dict = async_copy_to(feed_dict, gpu_id)
# forward pass
scores_tmp = segmentation_module(feed_dict, segSize=segSize)
scores = scores + scores_tmp / len(cfg.DATASET.imgSizes)
_, pred = torch.max(scores, dim=1)
pred = as_numpy(pred.squeeze(0).cpu())
# calculate accuracy and SEND THEM TO MASTER
acc, pix = accuracy(pred, seg_label)
intersection, union = intersectionAndUnion(pred, seg_label,
cfg.DATASET.num_class)
result_queue.put_nowait((acc, pix, intersection, union))
# visualization
if cfg.VAL.visualize:
visualize_result(
(batch_data['img_ori'], seg_label, batch_data['info']), pred,
os.path.join(cfg.DIR, 'result'))
def evaluate(segmentation_module, loader, cfg, gpu):
acc_meter = AverageMeter()
intersection_meter = AverageMeter()
union_meter = AverageMeter()
time_meter = AverageMeter()
segmentation_module.eval()
pbar = tqdm(total=len(loader))
for batch_data in loader:
# process data
batch_data = batch_data[0]
seg_label = as_numpy(batch_data['seg_label'][0])
img_resized_list = batch_data['img_data']
torch.cuda.synchronize()
tic = time.perf_counter()
with torch.no_grad():
segSize = (seg_label.shape[0], seg_label.shape[1])
scores = torch.zeros(1, cfg.DATASET.num_class, segSize[0], segSize[1])
scores = async_copy_to(scores, gpu)
for img in img_resized_list:
feed_dict = batch_data.copy()
feed_dict['img_data'] = img
del feed_dict['img_ori']
del feed_dict['info']
feed_dict = async_copy_to(feed_dict, gpu)
# forward pass
scores_tmp = segmentation_module(feed_dict, segSize=segSize)
scores = scores + scores_tmp / len(cfg.DATASET.imgSizes)
_, pred = torch.max(scores, dim=1)
pred = as_numpy(pred.squeeze(0).cpu())
torch.cuda.synchronize()
time_meter.update(time.perf_counter() - tic)
# calculate accuracy
acc, pix = accuracy(pred, seg_label)
intersection, union = intersectionAndUnion(pred, seg_label, cfg.DATASET.num_class)
acc_meter.update(acc, pix)
intersection_meter.update(intersection)
union_meter.update(union)
# visualization
if cfg.VAL.visualize:
visualize_result(
(batch_data['img_ori'], seg_label, batch_data['info']),
pred,
os.path.join(cfg.DIR, 'result')
)
pbar.update(1)
# summary
iou = intersection_meter.sum / (union_meter.sum + 1e-10)
for i, _iou in enumerate(iou):
print('class [{}], IoU: {:.4f}'.format(i, _iou))
print('[Eval Summary]:')
print('Mean IoU: {:.4f}, Accuracy: {:.2f}%, Inference Time: {:.4f}s'
.format(iou.mean(), acc_meter.average()*100, time_meter.average()))