/home/chaeyun/.conda/envs/cris/lib/python3.9/site-packages/timm/models/layers/__init__.py:48: FutureWarning: Importing from timm.models.layers is deprecated, please import via timm.layers
warnings.warn(f"Importing from {__name__} is deprecated, please import via timm.layers", FutureWarning)
/home/chaeyun/.conda/envs/cris/lib/python3.9/site-packages/torch/functional.py:478: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:2894.)
return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined]
Image size: 480
loading dataset refcocog into memory...
creating index...
index created.
DONE (t=6.91s)
lavt_one
Window size 12!
Randomly initialize Multi-modal Swin Transformer weights.
/home/chaeyun/.conda/envs/cris/lib/python3.9/site-packages/torchvision/transforms/functional.py:417: UserWarning: Argument 'interpolation' of type int is deprecated since 0.13 and will be removed in 0.15. Please use InterpolationMode enum.
warnings.warn(
/home/chaeyun/.conda/envs/cris/lib/python3.9/site-packages/torchvision/transforms/functional.py:417: UserWarning: Argument 'interpolation' of type int is deprecated since 0.13 and will be removed in 0.15. Please use InterpolationMode enum.
warnings.warn(
/home/chaeyun/.conda/envs/cris/lib/python3.9/site-packages/torchvision/transforms/functional.py:417: UserWarning: Argument 'interpolation' of type int is deprecated since 0.13 and will be removed in 0.15. Please use InterpolationMode enum.
warnings.warn(
/home/chaeyun/.conda/envs/cris/lib/python3.9/site-packages/torchvision/transforms/functional.py:417: UserWarning: Argument 'interpolation' of type int is deprecated since 0.13 and will be removed in 0.15. Please use InterpolationMode enum.
warnings.warn(
Test: [ 0/5023] eta: 1 day, 11:23:15 time: 25.3624 data: 1.4797 max mem: 1021
Test: [ 100/5023] eta: 0:33:48 time: 0.1684 data: 0.0016 max mem: 1021
Test: [ 200/5023] eta: 0:23:03 time: 0.1592 data: 0.0017 max mem: 1021
Test: [ 300/5023] eta: 0:19:25 time: 0.1644 data: 0.0016 max mem: 1021
Test: [ 400/5023] eta: 0:17:22 time: 0.1612 data: 0.0017 max mem: 1021
Test: [ 500/5023] eta: 0:16:03 time: 0.1652 data: 0.0018 max mem: 1021
Test: [ 600/5023] eta: 0:15:05 time: 0.1696 data: 0.0017 max mem: 1021
Test: [ 700/5023] eta: 0:14:20 time: 0.1571 data: 0.0017 max mem: 1021
Test: [ 800/5023] eta: 0:13:43 time: 0.1656 data: 0.0016 max mem: 1021
Test: [ 900/5023] eta: 0:13:10 time: 0.1706 data: 0.0065 max mem: 1021
Test: [1000/5023] eta: 0:12:43 time: 0.1676 data: 0.0018 max mem: 1021
Test: [1100/5023] eta: 0:12:15 time: 0.1624 data: 0.0018 max mem: 1021
Test: [1200/5023] eta: 0:11:49 time: 0.1668 data: 0.0016 max mem: 1021
Test: [1300/5023] eta: 0:11:25 time: 0.1618 data: 0.0016 max mem: 1021
Test: [1400/5023] eta: 0:11:01 time: 0.1540 data: 0.0017 max mem: 1021
Test: [1500/5023] eta: 0:10:38 time: 0.1667 data: 0.0017 max mem: 1021
Test: [1600/5023] eta: 0:10:16 time: 0.1638 data: 0.0017 max mem: 1021
Test: [1700/5023] eta: 0:09:55 time: 0.1625 data: 0.0017 max mem: 1021
Test: [1800/5023] eta: 0:09:35 time: 0.1670 data: 0.0017 max mem: 1021
Test: [1900/5023] eta: 0:09:15 time: 0.1800 data: 0.0148 max mem: 1021
Test: [2000/5023] eta: 0:08:55 time: 0.1717 data: 0.0017 max mem: 1021
Test: [2100/5023] eta: 0:08:35 time: 0.1545 data: 0.0017 max mem: 1021
Test: [2200/5023] eta: 0:08:16 time: 0.1496 data: 0.0017 max mem: 1021
Test: [2300/5023] eta: 0:07:57 time: 0.1710 data: 0.0018 max mem: 1021
Test: [2400/5023] eta: 0:07:38 time: 0.1629 data: 0.0017 max mem: 1021
Test: [2500/5023] eta: 0:07:20 time: 0.1680 data: 0.0017 max mem: 1021
Test: [2600/5023] eta: 0:07:02 time: 0.1635 data: 0.0017 max mem: 1021
Test: [2700/5023] eta: 0:06:43 time: 0.1665 data: 0.0018 max mem: 1021
Test: [2800/5023] eta: 0:06:25 time: 0.1665 data: 0.0017 max mem: 1021
Test: [2900/5023] eta: 0:06:07 time: 0.1705 data: 0.0017 max mem: 1021
Test: [3000/5023] eta: 0:05:49 time: 0.1665 data: 0.0016 max mem: 1021
Test: [3100/5023] eta: 0:05:32 time: 0.1715 data: 0.0016 max mem: 1021
Test: [3200/5023] eta: 0:05:15 time: 0.1609 data: 0.0017 max mem: 1021
Test: [3300/5023] eta: 0:04:57 time: 0.1610 data: 0.0017 max mem: 1021
Test: [3400/5023] eta: 0:04:39 time: 0.1459 data: 0.0017 max mem: 1021
Test: [3500/5023] eta: 0:04:21 time: 0.1573 data: 0.0016 max mem: 1021
Test: [3600/5023] eta: 0:04:04 time: 0.1657 data: 0.0018 max mem: 1021
Test: [3700/5023] eta: 0:03:46 time: 0.1691 data: 0.0045 max mem: 1021
Test: [3800/5023] eta: 0:03:29 time: 0.1700 data: 0.0017 max mem: 1021
Test: [3900/5023] eta: 0:03:12 time: 0.1571 data: 0.0016 max mem: 1021
Test: [4000/5023] eta: 0:02:54 time: 0.1535 data: 0.0017 max mem: 1021
Test: [4100/5023] eta: 0:02:37 time: 0.1576 data: 0.0018 max mem: 1021
Test: [4200/5023] eta: 0:02:19 time: 0.1623 data: 0.0017 max mem: 1021
Test: [4300/5023] eta: 0:02:02 time: 0.1656 data: 0.0017 max mem: 1021
Test: [4400/5023] eta: 0:01:45 time: 0.1578 data: 0.0017 max mem: 1021
Test: [4500/5023] eta: 0:01:28 time: 0.1532 data: 0.0016 max mem: 1021
Test: [4600/5023] eta: 0:01:11 time: 0.1494 data: 0.0017 max mem: 1021
Test: [4700/5023] eta: 0:00:54 time: 0.1659 data: 0.0017 max mem: 1021
Test: [4800/5023] eta: 0:00:37 time: 0.1613 data: 0.0016 max mem: 1021
Test: [4900/5023] eta: 0:00:20 time: 0.1614 data: 0.0017 max mem: 1021
Test: [5000/5023] eta: 0:00:03 time: 0.1661 data: 0.0016 max mem: 1021
Test: Total time: 0:14:08
Final results:
Mean IoU is 65.28
precision@0.5 = 73.84
precision@0.6 = 69.06
precision@0.7 = 62.71
precision@0.8 = 51.72
precision@0.9 = 26.82
overall IoU = 63.68