When we execute the test code of REDS4，have some mistakes. about ftvsr HOT 9 CLOSED

could you provide the error logs and you running config/command?

from ftvsr.

There are the running command and error logs:
(FTVSR003) zqiang@server-03:~/FTVSR-main$ CUDA_VISIBLE_DEVICES=0 python ./tools/test.py configs/FTVSR_reds4.py model/FTVSR_REDS.pth --save-path Save_
Traceback (most recent call last):
File "./tools/test.py", line 229, in
main()
File "./tools/test.py", line 151, in main
model = build_model(cfg.model, train_cfg=None, test_cfg=cfg.test_cfg)
File "/share4/home/zqiang/FTVSRmmediting02/mmedit/models/builder.py", line 60, in build_model
return build(cfg, MODELS, dict(train_cfg=train_cfg, test_cfg=test_cfg))
File "/share4/home/zqiang/FTVSRmmediting02/mmedit/models/builder.py", line 22, in build
return build_from_cfg(cfg, registry, default_args)
File "/share4/home/zqiang/anaconda3/envs/FTVSR003/lib/python3.7/site-packages/mmcv/utils/registry.py", line 45, in build_from_cfg
f'{obj_type} is not in the {registry.name} registry')
KeyError: 'TTVSR is not in the model registry'

Thank you!!!

from ftvsr.

The config file is https://github.com/researchmm/FTVSR/blob/main/configs/FTVSR_reds4.py.

from ftvsr.

When we execute the test code of Vimeo90K, we also have got some mistakes, it's so confusing...

(FTVSR003) zqiang@server-04:~/FTVSR-main$ CUDA_VISIBLE_DEVICES=6 python ./tools/test.py configs/FTVSR_vimeo90k.py model/FTVSR_Vimeo90K.pth --save-path Save_
Traceback (most recent call last):
File "/share4/home/zqiang/anaconda3/envs/FTVSR003/lib/python3.7/site-packages/mmcv/utils/registry.py", line 52, in build_from_cfg
return obj_cls(**args)
TypeError: init() missing 1 required positional argument: 'ann_file'

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "./tools/test.py", line 229, in
main()
File "./tools/test.py", line 136, in main
dataset = build_dataset(cfg.data.test)
File "/share4/home/zqiang/FTVSRmmediting02/mmedit/datasets/builder.py", line 78, in build_dataset
dataset = build_from_cfg(cfg, DATASETS, default_args)
File "/share4/home/zqiang/anaconda3/envs/FTVSR003/lib/python3.7/site-packages/mmcv/utils/registry.py", line 55, in build_from_cfg
raise type(e)(f'{obj_cls.name}: {e}')
TypeError: SRVid4Dataset: init() missing 1 required positional argument: 'ann_file'

We really need the correct version for achieving the FTVSR successfully！ Thank you very much!!!

from ftvsr.

When we execute the test code of Vimeo90K with multi GPU, we also have got some other mistakes.
This reason may be the dataset setting of 'calendar_0_0', 'calendar_0_1','calendar_1_0','calendar_1_1'. We don't know why to change the test datasets to '_0_0' format. It's so confusing....

==================================================================================
(FTVSR003) zqiang@server-04:~/FTVSR-main$ CUDA_VISIBLE_DEVICES=6,7 ./tools/dist_test.sh configs/FTVSR_vimeo90k.py model/FTVSR_Vimeo90K.pth 2 --save-path Save_
/share4/home/zqiang/anaconda3/envs/FTVSR003/lib/python3.7/site-packages/torch/distributed/launch.py:186: FutureWarning: The module torch.distributed.launch is deprecated
and will be removed in future. Use torchrun.
Note that --use_env is set by default in torchrun.
If your script expects --local_rank argument to be set, please
change it to read from os.environ['LOCAL_RANK'] instead. See
https://pytorch.org/docs/stable/distributed.html#launch-utility for
further instructions

FutureWarning,
WARNING:torch.distributed.run:

Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed.

2022-09-10 04:40:58,017 - mmedit - INFO - Use load_from_http loader

Use load_from_local loader
Use load_from_local loader
[ ] 0/16, elapsed: 0s, ETA:/share4/home/zqiang/anaconda3/envs/FTVSR003/lib/python3.7/site-packages/torch/functional.py:568: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at /opt/conda/conda-bld/pytorch_1646755953518/work/aten/src/ATen/native/TensorShape.cpp:2228.)
return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined]
/share4/home/zqiang/anaconda3/envs/FTVSR003/lib/python3.7/site-packages/torch/functional.py:568: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at /opt/conda/conda-bld/pytorch_1646755953518/work/aten/src/ATen/native/TensorShape.cpp:2228.)
return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined]
[>>>>>>>>>>>>>>>>>> ] 6/16, 0.0 task/s, elapsed: 348s, ETA: 580sTraceback (most recent call last):
File "./tools/test.py", line 229, in
main()
File "./tools/test.py", line 191, in main
empty_cache=empty_cache)
File "/share4/home/zqiang/FTVSR-main/mmedit/apis/test.py", line 108, in multi_gpu_test
**data)
File "/share4/home/zqiang/anaconda3/envs/FTVSR003/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl
return forward_call(*input, **kwargs)
File "/share4/home/zqiang/FTVSR-main/mmedit/core/distributed_wrapper.py", line 113, in forward
return self.module(*inputs[0], **kwargs[0])
File "/share4/home/zqiang/anaconda3/envs/FTVSR003/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl
return forward_call(*input, **kwargs)
File "/share4/home/zqiang/anaconda3/envs/FTVSR003/lib/python3.7/site-packages/mmcv/runner/fp16_utils.py", line 98, in new_func
return old_func(*args, **kwargs)
File "/share4/home/zqiang/FTVSR-main/mmedit/models/restorers/basic_restorer.py", line 74, in forward
return self.forward_test(lq, gt, qp, **kwargs)
File "/share4/home/zqiang/FTVSR-main/mmedit/models/restorers/ttvsr.py", line 179, in forward_test
output = self.generator(lq)
File "/share4/home/zqiang/anaconda3/envs/FTVSR003/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl
return forward_call(*input, **kwargs)
File "/share4/home/zqiang/anaconda3/envs/FTVSR003/lib/python3.7/site-packages/torch/nn/parallel/distributed.py", line 963, in forward
output = self.module(*inputs[0], **kwargs[0])
File "/share4/home/zqiang/anaconda3/envs/FTVSR003/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl
return forward_call(*input, **kwargs)
File "/share4/home/zqiang/FTVSR-main/mmedit/models/backbones/sr_backbones/ftvsr.py", line 132, in forward
'The height and width of inputs should be at least 64, '
AssertionError: The height and width of inputs should be at least 64, but got 60 and 88.
[>>>>>>>>>>>>>>>>>>>>>>>>> ] 8/16, 0.0 task/s, elapsed: 414s, ETA: 414sTraceback (most recent call last):
File "./tools/test.py", line 229, in
main()
File "./tools/test.py", line 191, in main
empty_cache=empty_cache)
File "/share4/home/zqiang/FTVSR-main/mmedit/apis/test.py", line 108, in multi_gpu_test
**data)
File "/share4/home/zqiang/anaconda3/envs/FTVSR003/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl
return forward_call(*input, **kwargs)
File "/share4/home/zqiang/FTVSR-main/mmedit/core/distributed_wrapper.py", line 113, in forward
return self.module(*inputs[0], **kwargs[0])
File "/share4/home/zqiang/anaconda3/envs/FTVSR003/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl
return forward_call(*input, **kwargs)
File "/share4/home/zqiang/anaconda3/envs/FTVSR003/lib/python3.7/site-packages/mmcv/runner/fp16_utils.py", line 98, in new_func
return old_func(*args, **kwargs)
File "/share4/home/zqiang/FTVSR-main/mmedit/models/restorers/basic_restorer.py", line 74, in forward
return self.forward_test(lq, gt, qp, **kwargs)
File "/share4/home/zqiang/FTVSR-main/mmedit/models/restorers/ttvsr.py", line 179, in forward_test
output = self.generator(lq)
File "/share4/home/zqiang/anaconda3/envs/FTVSR003/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl
return forward_call(*input, **kwargs)
File "/share4/home/zqiang/anaconda3/envs/FTVSR003/lib/python3.7/site-packages/torch/nn/parallel/distributed.py", line 963, in forward
output = self.module(*inputs[0], **kwargs[0])
File "/share4/home/zqiang/anaconda3/envs/FTVSR003/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl
return forward_call(*input, **kwargs)
File "/share4/home/zqiang/FTVSR-main/mmedit/models/backbones/sr_backbones/ftvsr.py", line 132, in forward
'The height and width of inputs should be at least 64, '
AssertionError: The height and width of inputs should be at least 64, but got 60 and 88.

from ftvsr.

We have another question:
training the FTVSR needing GPU requirement, how many GPU numbers and GPU memory can be trained successfully?

from ftvsr.

dataset = build_from_cfg(cfg, DATASETS, default_args)

The code works fine on our machine. Maybe there are some environmental problems?

from ftvsr.

When we execute the test code of Vimeo90K with multi GPU, we also have got some other mistakes. This reason may be the dataset setting of 'calendar_0_0', 'calendar_0_1','calendar_1_0','calendar_1_1'. We don't know why to change the test datasets to '_0_0' format. It's so confusing....

================================================================================== (FTVSR003) zqiang@server-04:~/FTVSR-main$ CUDA_VISIBLE_DEVICES=6,7 ./tools/dist_test.sh configs/FTVSR_vimeo90k.py model/FTVSR_Vimeo90K.pth 2 --save-path Save_ /share4/home/zqiang/anaconda3/envs/FTVSR003/lib/python3.7/site-packages/torch/distributed/launch.py:186: FutureWarning: The module torch.distributed.launch is deprecated and will be removed in future. Use torchrun. Note that --use_env is set by default in torchrun. If your script expects --local_rank argument to be set, please change it to read from os.environ['LOCAL_RANK'] instead. See https://pytorch.org/docs/stable/distributed.html#launch-utility for further instructions

FutureWarning, WARNING:torch.distributed.run:

Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed.

2022-09-10 04:40:58,017 - mmedit - INFO - Use load_from_http loader

Use load_from_local loader Use load_from_local loader [ ] 0/16, elapsed: 0s, ETA:/share4/home/zqiang/anaconda3/envs/FTVSR003/lib/python3.7/site-packages/torch/functional.py:568: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at /opt/conda/conda-bld/pytorch_1646755953518/work/aten/src/ATen/native/TensorShape.cpp:2228.) return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined] /share4/home/zqiang/anaconda3/envs/FTVSR003/lib/python3.7/site-packages/torch/functional.py:568: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at /opt/conda/conda-bld/pytorch_1646755953518/work/aten/src/ATen/native/TensorShape.cpp:2228.) return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined] [>>>>>>>>>>>>>>>>>> ] 6/16, 0.0 task/s, elapsed: 348s, ETA: 580sTraceback (most recent call last): File "./tools/test.py", line 229, in main() File "./tools/test.py", line 191, in main empty_cache=empty_cache) File "/share4/home/zqiang/FTVSR-main/mmedit/apis/test.py", line 108, in multi_gpu_test **data) File "/share4/home/zqiang/anaconda3/envs/FTVSR003/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl return forward_call(*input, **kwargs) File "/share4/home/zqiang/FTVSR-main/mmedit/core/distributed_wrapper.py", line 113, in forward return self.module(*inputs[0], **kwargs[0]) File "/share4/home/zqiang/anaconda3/envs/FTVSR003/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl return forward_call(*input, **kwargs) File "/share4/home/zqiang/anaconda3/envs/FTVSR003/lib/python3.7/site-packages/mmcv/runner/fp16_utils.py", line 98, in new_func return old_func(*args, **kwargs) File "/share4/home/zqiang/FTVSR-main/mmedit/models/restorers/basic_restorer.py", line 74, in forward return self.forward_test(lq, gt, qp, **kwargs) File "/share4/home/zqiang/FTVSR-main/mmedit/models/restorers/ttvsr.py", line 179, in forward_test output = self.generator(lq) File "/share4/home/zqiang/anaconda3/envs/FTVSR003/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl return forward_call(*input, **kwargs) File "/share4/home/zqiang/anaconda3/envs/FTVSR003/lib/python3.7/site-packages/torch/nn/parallel/distributed.py", line 963, in forward output = self.module(*inputs[0], **kwargs[0]) File "/share4/home/zqiang/anaconda3/envs/FTVSR003/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl return forward_call(*input, **kwargs) File "/share4/home/zqiang/FTVSR-main/mmedit/models/backbones/sr_backbones/ftvsr.py", line 132, in forward 'The height and width of inputs should be at least 64, ' AssertionError: The height and width of inputs should be at least 64, but got 60 and 88. [>>>>>>>>>>>>>>>>>>>>>>>>> ] 8/16, 0.0 task/s, elapsed: 414s, ETA: 414sTraceback (most recent call last): File "./tools/test.py", line 229, in main() File "./tools/test.py", line 191, in main empty_cache=empty_cache) File "/share4/home/zqiang/FTVSR-main/mmedit/apis/test.py", line 108, in multi_gpu_test **data) File "/share4/home/zqiang/anaconda3/envs/FTVSR003/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl return forward_call(*input, **kwargs) File "/share4/home/zqiang/FTVSR-main/mmedit/core/distributed_wrapper.py", line 113, in forward return self.module(*inputs[0], **kwargs[0]) File "/share4/home/zqiang/anaconda3/envs/FTVSR003/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl return forward_call(*input, **kwargs) File "/share4/home/zqiang/anaconda3/envs/FTVSR003/lib/python3.7/site-packages/mmcv/runner/fp16_utils.py", line 98, in new_func return old_func(*args, **kwargs) File "/share4/home/zqiang/FTVSR-main/mmedit/models/restorers/basic_restorer.py", line 74, in forward return self.forward_test(lq, gt, qp, **kwargs) File "/share4/home/zqiang/FTVSR-main/mmedit/models/restorers/ttvsr.py", line 179, in forward_test output = self.generator(lq) File "/share4/home/zqiang/anaconda3/envs/FTVSR003/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl return forward_call(*input, **kwargs) File "/share4/home/zqiang/anaconda3/envs/FTVSR003/lib/python3.7/site-packages/torch/nn/parallel/distributed.py", line 963, in forward output = self.module(*inputs[0], **kwargs[0]) File "/share4/home/zqiang/anaconda3/envs/FTVSR003/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl return forward_call(*input, **kwargs) File "/share4/home/zqiang/FTVSR-main/mmedit/models/backbones/sr_backbones/ftvsr.py", line 132, in forward 'The height and width of inputs should be at least 64, ' AssertionError: The height and width of inputs should be at least 64, but got 60 and 88.

Please remove the limitation of input size. We have updated the codes.

from ftvsr.

We have another question: training the FTVSR needing GPU requirement, how many GPU numbers and GPU memory can be trained successfully?

We use 8 V100 with 32G memory.

from ftvsr.