Dear author, thanks for you perfect code ,but I missed a problem when I try to run it on my device. I beg you advices!

[Yuanjia-Cao]

NameError: name 'torchmetrics' is not defined
The specific situation is list as follows
Traceback (most recent call last):
File "/media/yjc/G/DetectorFreeSfM/eval_dataset.py", line 13, in <module>
import torchmetrics
File "/home/yjc/miniconda3/envs/detectorfreesfm/lib/python3.9/site-packages/torchmetrics/init.py", line 26, in <module>
from torchmetrics import functional # noqa: E402
File "/home/yjc/miniconda3/envs/detectorfreesfm/lib/python3.9/site-packages/torchmetrics/functional/init.py", line 14, in <module>
from torchmetrics.functional.audio._deprecated import _permutation_invariant_training as permutation_invariant_training
File "/home/yjc/miniconda3/envs/detectorfreesfm/lib/python3.9/site-packages/torchmetrics/functional/audio/init.py", line 14, in <module>
from torchmetrics.functional.audio.pit import permutation_invariant_training, pit_permutate
File "/home/yjc/miniconda3/envs/detectorfreesfm/lib/python3.9/site-packages/torchmetrics/functional/audio/pit.py", line 22, in <module>
from torchmetrics.utilities import rank_zero_warn
File "/home/yjc/miniconda3/envs/detectorfreesfm/lib/python3.9/site-packages/torchmetrics/utilities/init.py", line 14, in <module>
from torchmetrics.utilities.checks import check_forward_full_state_property
File "/home/yjc/miniconda3/envs/detectorfreesfm/lib/python3.9/site-packages/torchmetrics/utilities/checks.py", line 25, in <module>
from torchmetrics.metric import Metric
File "/home/yjc/miniconda3/envs/detectorfreesfm/lib/python3.9/site-packages/torchmetrics/metric.py", line 30, in <module>
from torchmetrics.utilities.data import (
File "/home/yjc/miniconda3/envs/detectorfreesfm/lib/python3.9/site-packages/torchmetrics/utilities/data.py", line 38, in <module>
def dim_zero_sum(x: Tensor) -> torchmetrics.utilities.dataTensor:
NameError: name 'torchmetrics' is not defined

[hxy-123]

It seems that the torchmetrics module is required by the omegaconf module, where we forgot to include it in the requirements. You can try out the command pip install torchmetrics==0.6.0. We have also added it to the requirements.txt.

[Yuanjia-Cao]

yeah! You are greate! But I missed a new question with colmap, what should I do next? Best wishes to you!
2024-05-31 14:10:36.460 | INFO | main:eval_core:35 - Worker: 0 will process: ['/media/yjc/G/DetectorFreeSfM/SfM_dataset/example_dataset/example_scene'], total: 1 scenes
0%| | 0/1 [00:00<?, ?it/s]2024-05-31 14:10:36.462 | INFO | src.construct_pairs.pairs_exhaustive:exhaustive_all_pairs:11 - Total:28 pairs
2024-05-31 14:10:39.399 | WARNING | src.dataset.coarse_sfm_refinement_dataset:init:69 - COLMAP is not valid, current COLMAP path: /media/yjc/G/DetectorFreeSfM/SfM_dataset/example_dataset/example_scene/DetectorFreeSfM_loftr_official_coarse_only__scratch_no_intrin/colmap_coarse/-1
2024-05-31 14:10:39.399 | WARNING | src.post_optimization.post_optimization:post_optimization:142 - Build colmap coarse dataset fail! colmap point3D or images or cameras is empty!

[hxy-123]

The message thrown by the code shows that the coarse SfM failed. It seems that you are running our demo data, which has been tested working well by us. You can try out setting neuralsfm.redo_all=True and re-run the code to make sure the coarse matching has been performed.

[Yuanjia-Cao]

The message thrown by the code shows that the coarse SfM failed. It seems that you are running our demo data, which has been tested working well by us. You can try out setting neuralsfm.redo_all=True and re-run the code to make sure the coarse matching has been performed.

I create the environment in a new ubuntu system , and it encounter a new question.

Processing /media/yuanjia/Y/code/detectorfreesfm/third_party/RoIAlign.pytorch
Preparing metadata (setup.py) ... error
error: subprocess-exited-with-error

× python setup.py egg_info did not run successfully.
│ exit code: 1
╰─> [8 lines of output]
Traceback (most recent call last):
File "<string>", line 2, in <module>
File "<pip-setuptools-caller>", line 34, in <module>
File "/media/yuanjia/Y/code/detectorfreesfm/third_party/RoIAlign.pytorch/setup.py", line 3, in <module>
from torch.utils.cpp_extension import BuildExtension, CUDAExtension, CppExtension
File "/home/yuanjia/miniconda3/envs/detectorfreesfm/lib/python3.9/site-packages/torch/utils/cpp_extension.py", line 23, in <module>
from pkg_resources import packaging # type: ignore
ImportError: cannot import name 'packaging' from 'pkg_resources' (/home/yuanjia/miniconda3/envs/detectorfreesfm/lib/python3.9/site-packages/pkg_resources/init.py)
[end of output]

note: This error originates from a subprocess, and is likely not a problem with pip.
error: metadata-generation-failed

× Encountered error while generating package metadata.
╰─> See above for output.

note: This is an issue with the package mentioned above, not pip.
hint: See above for details.

[Osierddr]

The message thrown by the code shows that the coarse SfM failed. It seems that you are running our demo data, which has been tested working well by us. You can try out setting neuralsfm.redo_all=True and re-run the code to make sure the coarse matching has been performed.

I create the environment in a new ubuntu system , and it encounter a new question.

Processing /media/yuanjia/Y/code/detectorfreesfm/third_party/RoIAlign.pytorch Preparing metadata (setup.py) ... error error: subprocess-exited-with-error

× python setup.py egg_info did not run successfully. │ exit code: 1 ╰─> [8 lines of output] Traceback (most recent call last): File "", line 2, in File "", line 34, in File "/media/yuanjia/Y/code/detectorfreesfm/third_party/RoIAlign.pytorch/setup.py", line 3, in from torch.utils.cpp_extension import BuildExtension, CUDAExtension, CppExtension File "/home/yuanjia/miniconda3/envs/detectorfreesfm/lib/python3.9/site-packages/torch/utils/cpp_extension.py", line 23, in from pkg_resources import packaging # type: ignore ImportError: cannot import name 'packaging' from 'pkg_resources' (/home/yuanjia/miniconda3/envs/detectorfreesfm/lib/python3.9/site-packages/pkg_resources/init.py) [end of output]

note: This error originates from a subprocess, and is likely not a problem with pip. error: metadata-generation-failed

× Encountered error while generating package metadata. ╰─> See above for output.

note: This is an issue with the package mentioned above, not pip. hint: See above for details.

It can be seen from AUTOMATIC1111/stable-diffusion-webui#15863 (comment)
CHECK your version of setupotools, if >70.0.0, just degrade

[Starlit404]

The message thrown by the code shows that the coarse SfM failed. It seems that you are running our demo data, which has been tested working well by us. You can try out setting neuralsfm.redo_all=True and re-run the code to make sure the coarse matching has been performed.

I create the environment in a new ubuntu system , and it encounter a new question.

Processing /media/yuanjia/Y/code/detectorfreesfm/third_party/RoIAlign.pytorch Preparing metadata (setup.py) ... error error: subprocess-exited-with-error

× python setup.py egg_info did not run successfully. │ exit code: 1 ╰─> [8 lines of output] Traceback (most recent call last): File "", line 2, in File "", line 34, in File "/media/yuanjia/Y/code/detectorfreesfm/third_party/RoIAlign.pytorch/setup.py", line 3, in from torch.utils.cpp_extension import BuildExtension, CUDAExtension, CppExtension File "/home/yuanjia/miniconda3/envs/detectorfreesfm/lib/python3.9/site-packages/torch/utils/cpp_extension.py", line 23, in from pkg_resources import packaging # type: ignore ImportError: cannot import name 'packaging' from 'pkg_resources' (/home/yuanjia/miniconda3/envs/detectorfreesfm/lib/python3.9/site-packages/pkg_resources/init.py) [end of output]

note: This error originates from a subprocess, and is likely not a problem with pip. error: metadata-generation-failed

× Encountered error while generating package metadata. ╰─> See above for output.

note: This is an issue with the package mentioned above, not pip. hint: See above for details.

same question, do you have any solutions yet bro

[Starlit404]

The message thrown by the code shows that the coarse SfM failed. It seems that you are running our demo data, which has been tested working well by us. You can try out setting neuralsfm.redo_all=True and re-run the code to make sure the coarse matching has been performed.

I create the environment in a new ubuntu system , and it encounter a new question.

Processing /media/yuanjia/Y/code/detectorfreesfm/third_party/RoIAlign.pytorch Preparing metadata (setup.py) ... error error: subprocess-exited-with-error

× python setup.py egg_info did not run successfully. │ exit code: 1 ╰─> [8 lines of output] Traceback (most recent call last): File "", line 2, in File "", line 34, in File "/media/yuanjia/Y/code/detectorfreesfm/third_party/RoIAlign.pytorch/setup.py", line 3, in from torch.utils.cpp_extension import BuildExtension, CUDAExtension, CppExtension File "/home/yuanjia/miniconda3/envs/detectorfreesfm/lib/python3.9/site-packages/torch/utils/cpp_extension.py", line 23, in from pkg_resources import packaging # type: ignore ImportError: cannot import name 'packaging' from 'pkg_resources' (/home/yuanjia/miniconda3/envs/detectorfreesfm/lib/python3.9/site-packages/pkg_resources/init.py) [end of output]

note: This error originates from a subprocess, and is likely not a problem with pip. error: metadata-generation-failed

× Encountered error while generating package metadata. ╰─> See above for output.

note: This is an issue with the package mentioned above, not pip. hint: See above for details.

finally i tried out the successful way to solve this problem, it is because of the version of setuptools, you can try to downgrade it to lower version like 69.5.1