Comments (3)
More specifically:
INFO:__main__:Starting reconstruction of files matching /home/dev/Anantak/Pipelines/ontario_map_3/scene/images/.
INFO:__main__:Trying seeds: [0.36983939 0.28398129 0.75519018 0.17367966 0.46093806]
INFO:__main__:Processing 5 seeds in parallel.
[Parallel(n_jobs=3)]: Using backend LokyBackend with 3 concurrent workers.
INFO:ace_trainer:Using device for training: cuda
INFO:ace_trainer:ACE feature buffer device: cuda
INFO:ace_trainer:Setting random seed to 2089
INFO:ace_trainer:Disabling multi-threaded data loading because we cannot run multiple depth inference passes simultaneously.
INFO:dataset:Overwriting focal length with heuristic derived from image dimensions.
INFO:dataset:Loading RGB files from: /home/dev/Anantak/Pipelines/ontario_map_3/scene/images/
INFO:dataset:Overwriting dataset with single image: 0 - /home/dev/Anantak/Pipelines/ontario_map_3/scene/images/
INFO:dataset:Using ZoeDepth for depth initialization.
Using cache found in /home/dev/.cache/torch/hub/intel-isl_MiDaS_master
/home/dev/miniconda3/envs/ace0/lib/python3.8/site-packages/torch/hub.py:286: UserWarning: You are about to download and run code from an untrusted repository. In a future release, this won't be allowed. To add the repository to your trusted list, change the command to {calling_fn}(..., trust_repo=False) and a command prompt will appear asking for an explicit confirmation of trust, or load(..., trust_repo=True), which will assume that the prompt is to be answered with 'yes'. You can also use load(..., trust_repo='check') which will only prompt for confirmation if the repo is not already trusted. This will eventually be the default behaviour
warnings.warn(
Downloading: "https://github.com/isl-org/ZoeDepth/zipball/main" to /home/dev/.cache/torch/hub/main.zip
Traceback (most recent call last):
File "./train_ace.py", line 240, in <module>
trainer = TrainerACE(options)
File "/home/dev/Anantak/Pipelines/acezero/ace_trainer.py", line 100, in __init__
self.dataset = CamLocDataset(
File "/home/dev/Anantak/Pipelines/acezero/dataset.py", line 127, in __init__
self.depth_model = dataset_io.get_depth_model()
File "/home/dev/Anantak/Pipelines/acezero/dataset_io.py", line 208, in get_depth_model
model_zoe_nk = torch.hub.load(repo, "ZoeD_NK", pretrained=True, force_reload=init)
File "/home/dev/miniconda3/envs/ace0/lib/python3.8/site-packages/torch/hub.py", line 558, in load
model = _load_local(repo_or_dir, model, *args, **kwargs)
File "/home/dev/miniconda3/envs/ace0/lib/python3.8/site-packages/torch/hub.py", line 584, in _load_local
hub_module = _import_module(MODULE_HUBCONF, hubconf_path)
File "/home/dev/miniconda3/envs/ace0/lib/python3.8/site-packages/torch/hub.py", line 98, in _import_module
spec.loader.exec_module(module)
File "<frozen importlib._bootstrap_external>", line 843, in exec_module
File "<frozen importlib._bootstrap>", line 219, in _call_with_frames_removed
File "/home/dev/.cache/torch/hub/isl-org_ZoeDepth_main/hubconf.py", line 26, in <module>
File "/home/dev/.cache/torch/hub/isl-org_ZoeDepth_main/zoedepth/utils/config.py", line 28, in <module>
ModuleNotFoundError: No module named 'zoedepth.utils.easydict'
joblib.externals.loky.process_executor._RemoteTraceback:
"""
Looks like a Zoe-Depth related module? Not the weights itself
from acezero.
Try to set the init parameter of the function get_depth_model() in dataset_io.py to True. Let me/us know if it works.
Shouldnt this option be added as a flag for the parser maybe?
from acezero.
Thanks for your report.
There was a potential race condition in the download of the ZoeDepth model from torch.hub
causing corrupted downloads, since we run multiple seed iterations in parallel.
I pushed a fix, please update the repo and delete the contents of these folders in your home directory to force a clean download of the dependency:
rm -rf ~/.cache/torch/hub/intel-isl_MiDaS_master
rm -rf ~/.cache/torch/hub/isl-org_ZoeDepth_main
Please let us know if there are other problems.
from acezero.
Related Issues (20)
- Multiple cameras , intrinsics? HOT 1
- ffmpeg path HOT 1
- ACE0 with Sparse View Inputs HOT 1
- mean camera center when camera poses are unknown HOT 1
- Using the poses generated by acezero with 3DGS HOT 2
- Errors running ace_zero.py with WSL2 HOT 12
- RuntimeError: Re-rendering failed too often... HOT 2
- GLIBCXX_3.4.30 not found when --render_visualization True HOT 3
- ace_zero.py traceback HOT 3
- Submodule Build error HOT 2
- The speed does not match the paper. HOT 1
- ace_zero.py "/path/to/some/images/*.jpg" result_folder Traceback HOT 2
- RGBD as input? HOT 1
- AttributeError: 'NoneType' object has no attribute 'eglGetCurrentContext'
- urllib.error.HTTPError HOT 2
- Incomplete reconstruction HOT 1
- PLY Point Cloud File Generation HOT 1
- Install Error: Package not found HOT 2
- The point cloud visualization shows that the reconstruction effect is too poor. Please tell me what I did wrong. HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from acezero.