Comments (12)
I commented out:
- /habitat_baselines/rl/policy/obs_transforms:
- resize
in the ver_goat.yaml
and it worked. However, I'm not sure if this is the correct solution.
Additionally, I encountered the following error during execution:
FileNotFoundError: [Errno 2] No such file or directory: 'data/datasets/languagenav/hm3d/v5_final/train_embeddings/clip_train_embeddings.pkl
Could I possibly get the relevant data?
from goat-bench.
Hi, I encountered the same issue during inference. In addition, when attempting to load the task dataset alone, I encountered the following error:
Traceback (most recent call last):
File "NExplore/train/habitat_vis_exploration.py", line 43, in <module>
dataset = HabitatChallengeDataset(config, device=torch.device("cuda" if torch.cuda.is_available() else "cpu"))
File "/home/yan/Work/active_mapping/SeRFnav-goat/NExplore/datasets/dataset.py", line 59, in __init__
self.sim = habitat.Env(cfg)
File "/home/yan/Work/active_mapping/SeRFnav-goat/habitat-lab/habitat-lab/habitat/core/env.py", line 118, in __init__
self._task = make_task(
File "/home/yan/Work/active_mapping/SeRFnav-goat/habitat-lab/habitat-lab/habitat/tasks/registration.py", line 22, in make_task
return _task(**kwargs)
File "/home/yan/Work/active_mapping/SeRFnav-goat/goat-bench/goat_bench/task/goat_task.py", line 83, in __init__
super().__init__(*args, **kwargs)
File "/home/yan/Work/active_mapping/SeRFnav-goat/habitat-lab/habitat-lab/habitat/tasks/nav/nav.py", line 1320, in __init__
super().__init__(config=config, sim=sim, dataset=dataset)
File "/home/yan/Work/active_mapping/SeRFnav-goat/habitat-lab/habitat-lab/habitat/core/embodied_task.py", line 249, in __init__
self._init_entities(
File "/home/yan/Work/active_mapping/SeRFnav-goat/habitat-lab/habitat-lab/habitat/core/embodied_task.py", line 274, in _init_entities
entities[entity_name] = entity_type(
File "/home/yan/Work/active_mapping/SeRFnav-goat/habitat-lab/habitat-lab/habitat/tasks/nav/object_nav_task.py", line 128, in __init__
super().__init__(config=config)
File "/home/yan/Work/active_mapping/SeRFnav-goat/habitat-lab/habitat-lab/habitat/core/simulator.py", line 91, in __init__
self.observation_space = self._get_observation_space(*args, **kwargs)
File "/home/yan/Work/active_mapping/SeRFnav-goat/habitat-lab/habitat-lab/habitat/tasks/nav/object_nav_task.py", line 141, in _get_observation_space
self._dataset.category_to_task_category_id.values()
AttributeError: 'GoatDatasetV1' object has no attribute 'category_to_task_category_id'
It seems that the habitat-lab version isn't correct, or there might be some undeclared modifications to the source code of habitat-lab v0.2.3. Could you provide further guidance on this? @Ram81 @mukulkhanna @gchhablani
from goat-bench.
I installed the packages according to the README, but encountered some issues.
I needed to additionally install the lavis and vc_models packages. Also, even after installing the above packages, I still receive the following error when I try to run the train script.
MissingConfigException: In 'ver_goat.yaml': Could not load 'habitat_baselines/rl/policy/obs_transforms/resize'.
Is v0.2.3 the correct version of habitat-lab?
If you have the correct installation procedure with modifications, could you let me know? I look forward to your response.
I faced the same issues.
from vc_models.models.vit import model_utils
ModuleNotFoundError: No module named 'vc_models'
How did you install the vc_models package? @miyatai2 @Ram81 @mukulkhanna @gchhablani @Cassie-Lim
from goat-bench.
I used the vc_models from https://github.com/facebookresearch/eai-vc @yusirhhh
from goat-bench.
Thanks for your kind words. I have fixed the package issue with vc_models. However, when I tried to install salesforce-lavis using pip, I encountered the following error:
ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.
pydantic-core 2.14.6 requires typing-extensions!=4.7.0,>=4.6.0, but you have typing-extensions 4.4.0 which is incompatible.
openai 1.4.0 requires typing-extensions<5,>=4.5, but you have typing-extensions 4.4.0 which is incompatible.
vc-models 0.1 requires timm==0.6.11, but you have timm 0.4.12 which is incompatible.
What's the version of Python and salesforce-lavis you used, @miyatai2?
from goat-bench.
Thanks for your kind words. I have fixed the package issue with vc_models. However, when I tried to install salesforce-lavis using pip, I encountered the following error:
ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts. pydantic-core 2.14.6 requires typing-extensions!=4.7.0,>=4.6.0, but you have typing-extensions 4.4.0 which is incompatible. openai 1.4.0 requires typing-extensions<5,>=4.5, but you have typing-extensions 4.4.0 which is incompatible. vc-models 0.1 requires timm==0.6.11, but you have timm 0.4.12 which is incompatible.What's the version of Python and salesforce-lavis you used, @miyatai2?
I use salesforce-lavis 1.0.2 and python 3.8.18.
from goat-bench.
I commented out:
- /habitat_baselines/rl/policy/obs_transforms: - resize
in the
ver_goat.yaml
and it worked. However, I'm not sure if this is the correct solution.Additionally, I encountered the following error during execution:
FileNotFoundError: [Errno 2] No such file or directory: 'data/datasets/languagenav/hm3d/v5_final/train_embeddings/clip_train_embeddings.pkl
Could I possibly get the relevant data?
I can't find 'clip_train_embeddings.pkl' either. Have you solved it? @miyatai2
from goat-bench.
I have not resolved it yet.
from goat-bench.
Hi @miyatai2 @yusirhhh @Cassie-Lim @74284853 , apologies for the delay here. We have fixed a bunch of issues related to configs and installation and pushed to the main branch today. Please let me know if you are facing issues even after you rebase with latest changes from main.
@74284853 the missing cache files are available here.
from goat-bench.
@Ram81 FileNotFoundError: [Errno 2] No such file or directory: 'data/goat-assets/goal_cache/language_nav/val_seen_bert_embedding.pkl'
The val_seen_bert_embedding.pkl is not in https://github.com/Ram81/goat-bench?tab=readme-ov-file#cached-embeddings-and-model-checkpoints
from goat-bench.
@yusirhhh I could download the cache files with the following command:
git lfs clone https://huggingface.co/datasets/axel81/goat-bench data/goat-assets/
from goat-bench.
@Ram81 Thank you for the support! I was able to successfully execute the code with the latest updates/fixes. Since the problem has been resolved, I will be closing this issue now.
from goat-bench.
Related Issues (11)
- Is paper public? HOT 1
- How to run the evaluation? HOT 2
- Pretrained weights HOT 4
- About Table 5 in the Appendix. HOT 1
- oduleNotFoundError: No module named 'goat' HOT 2
- Will the pure language navigation dataset be released? HOT 3
- Could you please provide a more detailed instruction on the download and preparation of hm3d dataset? HOT 1
- Hi, what is the "full HM3D"? HOT 4
- AttributeError: 'BaseEpisode' object has no attribute 'tasks'
- Hi, Ques about goat-bench dataset HOT 1
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 goat-bench.