Comments (3)
Update:
The code crashes in the following block:
# build unsupervised dataloader datasets, dataloaders, samplers = build_unsupervised_dataloader( dataset_cfg=cfg.DATA_CONFIG, class_names=cfg.CLASS_NAMES, batch_size=args.batch_size, root_path=cfg.DATA_CONFIG.DATA_PATH, dist=dist_train, workers=args.workers, logger=logger, merge_all_iters_to_one_epoch=args.merge_all_iters_to_one_epoch )
Found in the tools/train_pointcontrast.py
file
from 3dtrans.
Update:
The code seems to crash on this specific code block in once_semi_dataset.py
On line 64 and 65.
The script sometimes manages to load the once_raw_data_small.pkl
file and sometimes doesn't.
![image](https://private-user-images.githubusercontent.com/60174223/282776566-c629c9a5-b526-4940-9f3b-e5d0fbc313b9.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.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.lAYdG-Z7qIEWHwImGHNeYoosi-8LpyVqtyxqLbNJMfA)
Do you have any idea why this might be happening @BOBrown?
from 3dtrans.
Update.
Fixed the problem, it was due to a lack of GPU resources
Thanks for help :)
from 3dtrans.
Related Issues (20)
- About ReSimAD HOT 2
- The installation of gcc-5.4.0 HOT 1
- TypeError: __init__() missing 3 required positional arguments: 'num_class_s2', 'dataset_s2', and 'source_one_name'[] HOT 1
- Using the merge_labels.py file HOT 7
- Pretraining on NuScenes HOT 1
- KeyError: "param 'initial_lr' is not specified in param_groups[0] when resuming an optimizer" HOT 4
- Using ckpt for pretraining HOT 4
- Creating Waymo infos using huge amounts of ram HOT 1
- How should I use Uni3D to train multiple datasets? HOT 2
- Why is SHIFT_COOR set to [0.0, 0.0, 1.6] in KITTI? HOT 2
- Question About AD-PT HOT 2
- Waymo evaluation issue HOT 6
- Questions on detection heads of Uni3D HOT 4
- Questions on Training Uni3D HOT 5
- Quick Squence Demo for 3DTrans ( KITTI / Waymo) HOT 1
- Fine-tuning on Waymo-Kitti HOT 1
- Question on generalization study on Uni3D HOT 1
- Problem about GPU memory HOT 1
- Question for lidar intensity input 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 3dtrans.