Comments (2)
Hi @ruomingzhai,
I think this might be due to the fact that torch-points3d
does not like loading optimizers with differential learning rates. Indeed, to train the 3D+2D models, some blocks of the model have different learning rates (eg the 2D blocks vs the 3D blocks). When loading the optimizer, this might cause issues.
As of now, the project does not support loading pretrained optimizer and scheduler to fine-tune on. If you want to reproduce the training experiments, use scripts/train_kitti360.sh
. If you want to infer using the pretrained weights, use notebooks/kitti360_inference.ipynb
.
If you want to fine-tune a pretrained model, you will need to create a new optimizer and scheduler anyways, which should bypass the problem you encountered. For that, you can simply follow the procedure in scripts/train_kitti360.sh
, with a few changes:
- add the path to the pretrained model in your model config:
<model_name>:
path_pretrained: /path/to/the/pretrained/model/<model_name>.pt
...
- adapt the
training
config to suit your needs, especially for the learning rates, which you might want to reduce - adapt the
lr_scheduler
config to suit your needs
Hope that helps !
from deepviewagg.
Hi, assuming the last reply addressed the question, I am closing the issue.
from deepviewagg.
Related Issues (20)
- Intermediate Fusion Model Config Issues with KITTI and ScanNet HOT 3
- torch-points-kernels and torchsparse install error with 3090, CUDA 11.2 HOT 2
- Is it possible to run with multiple GPU? HOT 2
- Should the kitti360 dataset be complete now, or only a portion of it need to be downloaded HOT 3
- training time HOT 4
- Hi, Author. HOT 1
- mm_files folder problem. HOT 13
- problem in creating no3d model HOT 1
- A problem about IndexError: index 8 is out of bounds for dimension 0 with size 5 HOT 2
- The problem about AttributeError: 'int' object has no attribute 'feats' HOT 8
- I found an issue while testing the project HOT 2
- How to produce KITTI-360 `test` predictions ? HOT 1
- My training is unable to execute the final Epoch.
- Python 3.8.5 HOT 8
- Error when running last cell in kitti360_inference.ipynb notebook... HOT 4
- Warning -> Error when running kitti360_inference.ipynb HOT 6
- Accuracy for KITTI-360 inference on Validation dataset HOT 3
- How to test custom data HOT 1
- Accuracy is low for Validation dataset HOT 1
- Issue when running the inference script on the test data
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 deepviewagg.