Comments (8)
Oh and the newer gpu and the much weaker one trains the same length of time so somewhere is a bottle neck.
from darts.
Hi @Laenita,
Would you mind sharing the value of the parameters? So that we can have an idea of the number of parameters/size of the model.
Is the GPU acceleration being used at 1% for both the old and the new devices?
The pl_trainer_kwargs
argument looks good, this is what Pytorch-Lightning expects to enable this acceleration. I would recommend looking up their documentation at this this what Darts relies on for the deep learning models.
from darts.
Hi @madtoinou
Of course here are my parameters for my model I hope this helps:
input_length_chunk = 20
forecasting_horizon = 3
number_stacks = 4
number_blocks = 5
number_layers = 5
batch_size = 64
dropout_rate = 0.1
number_epochs = 180
number_epochs_val_period = 1
And yes, both the old and newer (and much faster) GPU's are both only showing 1% utilisation and also training the same time on the same model, indicating that something is wrong and heavy under-utilising.
But also the num_loader_workers=1 is not working at all for me, takes more than an hour with num_loader_workers >0.
Thanks for your assistance!
from darts.
Yes, I have the same problem: I am told that num_loader_workers is not a legit parameter.
from darts.
Hi @igorrivin & @Laenita,
As mentioned in another tread, the PR ##2295 is adding support for those arguments. Maybe try installing this branch/copy the changes and see if it solves the bottleneck?
from darts.
Hi @madtoinou
I have copied the changes from PR ##2295
But now whenever I add persistent_workers= True and num_loader_workers=16 (or even just 1) it gets stuck on Sanity_checking? Did I maybe miss anything? Thank you for your assistance!
from darts.
Which sanity checking are you referring to?
from darts.
Hi @madtoinou, the best explanation I can show is this PNG where the model first goes into a Sanity Checking Phase before starting training:
from darts.
Related Issues (20)
- TSMixer ConditionalMixer Skip Connections HOT 1
- [BUG] PLForecastingModule._calculate_metrics should call log_dict with batch_size HOT 2
- [BUG] TorchMetrics loop implementation isn't compatible with stateful metrics HOT 1
- [BUG] TCNModel changes the shape of data erroneously before loss evaluation HOT 3
- [BUG] TFTModel returns StopIteration on decoder_vsn() call in forward() HOT 5
- How to make TorchForecastingModel store the best model checkpoint? HOT 1
- New model - TimeMixer
- [BUG] Static covariates not added to val_series for RegressionModel HOT 1
- Embedding extraction for clustering HOT 1
- [BUG] Scaler took a long time to start fit
- [BUG] Distributed prediction crash HOT 2
- Loading historical forecasts of future covariates for training - forecast changes each time step
- [Question] How to plot prediction in tensorboard for torch/lightning models?
- Enhance integration of Global and Local models. HOT 2
- [QUESTION] from darts.explainability import TFTExplainer ImportError: cannot import name 'TFTExplainer' from 'darts.explainability' HOT 1
- Is there a Way to Represent Static Covariates and Also Different Items? HOT 1
- Question about past covariates, input_chunk_length, output_chunk_length and using trained model in real-life problem. HOT 2
- [FEATURE REQUEST] Add temporal_hidden_past and temporal_hidden_future hyperparams to TiDEModel
- [BUG]Inconsistent Prediction Behavior Using GPU vs. CPU in Darts Framework HOT 1
- [Question] 'numpy.linalg.LinAlgError' with VARIMA model HOT 5
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 darts.