albertogaspar / dts Goto Github PK
View Code? Open in Web Editor NEWA Keras library for multi-step time-series forecasting.
License: MIT License
A Keras library for multi-step time-series forecasting.
License: MIT License
When installing all dependencies according to ENV 2, i get the following error:
Using TensorFlow backend.
Traceback (most recent call last):
File "C:\PATH\Python\Python37\lib\pkgutil.py", line 493, in find_loader
spec = importlib.util.find_spec(fullname)
File "C:\PATH\Python\Python37\lib\importlib\util.py", line 114, in find_spec
raise ValueError('{}.__spec__ is None'.format(name))
ValueError: tensorflow.__spec__ is None
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "recurrent.py", line 15, in <module>
from dts import config
File "c:\PATH\dts\dts\__init__.py", line 10, in <module>
from dts.utils.logger import logger
File "c:\PATH\dts\dts\utils\__init__.py", line 3, in <module>
from dts.utils.experiments import DTSExperiment, log_metrics, run_single_experiment, run_grid_search
File "c:\PATH\dts\dts\utils\experiments.py", line 1, in <module>
from sacred import Experiment
File "C:\PATH\dts\.venv\lib\site-packages\sacred\__init__.py", line 13, in <m
odule>
from sacred.experiment import Experiment
File "C:\PATH\dts\.venv\lib\site-packages\sacred\experiment.py", line 13, in
<module>
from sacred.arg_parser import format_usage, get_config_updates
File "C:\PATH\dts\.venv\lib\site-packages\sacred\arg_parser.py", line 16, in
<module>
from sacred.serializer import restore
File "C:\PATH\dts\.venv\lib\site-packages\sacred\serializer.py", line 8, in <
module>
from sacred import optional as opt
File "C:\PATH\dts\.venv\lib\site-packages\sacred\optional.py", line 40, in <m
odule>
has_tensorflow = modules_exist("tensorflow")
File "C:\PATH\dts\.venv\lib\site-packages\sacred\utils.py", line 656, in modu
les_exist
return all(module_exists(m) for m in modnames)
File "C:\PATH\dts\.venv\lib\site-packages\sacred\utils.py", line 656, in <gen
expr>
return all(module_exists(m) for m in modnames)
File "C:\PATH\dts\.venv\lib\site-packages\sacred\utils.py", line 652, in modu
le_exists
return pkgutil.find_loader(modname) is not None
File "C:\Users\carlv\AppData\Local\Programs\Python\Python37\lib\pkgutil.py", line 499, in find_loader
raise ImportError(msg.format(fullname, type(ex), ex)) from ex
ImportError: Error while finding loader for 'tensorflow' (<class 'ValueError'>: tensorflow.__spec__ is None)
i do konw how tu run " python FILENAME.py --add_config FULLPATH_TO_YAML_FILE "
Do you mean to create a FILENAME.PY file first? What code is in filename? Thank you
Line 241 in f10ab16
Can we alter the code somewhere to predict not just one time series, but predict all the multivariate inputs?
Hello, I am trying to run the tcn.py example and I am facing some difficulties.
with
--add_config [...]/config/tcn.yaml --observer file
It returns
File "[...]\dts\examples\tcn.py", line 184, in <module>
observer_type=args.observer)
TypeError: run_single_experiment() missing 1 required positional argument: 'log_dir'
Can you please provide some fruitful input?
I'm currently reproducing the paper results for the UCI dataset, using the GRU architecture.
My results were almost identical to them:
RMSE: 0.745 ± 0.001
MAE: 0.529 ± 0.002
But looking at the recurrent.yaml file used, the output_sequence_length seems to be only 24 steps ahead:
train: False
dataset: 'uci'
exogenous: False
epochs: 1
batch_size: 1024
input_sequence_length: 96
output_sequence_length: 24
dropout: 0.0
layers: 1
units: 50
learning_rate: 0.001
cell: 'gru'
l2: 0.0005
MIMO: True
detrend: True
Due to the UCI dataset having 15min sampling frequency, this means the model is forecasting only 6h into the future, instead of the 24h reported.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.