Comments (2)
@liudexiang3218 Thanks for bringing it to our notice. I'll get this fixed soon. However, if you're not restricted to only use mlflow
, I recommend you to use the sktime-native saving method:
from sktime.classification.deep_learning.lstmfcn import LSTMFCNClassifier
from sktime.datasets import load_italy_power_demand
from sktime.base import load
X_train, y_train = load_italy_power_demand(split="train", return_type="numpy3D")
X_new, _ = load_italy_power_demand(split="test", return_type="numpy3D")
classifier=LSTMFCNClassifier(verbose=2,n_epochs=5)
classifier.fit(X_train,y_train)
classifier.save("estimator")
new_classifier = load("estimator")
new_classifier.predict(X_new)
from sktime.
This should be resolved by #5526.
from sktime.
Related Issues (20)
- [BUG] `test_VARMAX_against_statsmodels` crashing with memory failure
- [ENH] randomization/derandomization tag and conditional test logic HOT 2
- [BUG] `save()` method fails to save a trained `CNNClassifier` instance HOT 2
- [BUG] `unequal_length` clusterer bugs out in unequal data set HOT 9
- [ENH] Composition forecaster that clusters time series and forecasts by cluster HOT 19
- [BUG] `dask` related failures, sporadic HOT 6
- [BUG] Images are broken on https://www.sktime.net/en/stable/examples/forecasting/01c_forecasting_hierarchical_global.html HOT 3
- [DOC] Report on Improving user journey in retrieving algorithms, tags, metadata HOT 1
- [ENH] Syntetos/Boylan ADI/CV feature extractor for different types of demand (intermittent etc) HOT 8
- [BUG] `AutoETS` gives different forecasts on different machines and different OS; for same input data HOT 25
- [ENH] install package via `uv` instead of `pip` HOT 4
- [ENH] allow `FeatureSelection` to select features in pairs/sets HOT 2
- [BUG] TBATS docstring example does not run HOT 2
- [BUG] Version 0.28.0 `conda` release, all extras dep set `sktime-all-extras`, does not install on windows due to broken `pycatch22` specification identifier HOT 29
- AutoETS Different prediction result on different OS HOT 1
- [ENH] Using custom distance measure with `TimeSeriesKMeans` (`distance_matrix_fast` of `dtaidistance`) HOT 10
- [ENH] Smooth Forecast Reconciliation algorithm by S Ando
- [MNT] lack of test coverage of `pandas 2.2.X` *and* deep learning backends HOT 11
- [ENH] Bollinger bands HOT 1
- [BUG] I do not understand why this code is not working properly 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 sktime.