pykeen
Tutorials
Installation
First Steps
A Toy Example with Translational Distance Models
Inductive Link Prediction
How-to Guides
Bring Your Own Data
Bring Your Own Interaction
Extending the Datasets
Extending the Models
Splitting
Getting Started with NodePiece
Using Resolvers
Saving Checkpoints during Training
Optimizing a Model’s Hyper-parameters
Running an Ablation Study
Tracking Results during Training
Using MLflow
Using Weights and Biases
Using Tensorboard
Using File-Based Tracking
Troubleshooting
Explanation
Knowledge Graph Embedding Models
Interaction Functions
Representations
Normalizer, Constrainer & Regularizer
Understanding the Evaluation
Performance Tricks
Dataset Degree Distributions
Reference
Pipeline
Models
Datasets
Inductive Datasets
Entity Alignment
Triples
Triples Workflows
Inverse Relations
Training
Stoppers
Loss Functions
Loss Weighting
Regularizers
Result Trackers
Negative Sampling
Filtering
Optimizers
Evaluation
Metrics
Hyper-parameter Optimization
Ablation
Prediction
Uncertainty
Sealant
Constants
Flexible Weight Checkpoints
pykeen.nn
PyTorch Lightning Integration
Utilities
Appendix
References
pykeen
Tracking Results during Training
View page source
Tracking Results during Training
Result Trackers
Using MLflow
Pipeline Example
HPO Example
Reusing Experiments
Adding Tags
Using Weights and Biases
Pipeline Example
HPO Example
Using Tensorboard
Installing Tensorboard
Starting Tensorboard
Minimal Pipeline Example
Specifying a Log Name
Specifying a Custom Log Directory
Minimal HPO Pipeline Example
Using File-Based Tracking
Minimal Pipeline Example with CSV
Specifying a Name
Combining with
tail
Pipeline Example with JSON