pykeen
v1.7.0
Getting Started
Installation
First Steps
Tracking Results during Training
Using MLflow
Using Neptune.ai
Using Weights and Biases
Using Tensorboard
Using File-Based Tracking
Saving Checkpoints during Training
A Toy Example with Translational Distance Models
Understanding the Evaluation
Optimizing a Model’s Hyper-parameters
Novel Link Prediction
Running an Ablation Study
Performance Tricks
Representations
Bring Your Own
Bring Your Own Data
Bring Your Own Interaction
Extending PyKEEN
Extending the Datasets
Extending the Models
Extending the Interaction Models (Old-Style)
Reference
Pipeline
Models
Datasets
Triples
Training
Stoppers
Loss Functions
Regularizers
Result Trackers
Negative Sampling
Filtering
Evaluation
Hyper-parameter Optimization
Ablation
Lookup
Prediction
Uncertainty
Sealant
Constants
pykeen.nn
Utilities
Appendix
References
pykeen
»
Tracking Results during Training
Edit on GitHub
Tracking Results during Training
Using MLflow
Pipeline Example
HPO Example
Reusing Experiments
Adding Tags
Using Neptune.ai
Preparation
Pipeline 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
Read the Docs
v: v1.7.0
Versions
latest
stable
v1.7.0
v1.6.0
v1.5.0
v1.4.0
v1.3.0
v1.1.0
v1.0.5
v1.0.0
Downloads
On Read the Docs
Project Home
Builds