TensorBoard
E97076
TensorBoard is a visualization and debugging toolkit for TensorFlow that lets users inspect model graphs, track metrics, and analyze training runs.
Observed surface forms (1)
| Surface form | As subject | As object |
|---|---|---|
| Vertex AI TensorBoard | 0 | 1 |
Statements (50)
| Predicate | Object |
|---|---|
| instanceOf |
debugging toolkit
→
open-source software → software tool → visualization toolkit → |
| accessedVia |
command-line interface
→
web-based user interface → |
| developedBy |
Google
→
Google Brain → |
| developedFor | TensorFlow → |
| documentationURL | https://www.tensorflow.org/tensorboard → |
| hasComponent |
audio dashboard
→
distributions dashboard → graphs dashboard → histograms dashboard → images dashboard → profile dashboard → projector dashboard → scalars dashboard → text dashboard → |
| hostedOn | GitHub → |
| integratesWith |
Keras
→
TensorFlow Estimators → Keras →
surface form:
tf.keras
|
| license | Apache License 2.0 NERFINISHED → |
| partOf | TensorFlow ecosystem → |
| programmingLanguage | Python → |
| requires | event log files → |
| supports |
audio summaries
→
comparison of multiple training runs → custom plugins → debugging of training runs → distribution visualization → embedding visualization → graph visualization → histogram summaries → hyperparameter tuning visualization → image summaries → machine learning model visualization → metric tracking → performance analysis → profiling of TensorFlow programs → projector for embeddings → scalar summaries → training monitoring → |
| uses | TensorFlow summary operations → |
| visualizes |
accuracy curves
→
computational graphs → learning rate schedules → loss curves → model weights distributions → |
Referenced by (2)
Full triples — surface form annotated when it differs from this entity's canonical label.
this entity surface form:
Vertex AI TensorBoard