Difference between revisions of "TensorBoard"
m |
m |
||
| Line 18: | Line 18: | ||
* [[TensorWatch]] | * [[TensorWatch]] | ||
* [[Principal Component Analysis (PCA)]] ...linear | * [[Principal Component Analysis (PCA)]] ...linear | ||
| − | * [[T-Distributed Stochastic Neighbor Embedding (t-SNE)]] ...non-linear | + | * [[Embedding]] |
| + | ** [[T-Distributed Stochastic Neighbor Embedding (t-SNE)]] ...non-linear | ||
* [[Graphical Tools for Modeling AI Components]] | * [[Graphical Tools for Modeling AI Components]] | ||
* [http://idl.cs.washington.edu/files/2018-TensorFlowGraph-VAST.pdf Visualizing Dataflow Graphs of Deep Learning Models in TensorFlow | K. Wongsuphasawat, D. Smilkov, J. Wexler, J. Wilson, D. Mane, D. Fritz, D. Krishnan,] [[Creatives#Fernanda Viegas |F. Viegas]], and [[Creatives#Martin Wattenberg |M. Wattenberg]] | * [http://idl.cs.washington.edu/files/2018-TensorFlowGraph-VAST.pdf Visualizing Dataflow Graphs of Deep Learning Models in TensorFlow | K. Wongsuphasawat, D. Smilkov, J. Wexler, J. Wilson, D. Mane, D. Fritz, D. Krishnan,] [[Creatives#Fernanda Viegas |F. Viegas]], and [[Creatives#Martin Wattenberg |M. Wattenberg]] | ||
| − | In machine learning, to improve something you often need to be able to measure it. TensorBoard is a tool for providing the measurements and visualizations needed during the machine learning workflow. It enables tracking experiment metrics like loss and accuracy, visualizing the model graph, projecting | + | In machine learning, to improve something you often need to be able to measure it. TensorBoard is a tool for providing the measurements and visualizations needed during the machine learning workflow. It enables tracking experiment metrics like loss and accuracy, visualizing the model graph, projecting [[embedding]]s to a lower dimensional space, and much more. provides the visualization and tooling needed for machine learning experimentation: |
* Tracking and visualizing metrics such as loss and accuracy | * Tracking and visualizing metrics such as loss and accuracy | ||
* Visualizing the model graph (ops and layers) | * Visualizing the model graph (ops and layers) | ||
* Viewing histograms of weights, biases, or other tensors as they change over time | * Viewing histograms of weights, biases, or other tensors as they change over time | ||
| − | * Projecting | + | * Projecting [[embedding]]s to a lower dimensional space |
* Displaying images, text, and audio data | * Displaying images, text, and audio data | ||
* Profiling TensorFlow programs | * Profiling TensorFlow programs | ||
Revision as of 19:49, 26 June 2023
YouTube search... ...Google search
- TensorBoard | Google ...TensorFlow's visualization toolkit
- TensorFlow
- TensorFlow Playground
- TensorBoard: Graph Visualization
- Neural Networks Playground
- Visualization
- Colaboratory (Colab)
- Data Flow Graph (DFG)
- TensorWatch
- Principal Component Analysis (PCA) ...linear
- Embedding
- T-Distributed Stochastic Neighbor Embedding (t-SNE) ...non-linear
- Graphical Tools for Modeling AI Components
- Visualizing Dataflow Graphs of Deep Learning Models in TensorFlow | K. Wongsuphasawat, D. Smilkov, J. Wexler, J. Wilson, D. Mane, D. Fritz, D. Krishnan, F. Viegas, and M. Wattenberg
In machine learning, to improve something you often need to be able to measure it. TensorBoard is a tool for providing the measurements and visualizations needed during the machine learning workflow. It enables tracking experiment metrics like loss and accuracy, visualizing the model graph, projecting embeddings to a lower dimensional space, and much more. provides the visualization and tooling needed for machine learning experimentation:
- Tracking and visualizing metrics such as loss and accuracy
- Visualizing the model graph (ops and layers)
- Viewing histograms of weights, biases, or other tensors as they change over time
- Projecting embeddings to a lower dimensional space
- Displaying images, text, and audio data
- Profiling TensorFlow programs
