Comments (5)
Thanks for reaching out Tanmay and glad you were able to get attributions working with WIT in notebook mode.
Unfortunately, WIT in TensorBoard doesn't currently support attributions. This is because WIT in TensorBoard queries the models through TF Serving's PredictionService API, which only returns prediction results from the served model, and not other custom calculated values such as shap values. We rely on the model being queried to provide the attribution results (just as you did with a custom prediction fn when using attributions in notebook mode).
When you mention wanting to use TB mode due to a bigger data size, what exactly do you refer to? Are you able to load more data points when using WIT in TB vs in notebook mode, or were you just experimenting with the limits of each mode?
from what-if-tool.
Thanks a lot for replying and clarifying James, really appreciate your prompt response.
When I say bigger data size, I meant a test dataset of 100000 data points and ~2000 features. In the notebook mode, I experimented with a subset of my dataset of 500 data points and 50 features and was able to get the desired results. But when I triggered the WIT tool with complete dataset, the kernel kept dying repeatedly, so I thought it might be memory issue for notebook and thus wanted to experiment with the dataset in Tensorboard mode.
Please suggest for better ways to handle bigger sets for WIT, if possible. Regards.
from what-if-tool.
WIT does have limits on the amount of datapoints it can handle, which changes based on the size of each datapoint. This is because WIT sends all datapoints to the frontend for interactive analysis.
I'm curious how many data points you are able to use it with if you keep your same number of features but decrease the number of datapoints, and vice versa, if you are able to provide that data.
In general, for large-scale analysis, I would suggest tools that do offline processing, such as TensorFlow Model Analysis (https://www.tensorflow.org/tfx/model_analysis/install). That tool can be used in conjunction with WIT in colab/jupyter, where you find interesting data slices with TFMA, and then can load samples from that slice in WIT for further analysis. See https://ai.googleblog.com/2019/12/fairness-indicators-scalable.html for details on using TFMA's FairnessIndicators together with WIT.
from what-if-tool.
WIT does have limits on the amount of datapoints it can handle, which changes based on the size of each datapoint. This is because WIT sends all datapoints to the frontend for interactive analysis.
I'm curious how many data points you are able to use it with if you keep your same number of features but decrease the number of datapoints, and vice versa, if you are able to provide that data.
In general, for large-scale analysis, I would suggest tools that do offline processing, such as TensorFlow Model Analysis (https://www.tensorflow.org/tfx/model_analysis/install). That tool can be used in conjunction with WIT in colab/jupyter, where you find interesting data slices with TFMA, and then can load samples from that slice in WIT for further analysis. See https://ai.googleblog.com/2019/12/fairness-indicators-scalable.html for details on using TFMA's FairnessIndicators together with WIT.
from what-if-tool.
Thanks again James for your inputs. Really helped me a lot. I'm closing the issue now as I have a direction to go and experiment. I have another concern w.r.t 3d inputs in google explain for which I would open a new issue.
from what-if-tool.
Related Issues (20)
- Multiclass classification HOT 1
- Does what-if-tool support lightgbm or xgboost or scikit learning models? HOT 1
- Replacing model with predictions data HOT 1
- GOOGLE APPLICATION CREDENTIALS HOT 3
- Can this work just on data without any model input? HOT 1
- Can the dashboard be changed according to our need? HOT 1
- what if tool for ranking model? HOT 1
- how to install what if in managed notebook of vertex ai? HOT 3
- UnboundLocalError("local variable 'values' referenced before assignment") HOT 7
- what-if tool unable to return predictions - InactiveRpcError
- Enabling Persistence with what-if tensorboard plugin
- Data loading issue at scale with tensorboard what-if plugin
- Error when trying to reproduce example notebook locally HOT 6
- Custom Sprite Thumbnail Dimensions HOT 1
- Unable to import Witwidget
- Cant use fairness solution for regression so In that case How to mitigate the bias for the regression model? HOT 1
- ERROR: An error occurred during the fetch of repository 'zlib': HOT 1
- Uncaught (in promise) Error: Tensorflow Op is not supported: _FusedConv2D HOT 5
- Failed to load view class 'WITView' from module 'wit-widget'
- Predict in Datapoint-Editor leads to non-deterministic behavior 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 what-if-tool.