Comments (5)
Thank you for your interest in the library! I appreciate that we are a bit heavy on the dependencies, but we would need to think carefully which packages to split out as it would make several algorithms not work out-of-the-box for all use cases (e.g. we use tensorflow
internally for optimization, opencv-python
for downloading image datasets and spacy
for NLP corpus use cases. One option would be to try split the dependencies across use cases, e.g. to enable nlp
one could install alibi[nlp]
or for image usecases alibi[cv]
. Did you have any particular thoughts about this?
from alibi.
Using opencv-python just to download datasets seems like overkill, but otherwise that's pretty much what I had in mind. Dask is a pretty good example of doing this, using both extras (https://github.com/dask/dask/blob/master/setup.py) and subsidiary packages: (e.g. https://github.com/dask/dask-ml, https://github.com/dask/dask-xgboost)
It's also worth considering that, if people want to explain keras models, then they will already have keras installed, so it may not be necessary to have it as an explicit extra.
If you're using tensorflow internally, then clearly it's OK to have that as an install dependency. Although if it's only used for a small subset of the functionality, then it might still be worth having as an extra, like some tools do for their CLI (e.g. https://github.com/theskumar/python-dotenv/blob/master/setup.py).
from alibi.
Thanks for the feedback, I'm working on stripping out some of the unnecessary deps. For image downloading we can probably go with PIL
instead of opencv
which is much lighter.
from alibi.
@jamesmyatt I've slimmed down the package a little in v0.2.1. For now we will not split it up depending on the use case, but this might change as the functionality grows and the API stabilises. Probably the heaviest dependency is tensorflow
, it's quite key for some of the underlying optimization algorithms, but on the other hand not every method will use it. I will keep this issue open for now for further discussion.
from alibi.
Will close for now as currently running a fairly minimal set of dependencies for what we want to do.
from alibi.
Related Issues (20)
- IndexError with AnchorExplainer and Yolov8
- `typing-extensions` 4.6.0 breakage HOT 1
- Predictor attr not properly cleared when saving HOT 2
- `numba` warnings regarding `nopython` keyword HOT 3
- `PartialDependenceVariance` cannot be saved
- CI failing due to use of `np.int` in `shap` HOT 2
- How to pass parameters to the /api/v1.0/explain using AnchorImage? HOT 2
- `KernelShap` returns no explanations when `link='logit'` and predicted proba is 0 or 1
- RuntimeError: The Session graph is empty. Add operations to the graph before calling run() HOT 6
- RuntimeError: tf.placeholder() is not compatible with eager execution.
- RuntimeError: The Session graph is empty. Add operations to the graph before calling run().
- TypeError: 'float' object is not subscriptable
- PDP plots failing with `matplotlib==3.8.0` HOT 1
- `matplotlib` 3.8.0 type hints for public APIs result in type-checking failures
- Logo in README.md HOT 1
- Columns and DataType Not Explicitly Set on line 61 of data.py
- When use explainer.fit(X_train)οΌit went into a loop of error
- After getting anchors, how to use it to predict the label of an instance?
- Mixed continuous and categorical features in the AnchorTabular explainers (my dataset doesn't contain NaNs)
- New release? HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
π 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. πππ
-
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 β€οΈ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from alibi.