Comments (2)
Hi @sallana22
As can be found in the logic of the infidelity metric, it "patches the input" meaning that it expects input data. I think the line:
data_applicability = {DataType.IMAGE, DataType.TIMESERIES, DataType.TABULAR}
may have caused the issue, as our implementation of the infidelity metric does not support tabular data. This is removed in the following commit: 0ef57b6.
The second error appeared as we assumed that the input also had a channel, the docstring includes "Checks if value is smaller than input size, assumes batch and channel first dimension."
I have made changes (see PR #326) and will merge to main branch when the tests branch. Just pull from the main and then check that it is working for you.
from quantus.
Hi @annahedstroem,
Thanks for the quick resolution! I will exclude infidelity analysis on the tabular dataset.
For faithfulness correlation, your changes work but hit an error on asserts.py, line 295. Adding an elif on line 295 as below solves the problem:
if len(x.shape) == 2:
if value >= np.prod(x.shape[1:]):
raise ValueError(
f"'{value_name}' must be smaller than input size."
f" [{value} >= {np.prod(x.shape[1:])}]"
)
elif value >= np.prod(x.shape[2:]):
raise ValueError(
f"'{value_name}' must be smaller than input size."
f" [{value} >= {np.prod(x.shape[2:])}]"
)
The metric evaluation, however, is computationally slow on the complete test set. Evaluating on 10% of records (approx. 500) takes about 30 mins on a 2GHz quad-core cpu.
from quantus.
Related Issues (20)
- toml missing HOT 1
- Pointing game need a tolerance margin option
- numpy version requirements HOT 1
- Investigate vectorizing metric computation
- Adding more explantation methods HOT 1
- Py37 end of life HOT 1
- InputInvariance for CNN
- Infer_channel_first called even if channel_first is set HOT 3
- tf-explain does not work with various data types, make more explicit to users
- Refactor quantus.evaluate() and expand docstring with examples HOT 2
- Make SmoothMPRT faster for torch (see implementation)
- Add new "compressibility" (complexity) metric
- Support Model-Agnostic Explainers HOT 1
- The problem faced by GradCAM and Occlusion Sensitivity methods when dealing with images with more than 3 bands. HOT 1
- Lime with Relative Input Stability and Local Lipschitz Estimate HOT 1
- Remove dependency of pytest-lazy-fixture which causes problems with pytest==8.0.0
- ROAD takes 6 seconds for single image with GPU enabled HOT 1
- ROAD returns 0 all the time HOT 3
- Wrong calculation of selectivity HOT 3
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 quantus.