Comments (2)
I can contribute if you guide me.
As far as I understood explainer base class need to pass customer dict to PretrainedConfig
during init.
from transformers-interpret.
@lalitpagaria that would be really helpful thanks. So because this only applies to sequence classification tasks I think the best place to implement this would be in the __init__
of the SequenceClassificationExplainer
.
On the API level I see it looking something like
cls_explainer = SequenceClassificationExplainer(model, tokenizer, custom_id2label = {0: "my_label1", 1: "my_label2"})
Where custom_id2label
is a optional parameter that can passed and will set the new values. I don't think you even need to overwrite id2label
on the HF model's config itself because the classification explainer sets these as attributes itself so changing it for the explainer should do, I try as much as possible not to interfere with HF model itself.
Some other things that would be nice to do before actually setting the new values would be to check that the length of custom_id2label.keys()
matches the existing length. In a case where a user accidentally sets too few or too many labels I would see it raising some sort of value error.
Another thing that this has got me thinking is that once the new id2label
is set it would be to set label2id
with the inverse values.
Thanks for volunteering to help on this, let me know if you need any further guidance.
from transformers-interpret.
Related Issues (20)
- What algorithm is used to visualize text in SequenceClassificationExplainer
- How to use transformers-interpret for sequencelabelling, for example layoutlmv3 or v3 HOT 1
- MultiLabelSequenceClassificationExplainer potentially bugged. HOT 14
- ImportError: cannot import name 'PairwiseSequenceClassificationExplainer' HOT 1
- How to interpret the model fine tuning on the pre-trained ViT model using the imagery with larger resolution (500 * 500) than the pre-trained dataset (224 * 224)
- Token Classification Memory Issue
- Issue using BertTokenizer (AttributeError) HOT 2
- 'Bert' object has no attribute 'config'
- Text attribution fails for XLM-Roberta models HOT 4
- Is it normal that attribution takes multiple seconds per text, even on a GPU? HOT 1
- ZeroShotClassificationExplainer appears to be broken
- Prediction differs from non-explainable evaluation HOT 1
- Output probability - SequenceClassificationExplainer
- Support for Summarization models HOT 3
- Support for Longformer
- ImageClassificationExplainer: AttributeError: ndim when trying to visualize. HOT 3
- Issue with Zero Shot Classifier
- How to use other types of transformers models? HOT 1
- Support for Reformer
- Broken link for Captum Algorithm Overview in the README
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 transformers-interpret.