-
For example, when I try the LIME text explainer, I get the following error:
Attribute Error: 'SequenceClassifierOutput' object has no attribute 'detach'
Even the SHAP explainer code does not work …
-
https://engineering.linkedin.com/blog/2022/fasttreeshap--accelerating-shap-value-computation-for-trees
It looks like it's a drop-in replacement, which we'll start testing next week!
-
### Issue Description
I ran into a divide by zero issue in _violin.py when nbins =1
I'm not sure when this situation occurs but the module halts and does not give enough information to resolve it …
-
@slundberg Thanks for this amazing library. I have a model object of type xgboost.sklearn.XGBClassifier, which was trained with data passed from column transformer in sklearn. Hence it was a sparse CS…
-
Hi, slundberg,
**versions：**
keras 2.2.4
tensorflow 1.12.0
python2.7.18
CPU
shap 0.28.5
**Code piece：**
```
word_embedding_layer = Embedding(WORD_VOCAB_LEN,
W…
-
I'm using SHAP with LightGBM for regression.
The problem is that SHAP values don't sum up the predicted value.
Predicted values are all in the 0 - 10000 range. I have ~9000 features.
![Scree…
-
Hi,
I tried shap.force_plot with Iris dataset and kernel explainer, it is the same as the codes from the example in the front page of shap value.
The base value of explainer.expected_value[0] sh…
-
Hello,
I've written a simple binary classifier on a MobileNetV2 pretrained model (more info [here](https://keras.io/applications/#mobilenetv2)). When I run SHAP DeepExplainer,
```
background =…
-
How would you go about finding the feature importance for the DNN model?
-
Hello, I am trying to use Kernel SHAP with my own MNIST model. But when I run my code the SHAP values seem wrong. It for 8 of the 10 classes the values are always 0. For the class 0 the values are the…