-
### Problem Description
When I use seq2seq model,such as TCN or LSTM or Transformer,they are have two inputs,one is x,another is y.And x's shape is different with y's shape,for example x's shape is (…
-
Deepexplainer fails with TF2.3, ok with 2.2
-
I have a Random Forest model that is built on raw features and first-order interactions (tabular data). How should I map the SHAP values to the raw feature space for the interaction terms?
-
Hi,
I am working with data of shapes:
```
ins.shape = (1000,29,60,60)
outs.shape = (1000,1,60,60)
```
The output of this network is a 60x60 real-valued 'image'. The input into the algorithm …
-
Hi there,
thank you for the excellent work! I am trying to generate SHAP values for a model with two input branches: One LSTM branch that ingests sequential data (3D array) and one that ingests no…
-
Hey there 👋, I'm the founder of https://magus.gg/, and we're providing a web-based nerf implementation of shap-e. Users are able to directly download .glb generated files too. We also support point cl…
-
Copied from https://github.com/dsgibbons/shap/issues/98
We have seen GitHub Actions randomly fail occasionally due to floating-point precision issues. See, for example:
- https://github.com/dsgi…
-
Hi
Single-Class (churn) classification problem, about 500 features, trained with LightGbm. Want to use explain_prediction to get insight into how decisions are made for particular features.
What…
-
The code below shows the error I get when trying to install a Python package (just used `shap` like in the README) in my miniconda.
``` r
library(rminiconda)
rminiconda::install_miniconda(path …
-
TLDR: I couldn't make DeepExplainer show the correlation between input and output when using a softmax, the plots are below, the code is [here](https://github.com/ydib/shap_softmax_problem/blob/main/s…
ydib updated
5 months ago