-
Awesome implementation, have you considered adding Gradio as a UI layer for users to access the generation through the browser?
-
The following code something produces errors when using the CUDA backend:
```cpp
#include
#include
using namespace cl::sycl;
int main()
{
const int n = 10;
float res[n];
std…
-
I saw different documents using the two functions to extract shape values. What's their difference?
-
Thank you for such wonderful package.
I have categorical Treatment (value = 0, 1, 2) and I used DML.
The effect of the treatments is below.
Then I tried the marginal effect with base treatmen…
-
Is there a way to change the colours of the Force Plot if you are using Matplotlib = True?
-
Is there currently a way to pass a sklearn.pipeline.Pipeline object as the model parameter? I can't seem to do it, and I think that being able to do it would be better for the internal cross validatio…
-
SD.Next UI supports HuggingFace's diffusers and therefore models like SDXL, DeepfloydIF and Unidiffusion. Since Shap-E is also in diffusers, a better alternative would be to implement the model inside…
-
Are shap interaction values implemented only in TreeExplainer? Are there any plans to implement them soon in other explainers? Would it be easier to implement for KernelExplainer or DeepExplainer?
-
The problem is caused by transformation of the contributions which are computed for $P(Y=0)$ but we are actually interested in contributions to $P(Y=1)$.
The transformation is done by subtracting f…
-
First time posting here, so big props to @slundberg and everyone else contributing. Wonderful package.
I'm using a KernelExplainer to produce shapley values for a sample, and I noticed that each ti…