hummingbird icon indicating copy to clipboard operation
hummingbird copied to clipboard

Hummingbird compiles trained ML models into tensor computation for faster inference.

Results 89 hummingbird issues
Sort by recently updated
recently updated
newest added

[The Ubuntu 18.04 Actions runner image will begin deprecation on 8/8/22 and will be fully unsupported by 12/1/22 · Issue #6002 · actions/runner-images](https://github.com/actions/runner-images/issues/6002)

The description in Step 2 does not seem very clear, e.g., in " internal node is a parent of that internal node", it is not clear which nodes are referred...

good first issue

I was trying to convert a LightGBMRegressor model that has categorical features and I got the following error: `Exception has occurred: ValueError could not convert string to float: '0||1||2||3||4||10||13||14||21||22||23||25||27||29||30' File...

[sklearn.neighbors._nca.NeighborhoodComponentsAnalysis](https://scikit-learn.org/stable/modules/generated/sklearn.neighbors.NeighborhoodComponentsAnalysis.html) is an algorithm that uses a technique similar to k nearest neighbors to find a space in which neighborhoods of points sharing the same labels are tighter than points...

Hi,I used the convert to translate a mutli-ouput sklearn pipeline,Struction as: ![image](https://user-images.githubusercontent.com/21252416/139239405-41cfa12b-4b62-4b58-8196-564b843e8c5f.png) `scaler` and `selector` maybe is None Exception result: ``` hummingbird.ml.exceptions.MissingConverter: Unable to find converter for model type ....

Hello, I am trying to convert my model into a pytorch model. My model is generated by XGBoost in python and is saved in the Json format, as follows: ....

version problem

Trying to run hummingbird for NGBRegressor and receiving ` MissingConverter: Unable to find converter for model type . It usually means the pipeline being converted contains a transformer or a...

enhancement
help wanted

This is regarding the implementation of tf-idf issue (#164 ) @mattetti We can discuss the same in this issue.