CrabNet
hummingbird


CrabNet | hummingbird | |
---|---|---|
1 | 9 | |
96 | 3,385 | |
- | 0.4% | |
3.7 | 6.0 | |
almost 2 years ago | 26 days ago | |
Python | Python | |
MIT License | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
CrabNet
-
Artificial intelligence can revolutionise science
I don't know. As for "literature-based discovery," this project/paper sounded like a pretty big deal when it came out a few years ago: https://github.com/materialsintelligence/mat2vec . And I see this thing came out more recently: https://github.com/anthony-wang/CrabNet .
Of course not all fields lend themselves as well to this as does materials science.
hummingbird
- Treebomination: Convert a scikit-learn decision tree into a Keras model
-
[D] GPU-enabled scikit-learn
If are interested in just predictions you can try Hummingbird. It is part of the PyTorch ecosystem. We get already trained scikit-learn models and translate them into PyTorch models. From them you can run your model on any hardware support by PyTorch, export it into TVM, ONNX, etc. Performance on hardware acceleration is quite good (orders of magnitude better than scikit-learn is some cases)
-
Machine Learning with PyTorch and Scikit-Learn – The *New* Python ML Book
I think Rapids AI's cuML tried to go into this direction (essentially scikit-learn on the GPU): https://docs.rapids.ai/api/cuml/stable/api.html#logistic-reg.... For some reason it never took really off though.
Btw., going on a tangent, you might like Hummingbird (https://github.com/microsoft/hummingbird). It allows you trained scikit-learn tree-based models to PyTorch. I watched the SciPy talk last year, and it's a super smart & elegant idea.
-
Export and run models with ONNX
ONNX opens an avenue for direct inference using a number of languages and platforms. For example, a model could be run directly on Android to limit data sent to a third party service. ONNX is an exciting development with a lot of promise. Microsoft has also released Hummingbird which enables exporting traditional models (sklearn, decision trees, logistical regression..) to ONNX.
-
Supreme Court, in a 6–2 ruling in Google v. Oracle, concludes that Google’s use of Java API was a fair use of that material
And Python.
-
[D] Here are 3 ways to Speed Up Scikit-Learn - Any suggestions?
For inference, you can convert your models to other formats that support GPU acceleration. See Hummingbird https://github.com/microsoft/hummingbird
-
[D] Microsoft library, Hummingbird, compiles trained ML models into tensor computation for faster inference.
The surprising thing is that Hummingbird can be faster than the GPU implementation of LightGBM (and XGBoost) if you use tensor compilers such as TVM. [The paper](https://www.usenix.org/conference/osdi20/presentation/nakandala) describes our findings. We have also open sourced the [benchmark code](https://github.com/microsoft/hummingbird/tree/main/benchmarks) so you try yourself!
-
I learned about Microsoft's Hummingbird library today. 1000x performance??
I took their sample code from Github and tweaked it to spit out times for each model's prediction, as well as increase the number of rows to 5 million. I used Google's Colab and selected GPU for my hardware accelerator. This gives an option to run code on GPU, not that all computations will happen on the GPU.
What are some alternatives?
query-selector - LONG-TERM SERIES FORECASTING WITH QUERYSELECTOR – EFFICIENT MODEL OF SPARSEATTENTION
cuml - cuML - RAPIDS Machine Learning Library
ProteinStructurePrediction - Protein structure prediction is the task of predicting the 3-dimensional structure (shape) of a protein given its amino acid sequence and any available supporting information. In this section, we will Install and inspect sidechainnet, a dataset with tools for predicting and inspecting protein structures, complete two simplified implementations of Attention based Networks for predicting protein angles from amino acid sequences, and visualize our predictions along the way.
docker - Docker - the open-source application container engine
mat2vec - Supplementary Materials for Tshitoyan et al. "Unsupervised word embeddings capture latent knowledge from materials science literature", Nature (2019).
swift - The Swift Programming Language
ViTGAN - A PyTorch implementation of ViTGAN based on paper ViTGAN: Training GANs with Vision Transformers.
coremltools - Core ML tools contain supporting tools for Core ML model conversion, editing, and validation.
GAT - Graph Attention Networks (https://arxiv.org/abs/1710.10903)
onnx - Open standard for machine learning interoperability
Invariant-Attention - An implementation of Invariant Point Attention from Alphafold 2
ServiceTalk - A networking framework that evolves with your application

