turicreate
CNTK
turicreate | CNTK | |
---|---|---|
2 | 1 | |
11,134 | 17,435 | |
- | 0.0% | |
0.0 | 0.0 | |
6 months ago | about 1 year ago | |
C++ | C++ | |
BSD 3-clause "New" or "Revised" License | GNU General Public License v3.0 or later |
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.
turicreate
-
Mac Studio for Deep Learning
It depends. What kind of ML will you be working with? Apple's neural engine doesn't have an SDK, but they do have https://github.com/apple/turicreate which talks to CoreML. I've been thinking of getting an Mac Studio Ultra and have been researching whether this would be a good investment considering the advances in hardware lately, as well as Apple's release schedule. Been following Tenstorrent for news about their PCIe Gen 4 cards, too. In any case my wallet is going to be hurting soon. Also, have you checked this out? https://machinelearning.apple.com/research/neural-engine-transformers
-
I've got a basic prediction model using Random Forest, I'd like to convert it to Core ML model, any idea how I could do this?
What framework/library did you use to create your ML model? There is a very simplified way to create a Random Forest model using Turi create.
CNTK
What are some alternatives?
Pytorch - Tensors and Dynamic neural networks in Python with strong GPU acceleration
Theano - Theano was a Python library that allows you to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. It is being continued as PyTensor: www.github.com/pymc-devs/pytensor
tensorflow - An Open Source Machine Learning Framework for Everyone
DALI - A GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep learning training and inference applications.
Caffe - Caffe: a fast open framework for deep learning.
Keras - Deep Learning for humans
scikit-learn - scikit-learn: machine learning in Python
tiny-cnn - header only, dependency-free deep learning framework in C++14
gensim - Topic Modelling for Humans
ANNetGPGPU - A GPU (CUDA) based Artificial Neural Network library