Propel vs MNN: What are the differences?

Developers describe Propel as "Machine learning for JavaScript". Propel provides a GPU-backed numpy-like infrastructure for scientific computing in JavaScript. On the other hand, MNN is detailed as "A lightweight deep neural network inference engine (by Alibaba)". It is a lightweight deep neural network inference engine. It loads models and do inference on devices. At present, it has been integrated in more than 20 apps of Alibaba-inc, such as Taobao, Tmall, Youku and etc., covering live broadcast, short video capture, search recommendation, product searching by image, interactive marketing, equity distribution, security risk control and other scenarios. In addition, it is also used on embedded devices, such as IoT.

Propel and MNN can be categorized as "Machine Learning" tools.

Some of the features offered by Propel are:

• Run anywhere, in the browser or natively from Node
• Target multiple GPUs and make TCP connections
• PhD optional

On the other hand, MNN provides the following key features:

• Optimized for devices, no dependencies, can be easily deployed to mobile devices and a variety of embedded devices
• Supports Tensorflow, Caffe, ONNX, and supports common neural networks such as CNN, RNN, GAN
• High performance

Propel and MNN are both open source tools. MNN with 3.77K GitHub stars and 784 forks on GitHub appears to be more popular than Propel with 2.79K GitHub stars and 80 GitHub forks.