Download a free trial of the SoftNeuro Deep Learning SDK for Intel and Arm targets (Sponsored)

Morpho, a global research & development company established in Japan in 2004 and specialized in imaging technology, is now offering a free trial for the SoftNeuro deep learning SDK working on Intel processors with AVX2 SIMD extensions, 64-bit Arm targets, while also leveraging OpenCL and/or CUDA.

Some of the advantages of SoftNeuro are that the framework is easy to use even for those without any knowledge about deep learning, it’s fast thanks to the separation of the layers and their execution patterns, and it can run on several different hardware and OS being cross-platform.

SoftNeuro DNN model conversion

SoftNeuro relies on its own storage format (DNN format) to deliver the above advantages. But you can still use models trained with any mainstream deep learning framework. TensorFlow and Keras models can be directly converted to the DNN format, while models from other frameworks can be converted first to the ONNX format and then to the DNN format. SoftNeuro can also optimize your models for each platform (CPU speed-up instructions, GPU, DSP, etc.) without sacrificing accuracy. Encrypting the trained networks minimizes the risk of leaking machine learning know-how and the learned model parameters.

Jetson Xavier Tensorflow Lite vs SoftNeuro
Tensorflow Lite vs SoftNeuro on Jetson Xavier

Performance-wise, an internal evaluation at Morpho last 2021 showed SoftNeuro to significantly outperform Tensorflow Lite on NVIDIA Jetson Xavier hardware with VGG16, Resnet50, mobilenetV2, and mobilenetv3 models. SoftNeuro works on both 64-bit Linux and 64-bit Windows on Intel and Arm (Linux only) processors and the company provides C API, Python API and a CLI tool for development with details to get started available on SoftNeuro SDK documentation.

NeuroSoft Supported Platforms
Supported Platforms

You can see the solution in action in the video below with object detection, foreground segmentation, and classification, and an inexhaustive list of other use cases that include crowd counting, pose estimation, semantic segmentation, as well as voice and language processing.

For a deep dive into the internals, a research paper entitled “SoftNeuro: Fast Deep Inference using Multi-platform Optimization” explains the theory behind it, and how it all works under the hood.

If you’d like to try it out, you can download a free trial of the SoftNeuro SDK for evaluation and non-commercial use only until December 31st, 2021, and you could even win a 1000 Yen Amazon (Japan) gift card after completing a “user survey”.

Share this:

Support CNX Software! Donate via PayPal or cryptocurrencies, become a Patron on Patreon, or buy review samples

Subscribe
Notify of
guest
The comment form collects your name, email and content to allow us keep track of the comments placed on the website. Please read and accept our website Terms and Privacy Policy to post a comment.
0 Comments
Advertisement