What is the Intel® Deep Learning SDK?
The Intel® Deep Learning SDK is a free set of tools for data scientists and software developers to develop, train, and deploy deep learning solutions. The SDK encompasses a training tool and a deployment tool that can be used separately or together in a complete deep learning workflow.
- Easily prepare training data, design models, and train models with automated experiments and advanced visualizations
- Simplify the installation and usage of popular deep learning frameworks optimized for Intel platforms
Data scientists are the primary users.
- Optimize trained deep learning models through model compression and weight quantization, which are tailored to end-point device characteristics
- Deliver a unified API to integrate the inference with application logic
Application developers are the primary users.
- The beta release of the training tool and deployment tool that supports Intel® Distribution for Caffe* is now available. For more information, see the Download Center.
- The training tool for image classification includes many advanced features such as custom networks (topologies) for model creation, integration with interactive notebooks, and the ability to install on OS X* or Amazon Web Services (AWS)*.
The deployment tool supports image classification and image segmentation use cases with inference on floating point 32 bit precision (FP32).
|Required Hardware||Optimized for Intel® Xeon® processor, Intel® Xeon Phi™ processor, and Intel® Core™ i7 processor Extreme Edition|
|Required OS||Ubuntu* 14.04 or higher (64 bit)
CentOS* 7 (64 bit)
Mac OS* 10.11 or higher (64 bit)
|Supported Browser||Google Chrome*|
|Supported Use Cases||Image classification|
|Required Hardware||Optimized for Intel® Xeon® and Intel® Core™ processors|
|Required OS||Development Environment: Ubuntu 14.04, 16.04 (64 bit)
Target Inference Platform: Ubuntu 14.04 (64 bit)
|Supported Use Cases||Image classification and image segmentation|
|Supported Layers||Convolution, deconvolution, fully connected, pooling, rectified linear unit (RelU), softmax, eltwise, crop, local response normalization (LRN), concatenation, power, and split|