The Inference Engine MYRIAD plugin is developed for inference of neural networks on Intel® Movidius™ Neural Compute Stick and Intel® Neural Compute Stick 2.
For installation instructions, refer to the Installation Guide for Linux*.
For installation instructions, refer to the Installation Guide for Windows*.
The Inference Engine MYRIAD plugin supports the following networks:
Caffe*:
TensorFlow*:
MXNet*:
** Network is tested on Intel® Movidius™ Neural Compute Stick with BatchNormalization fusion optimization disabled during Model Optimizer import
*** Network is tested on Intel® Neural Compute Stick 2 with BatchNormalization fusion optimization disabled during Model Optimizer import
See VPU common configuration parameters for the VPU Plugins.
In addition to common parameters, the MYRIAD plugin accepts the following options:
| Parameter Name | Parameter Values | Default | Description |
|---|---|---|---|
KEY_VPU_PLATFORM |
VPU_2450/VPU_2480 |
If set, the plugin will use a device with spicific platform to allocate a network. | |
KEY_VPU_FORCE_RESET |
YES/NO |
YES |
Reset stalled devices on plugin initialization, must be used with SetConfig method |
Each IExecutableNetwork instance tries to allocate new device on InferenceEngine::InferencePlugin::LoadNetwork, but if all devices are in use already it will use the one with the minimal number of uploaded networks. The maximum number of networks single device can handle depends on device memory capacity and size of the networks.
By default the plugin resets all stalled devices on initialization for exclusive usage. This behavior can be changed by setting KEY_VPU_FORCE_RESET option to NO. This option must be passed on InferenceEngine::InferencePlugin::SetConfig before the first network is loaded into plugin. Several applications may run simultaneously using different devices, but each application must set KEY_VPU_FORCE_RESET option to NO. Single device cannot be shared across multiple processes.