Skip to content

Latest commit

 

History

History
23 lines (20 loc) · 3.41 KB

README.md

File metadata and controls

23 lines (20 loc) · 3.41 KB
Raw

Caffe Networks for the Intel® NCS 2 (or original NCS) with OpenVINO™ toolkit

This directory contains multiple subdirectories. Each subdirectory contains software, data, and instructions that pertain to using a specific Caffe neural network with a Neural Compute device such as the Intel® NCS 2. Along with the trained network itself, examples are provided via Makefile that show how the OpenVINO Model Optimizer can be used to compile the network to Intermediate Representation (IR) and also how to create a program that uses that IR model for inferencing. The sections below are categorized by network type and include a brief explaination of each network.

Caffe Image Classification Networks for Neural Compute devices

Image Classification Network Description
AgeGenderNet Network that classifies a face image into age ranges.
AlexNet Network that classifies images based on the 1000 categories described in Large Scale Visual Recognition Challenge 2012 (ILSVRC2012).
GoogLeNet BAIR/BLVC GoogleNet is a network based on GoogleNet, the winner of ILSVRC 2014, that classifies images based on the 1000 categories described in Large Scale Visual Recognition Challenge 2012 (ILSVRC2012).
ResNet-50 Deep Residual network with 50 layers that classifies images based on the 1000 categories described in Large Scale Visual Recognition Challenge 2012 (ILSVRC2012).
SqueezeNet Accuracy similar to AlexNet with many fewer parameters and small model size as described int the SqueezeNet paper. Network that classifies images based on the 1000 categories described in Large Scale Visual Recognition Challenge 2012 (ILSVRC2012).

Caffe Object Detection Networks for Neural Compute devices

Object Detection Network Description
face-detection-retail-0004 This is a nework that is trained to find faces in general. More information specific to this network is available.
SSD_Mobilenet MobileNet Single Shot Detector takes an image, detects the 20 PASCAL object classes as specified in the (Visual Object Classes Challenges), their bounding boxes, and classifications.
TinyYolo This Tiny You Only Look Once model is based on tiny-yolo DarkNet model . Given an image, detects the 20 PASCAL object classes as specified in the (Visual Object Classes Challenges), their bounding boxes, and classifications. Requires some post processing of results to narrow down relevant boxes.

Caffe Misc Networks for Neural Compute devices

Network Description
TBD TBD