代码拉取完成,页面将自动刷新
同步操作将从 lockout/ncappzoo 强制同步,此操作会覆盖自 Fork 仓库以来所做的任何修改,且无法恢复!!!
确定后同步将在后台操作,完成时将刷新页面,请耐心等待。
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 Neural Compute Stick. Typically examples are provided that show how the NCSDK can be used compile the network to a graph file and also how to create a program that uses that graph file for inferencing. The sections below are categorized by network type and include a brief explaination of each network.
Image Classification Network | Description |
---|---|
AgeNet | 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). |
GenderNet | Network that classifies a face image as male or female. |
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-18 | Deep Residual network 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). |
Object Detection Network | Description |
---|---|
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. |
此处可能存在不合适展示的内容,页面不予展示。您可通过相关编辑功能自查并修改。
如您确认内容无涉及 不当用语 / 纯广告导流 / 暴力 / 低俗色情 / 侵权 / 盗版 / 虚假 / 无价值内容或违法国家有关法律法规的内容,可点击提交进行申诉,我们将尽快为您处理。