MultiboxPeopleDetection

[DomLi]

Hi, I am emgu official user, and currently try to train own model used for MultiboxPeopleDetection but really confused how to train my own model used in as MultiboxPeopleDetection. Thanks

[emgucv]

First a disclaimer: I have not trained my own Single Shot Detector (The algorithm behind Multibox People Detection) with Tensorflow, but here is some information that I will read through if I need to train one: https://github.com/balancap/SSD-Tensorflow https://github.com/georgesung/ssd_tensorflow_traffic_sign_detection https://github.com/seann999/ssd_tensorflow

Or you can use the original Caffee implementation to train an SSD: https://github.com/weiliu89/caffe/tree/ssd and use the following tools to convert the Caffee model to Tensorflow: https://github.com/ethereon/caffe-tensorflow

[DomLi]

thx,lot Mate, I reckon the model to be used in emgu_tf may not be compatible to that trained in other different ways. will have look anyway, thanks again for kind reply, it is headache job, but I like emgu tf though

On 5 October 2017 at 03:47, Emgu CV [email protected] wrote:

First a disclaimer: I have not trained my own Single Shot Detector (The algorithm behind Multibox People Detection) with Tensorflow, but here is some information that I will read through if I need to train one: https://github.com/balancap/SSD-Tensorflow https://github.com/georgesung/ssd_tensorflow_traffic_sign_detection https://github.com/seann999/ssd_tensorflow

Or you can use the original Caffee implementation to train an SSD: https://github.com/weiliu89/caffe/tree/ssd and use the following tools to convert the Caffee model to Tensorflow: https://github.com/ethereon/caffe-tensorflow

— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub https://github.com/emgucv/emgutf/issues/5#issuecomment-334343968, or mute the thread https://github.com/notifications/unsubscribe-auth/AG5oBv0FAmMWJfVVSrnHm2vu64dlWCYxks5spEMzgaJpZM4Pt-Bk .

[DomLi]

How to train emgu_tf ssd

On 5 October 2017 at 03:47, Emgu CV [email protected] wrote:

First a disclaimer: I have not trained my own Single Shot Detector (The algorithm behind Multibox People Detection) with Tensorflow, but here is some information that I will read through if I need to train one: https://github.com/balancap/SSD-Tensorflow https://github.com/georgesung/ssd_tensorflow_traffic_sign_detection https://github.com/seann999/ssd_tensorflow

Or you can use the original Caffee implementation to train an SSD: https://github.com/weiliu89/caffe/tree/ssd and use the following tools to convert the Caffee model to Tensorflow: https://github.com/ethereon/caffe-tensorflow

— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub https://github.com/emgucv/emgutf/issues/5#issuecomment-334343968, or mute the thread https://github.com/notifications/unsubscribe-auth/AG5oBv0FAmMWJfVVSrnHm2vu64dlWCYxks5spEMzgaJpZM4Pt-Bk .