How to do transfer learning on this Face-Recognition model?

Autonomous Machines Jetson & Embedded Systems Jetson TX2
1

Hi AastaNV,

Could you give me some recommendation about the following questions:

1.How to do transfer learning on this Face-Recognition model?

2.What’s the neural network model of the merge.caffemodel? (FaceNet or others ?)

3.Could you release the detection.prototxt and classification.prototxt ?

BRs,

Albert

2

Hi,

1. You can use face-recognition model as pre-trained.
We train detectNet for face detection and googleNet for verification.

2. Combination of detectNet and googleNet

3. You can find more information in the following topics:
[url]https://devtalk.nvidia.com/default/topic/1023699/jetson-tx2/questions-about-face-recongnition/post/5209485/#5209485[/url]
[url]https://devtalk.nvidia.com/default/topic/1007313/jetson-tx2/how-to-build-the-objection-detection-framework-ssd-with-tensorrt-on-tx2-/post/5208082/#5208082[/url]

Thanks.