facenet-20180408-102900.md

facenet-20180408-102900

Use Case and High-Level Description

FaceNet: A Unified Embedding for Face Recognition and Clustering. For details see the repository, paper

Example

Specification

Metric	Value
Type	Face recognition
GFlops	2.846
MParams	23.469
Source framework	TensorFlow*

Performance

Input

Original model

1. Image, name - batch_join:0 , shape - [1x160x160x3], format [BxHxWxC], where:

   • B - batch size
   • H - image height
   • W - image width
   • C - number of channels

   Expected color order - RGB. Mean values - [127.5, 127.5, 127.5], scale factor for each channel - 128.0

2. A boolean input, manages state of the graph (train/infer), name - phase_train, shape - [1].

Converted model

Image, name - image_batch/placeholder_port_0, shape - [1x3x160x160], format [BxCxHxW], where:

- B - batch size
- C - number of channels
- H - image height
- W - image width

Expected color order - BGR.

Output

Original model

Vector of floating-point values - face embeddings, Name - embeddings.

Converted model

Face embeddings, name - InceptionResnetV1/Bottleneck/BatchNorm/Reshape_1/Normalize, in format [B,C], where:

- B - batch size
- C - row-vector of 512 floating-point values - face embeddings.

Legal Information

https://raw.githubusercontent.com/davidsandberg/facenet/master/LICENSE.md