The face-recognition-resnet100-arcface-onnx
model is a deep face recognition model with ResNet100 backbone and ArcFace loss. ArcFace is a novel supervisor signal called additive angular margin which used as an additive term in the softmax loss to enhance the discriminative power of softmax loss.
This model is pre-trained in MXNet* framework and converted to ONNX* format. More details provided in the paper and repository.
Metric | Value |
---|---|
Type | Face recognition |
GFLOPs | 24.2115 |
MParams | 65.1320 |
Source framework | MXNet* |
Metric | Value |
---|---|
LFW accuracy | 99.68% |
Image, name: data
, shape: 1, 3, 112, 112
, format: B, C, H, W
, where:
B
- batch sizeC
- channelH
- heightW
- width
Channel order is RGB
.
Image, name: data
, shape: 1, 3, 112, 112
, format: B, C, H, W
, where:
B
- batch sizeC
- channelH
- heightW
- width
Channel order is BGR
.
Face embeddings, name: fc1
, shape: 1, 512
, output data format: B, C
, where:
B
- batch sizeC
- row-vector of 512 floating points values, face embeddings
The net outputs on different images are comparable in cosine distance.
Face embeddings, name: fc1
, shape: 1, 512
, output data format: B, C
, where:
B
- batch sizeC
- row-vector of 512 floating points values, face embeddings
The net outputs on different images are comparable in cosine distance.
You can download models and if necessary convert them into Inference Engine format using the Model Downloader and other automation tools as shown in the examples below.
An example of using the Model Downloader:
omz_downloader --name <model_name>
An example of using the Model Converter:
omz_converter --name <model_name>
The original model is distributed under the
Apache License, Version 2.0.
A copy of the license is provided in <omz_dir>/models/public/licenses/APACHE-2.0.txt
.