InsightFace REST API for easy deployment of face recognition services with TensorRT in Docker.
Since a lot of updates happened since last release version is updated straight to v0.7.0.0
Comparing to previous release (v0.6.2.0) this release brings improved performance for SCRFD based detectors.
Here is performance comparison on GPU Nvidia RTX 2080 Super
for scrfd_10g_gnkps
detector paired with
glintr100
recognition model (all tests are using src/api_trt/test_images/Stallone.jpg
, 1 face per image):
Num workers | Client threads | FPS v0.6.2.0 | FPS v0.7.0.0 | Speed-up |
---|---|---|---|---|
1 | 1 | 56 | 103 | 83.9% |
1 | 30 | 72 | 128 | 77.7% |
6 | 30 | 145 | 179 | 23.4% |
Additions:
Model Zoo:
w600k_r50
and w600k_mbf
scrfd
based models now supports batch dimension.Improvements:
lumia.jpg
example with
scrfd_10g_gnkps
and threshold = 0.3 (432 faces detected)).face_align.norm_crop
implementation with help of Numba and removal of unused computations.
(Cropping 432 faces from lumia.jpg
example tooks 45 ms. vs 205 ms.).Fixes:
REST-API
httpx
lib for retrieving images by urls instead of urllib3 (which caused
performance drop in multi-GPU environment under load due to excessive usage of opened sockets)This release also includes previously missed release version 0.6.1.0:
REST-API
REST-API
scrfd_500m_bnkps
, scrfd_2.5g_bnkps
, scrfd_10g_bnkps
scrfd_500m_gnkps
, scrfd_2.5g_gnkps
, scrfd_10g_gnkps
glintr100
glintr100
and scrfd_10g_gnkps
REST-API
genderage
model.limit_faces
parameter
in extract
endpoint./multipart/draw_detections
endpoint, supporting image upload using multipart
form data.draw_detections
endpoints.extract
endpoint for debug and logging purposes.Old version based on TF MTCNN