clancylian / Retinaface
Licence: mit
Reimplement RetinaFace use C++ and TensorRT
Stars: ✭ 241
Labels
Projects that are alternatives of or similar to Retinaface
Dsrg
Weakly-Supervised Semantic Segmentation Network with Deep Seeded Region Growing (CVPR 2018).
Stars: ✭ 206 (-14.52%)
Mutual labels: caffe
Ide Baseline Market 1501
ID-discriminative Embedding (IDE) for Person Re-identification
Stars: ✭ 220 (-8.71%)
Mutual labels: caffe
Liteflownet2
A Lightweight Optical Flow CNN - Revisiting Data Fidelity and Regularization, TPAMI 2020
Stars: ✭ 195 (-19.09%)
Mutual labels: caffe
Raspberrypi Facedetection Mtcnn Caffe With Motion
MTCNN with Motion Detection, on Raspberry Pi with Love
Stars: ✭ 204 (-15.35%)
Mutual labels: caffe
Ck Caffe
Collective Knowledge workflow for Caffe to automate installation across diverse platforms and to collaboratively evaluate and optimize Caffe-based workloads across diverse hardware, software and data sets (compilers, libraries, tools, models, inputs):
Stars: ✭ 192 (-20.33%)
Mutual labels: caffe
Netron
Visualizer for neural network, deep learning, and machine learning models
Stars: ✭ 17,193 (+7034.02%)
Mutual labels: caffe
Caffe Yolov3 Windows
A windows caffe implementation of YOLO detection network
Stars: ✭ 210 (-12.86%)
Mutual labels: caffe
Up Down Captioner
Automatic image captioning model based on Caffe, using features from bottom-up attention.
Stars: ✭ 195 (-19.09%)
Mutual labels: caffe
Interactive Deep Colorization
Deep learning software for colorizing black and white images with a few clicks.
Stars: ✭ 2,465 (+922.82%)
Mutual labels: caffe
Pixelnet
The repository contains source code and models to use PixelNet architecture used for various pixel-level tasks. More details can be accessed at <http://www.cs.cmu.edu/~aayushb/pixelNet/>.
Stars: ✭ 194 (-19.5%)
Mutual labels: caffe
Caffe2 Ios
Caffe2 on iOS Real-time Demo. Test with Your Own Model and Photos.
Stars: ✭ 221 (-8.3%)
Mutual labels: caffe
Deepdetect
Deep Learning API and Server in C++14 support for Caffe, Caffe2, PyTorch,TensorRT, Dlib, NCNN, Tensorflow, XGBoost and TSNE
Stars: ✭ 2,306 (+856.85%)
Mutual labels: caffe
Caffe Deepbinarycode
Supervised Semantics-preserving Deep Hashing (TPAMI18)
Stars: ✭ 206 (-14.52%)
Mutual labels: caffe
Colorization
Automatic colorization using deep neural networks. "Colorful Image Colorization." In ECCV, 2016.
Stars: ✭ 2,791 (+1058.09%)
Mutual labels: caffe
Dgd person reid
Domain Guided Dropout for Person Re-identification
Stars: ✭ 229 (-4.98%)
Mutual labels: caffe
Dl inference
通用深度学习推理服务,可在生产环境中快速上线由TensorFlow、PyTorch、Caffe框架训练出的深度学习模型。
Stars: ✭ 209 (-13.28%)
Mutual labels: caffe
RetinaFace C++ Reimplement
source
Reference resources RetinaFace in insightface with python code.
model transformation tool
you need to add some layers yourself, and in caffe there is not upsample,you can replace with deconvolution,and maybe slight accuracy loss.
the origin model reference from mobilenet25,and I have retrain it.
Demo
$ mkdir build
$ cd build/
$ cmake ../
$ make
you need to modify dependency path in CmakeList file.
Speed
test hardware:1080Ti
test1:
model | speed | input size | preprocess time | inference | postprocess time |
---|---|---|---|---|---|
mxnet | 44.8ms | 1280x896 | 19.0ms | 8.0ms | 16.0ms |
caffe | 46.9ms | 1280x896 | 5.8ms | 24.1ms | 16.0ms |
tensorrt | 29.3ms | 1280x896 | 6.9ms | 5.4ms | 15.0ms |
test2:
model | speed | inputsize | preprocess time | inference | postprocess time |
---|---|---|---|---|---|
mxnet | 6.4ms | 320x416 | 1.3ms | 0.1ms | 4.2ms |
caffe | 30.8ms | 320x416 | 1.2ms | 27ms | 2.3ms |
tensorrt | 4.7ms | 320x416 | 0.7ms | 1.9ms | 1.8ms |
tensorrt batch test:
batchsize | inputsize | maxbatchsize | preprocess time | inference | postprocess time | all | GPU |
---|---|---|---|---|---|---|---|
1 | 448x448 | 8 | 1.0ms | 2.3ms | 2.6ms | 6.7ms | 35% |
2 | 448x448 | 8 | 2.5ms | 3.3ms | 5.2ms | 11.8ms | 33% |
4 | 448x448 | 8 | 4.1ms | 4.6ms | 10.0ms | 21.8ms | 28% |
8 | 448x448 | 8 | 8.7ms | 7.0ms | 20.3ms | 40.7ms | 23% |
16 | 448x448 | 32 | 28.1 | 14.7 | 38.7ms | 92.0ms | - |
32 | 448x448 | 32 | 36.2ms | 26.3 | 75.7ms | 163.5ms | - |
note: batch size have some advantage in inference but can't speed up preprocess and postprocess.
optimize post process:
batchsize | inputsize | maxbatchsize | preprocess time | inference | postprocess time | all | GPU |
---|---|---|---|---|---|---|---|
1 | 448x448 | 8 | 1.0ms | 2.3ms | 0.09ms | 3.5ms | 70% |
2 | 448x448 | 8 | 2.2ms | 2.8ms | 0.2ms | 5.3ms | 60% |
4 | 448x448 | 8 | 3.7ms | 5.0ms | 0.3ms | 8.4ms | 55% |
8 | 448x448 | 8 | 7.5ms | 6.5ms | 0.67ms | 14.9ms | 50% |
16 | 448x448 | 32 | 26ms | 13ms | 1.3ms | 41ms | 40% |
32 | 448x448 | 32 | 32ms | 22ms | 2.7ms | 56.6ms | 50% |
use nvidia npp library to speed up preprocess:
batchsize | inputsize | maxbatchsize | preprocess time | inference | postprocess time | all | GPU |
---|---|---|---|---|---|---|---|
1 | 448x448 | 8 | 0.2ms | 2.3ms | 0.1ms | 2.6ms | 91% |
2 | 448x448 | 8 | 0.3ms | 3.0ms | 0.2ms | 3.5ms | 85% |
4 | 448x448 | 8 | 0.5ms | 4.1ms | 0.32ms | 5.0ms | 82% |
8 | 448x448 | 8 | 1.2ms | 6.3ms | 0.77ms | 8.3ms | 79% |
16 | 448x448 | 32 | 2.2ms | 14ms | 1.3ms | 16.7ms | 80% |
32 | 448x448 | 32 | 5.0ms | 22ms | 2.8ms | 29.3ms | 77% |
INT8 inference
INT8 calibration table can generate by INT8-Calibration-Tool.
Accuracy
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].