GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → JDAI-CV → Centerx

JDAI-CV / Centerx

Licence: apache-2.0
This repo is implemented based on detectron2 and centernet

Programming Languages

python
139335 projects - #7 most used programming language

Labels

deep-learningobject-detectioncaffeonnx

Projects that are alternatives of or similar to Centerx

Yolov3
YOLOv3 in PyTorch > ONNX > CoreML > TFLite
Stars: ✭ 8,159 (+1924.57%)
Mutual labels:  object-detection, onnx
Caffe2 Ios
Caffe2 on iOS Real-time Demo. Test with Your Own Model and Photos.
Stars: ✭ 221 (-45.16%)
Mutual labels:  object-detection, caffe
Jacinto Ai Devkit
Training & Quantization of embedded friendly Deep Learning / Machine Learning / Computer Vision models
Stars: ✭ 49 (-87.84%)
Mutual labels:  object-detection, caffe
Multi Object Tracker
Multi-object trackers in Python
Stars: ✭ 451 (+11.91%)
Mutual labels:  object-detection, caffe
ppq
PPL Quantization Tool (PPQ) is a powerful offline neural network quantization tool.
Stars: ✭ 281 (-30.27%)
Mutual labels:  caffe, onnx
Jetson Inference
Hello AI World guide to deploying deep-learning inference networks and deep vision primitives with TensorRT and NVIDIA Jetson.
Stars: ✭ 5,191 (+1188.09%)
Mutual labels:  object-detection, 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 (+472.21%)
Mutual labels:  object-detection, caffe
Ncnn
ncnn is a high-performance neural network inference framework optimized for the mobile platform
Stars: ✭ 13,376 (+3219.11%)
Mutual labels:  caffe, onnx
yolov5 onnx2caffe
yolov5 onnx caffe
Stars: ✭ 73 (-81.89%)
Mutual labels:  caffe, onnx
onnx2caffe
pytorch to caffe by onnx
Stars: ✭ 341 (-15.38%)
Mutual labels:  caffe, onnx
Yolo2 Pytorch
PyTorch implementation of the YOLO (You Only Look Once) v2
Stars: ✭ 426 (+5.71%)
Mutual labels:  object-detection, onnx
X2paddle
Deep learning model converter for PaddlePaddle. (『飞桨』深度学习模型转换工具)
Stars: ✭ 315 (-21.84%)
Mutual labels:  caffe, onnx
Netron
Visualizer for neural network, deep learning, and machine learning models
Stars: ✭ 17,193 (+4166.25%)
Mutual labels:  caffe, onnx
Adversarial Frcnn
A-Fast-RCNN (CVPR 2017)
Stars: ✭ 461 (+14.39%)
Mutual labels:  object-detection, caffe
Php Opencv
php wrapper for opencv
Stars: ✭ 194 (-51.86%)
Mutual labels:  caffe, onnx
Yolov5
YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite
Stars: ✭ 19,914 (+4841.44%)
Mutual labels:  object-detection, onnx
Onnx Chainer
Add-on package for ONNX format support in Chainer
Stars: ✭ 83 (-79.4%)
Mutual labels:  caffe, onnx
Keras Oneclassanomalydetection
[5 FPS - 150 FPS] Learning Deep Features for One-Class Classification (AnomalyDetection). Corresponds RaspberryPi3. Convert to Tensorflow, ONNX, Caffe, PyTorch. Implementation by Python + OpenVINO/Tensorflow Lite.
Stars: ✭ 102 (-74.69%)
Mutual labels:  caffe, onnx
arcface retinaface mxnet2onnx
arcface and retinaface model convert mxnet to onnx.
Stars: ✭ 53 (-86.85%)
Mutual labels:  caffe, onnx
Onnx2caffe
pytorch to caffe by onnx
Stars: ✭ 282 (-30.02%)
Mutual labels:  caffe, onnx
View All Similar Projects ➔

This repo is implemented based on detectron2 and CenterNet

What's new

  • Support imgaug data augmentation
  • Support swa
  • Support Knowledge Distill, teacher-student, designed by myself
  • Support other LR_SCHEDULER
  • Support Optimizer RangerLars, not convergence in COCO
  • We provide some examples and scripts to convert centerX to Caffe, ONNX and TensorRT format in projects/speedup

What's comming

  • [️✔] Support simple inference
  • [✔] Support to caffe, onnx, tensorRT
  • [ ] Support keypoints

Requirements

  • Python >= 3.7
  • PyTorch >= 1.5
  • torchvision that matches the PyTorch installation.
  • OpenCV
  • pycocotools
pip install cython; pip install 'git+https://github.com/cocodataset/cocoapi.git#subdirectory=PythonAPI'
  • GCC >= 4.9
gcc --version
  • detectron2
pip install -U 'git+https://github.com/CPFLAME/detectron2.git'

pip install git+https://github.com/pabloppp/pytorch-tools -U

Data prepare

the same as detectron2

Training

modify your yamls in run.sh

sh run.sh

Testing and Evaluation

modify your yamls in run.sh, add eval-only and MODEL.WEIGHTS in your setting

sh run.sh

Performance

coco

This repo use less training time to get a competitive performance compared to other versions

Backbone ResNet-50

Code mAP epoch
centerX 33.2 70
centerX 34.3 140
centernet-better 34.9 140

Backbone ResNet-18

centerX_KD means ResNet-50(33.2) as teacher, ResNet-18(27.9) as student, Knowledge Distill for 70 epoch in coco.

Code mAP epoch
centerX 30.2 140
centerX 27.9 70
centerX_KD 31.0 70
centernet-better 29.8 140
centernet 28.1 140

crowd human

  • optim: SGD
  • lr: 0.02
  • scheduler: WarmupMultiStepLR ,drop 0.1 in (50, 62) for 80 epoch; (90 ,120) for 140 epoch
  • train size: 512 max size
  • test size: 512 max size
  • batch size: 64
  • woGT: KD only use teacher loss
Backbone mAP mAP50 mAP75 epoch teacher student_pretrain
resdcn18 31.2 56.6 30.8 80 - -
resdcn18_swa 31.1 56.6 30.4 80 - -
resdcn18_syncBN 31.3 56.6 30.7 80 - -
resdcn18_imgaug 29.6 54.7 28.9 80 - -
resdcn18_KD 34.5 60.2 34.3 80 resdcn50 resdcn18
resdcn18_KD_woGT 33.0 58.3 32.7 80 resdcn50 resdcn18
resdcn18_KD_woGT_scratch 32.8 58.1 32.6 140 resdcn50 imagenet
resdcn50 35.1 61.2 35.3 80 - -

KD exp

crowd human KD

Generalization performance for Knowledge Distill

Backbone crowd mAP coco_person mAP epoch teacher student_pretrain train_set
resdcn50 35.1 35.7 80 - - crowd
resdcn18(baseline) 31.2 31.2 80 - - crowd
resdcn18_KD 34.5 34.9 80 resdcn50 resdcn18 crowd
resdcn18_KD_woGT_scratch 32.8 34.2 140 resdcn50 imagenet crowd
resdcn18_KD_woGT_scratch 34.1 36.3 140 resdcn50 imagenet crowd+coco

multi teacher KD

Backbone mAP crowd mAP coco_car epoch teacher student_pretrain train_set
1.resdcn50 35.1 - 80 - - crowd
2.resdcn18 31.7 - 70 - - crowd
3.resdcn50 - 31.6 70 - - coco_car
4.resdcn18 - 27.8 70 - - coco_car
resdcn18_KD_woGT_scratch 31.6 29.4 140 1,3 imagenet crowd+coco_car
Backbone mAP crowd_human mAP widerface epoch teacher student_pretrain train_set
1.resdcn50 35.1 - 80 - - crowd
2.resdcn18 31.7 - 70 - - crowd
3.resdcn50 - 32.9 70 - - widerface
4.resdcn18 - 29.6 70 - - widerface
5.resdcn18_ignore_nolabel 29.1 24.2 140 - - crowd+wider
6.resdcn18_pseudo_label 28.9 27.7 140 - - crowd+wider
7.resdcn18_KD_woGT_scratch 31.3 32.1 140 1,3 imagenet crowd+wider

License

centerX is released under the Apache 2.0 license.

Acknowledgement

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].