项目链接:https://github.com/RangiLyu/nanodet
作者:RangiLyu
Model | Resolution | COCO mAP | Latency(ARM 4xCore) | FLOPS | Params | Model Size(ncnn bin) |
---|---|---|---|---|---|---|
NanoDet-m | 320*320 | 20.6 | 10.23ms | 0.72B | 0.95M | 1.8mb |
NanoDet-m | 416*416 | 21.7 | 16.44ms | 1.2B | 0.95M | 1.8mb |
YoloV3-Tiny | 416*416 | 16.6 | 37.6ms | 5.62B | 8.86M | 33.7mb |
YoloV4-Tiny | 416*416 | 21.7 | 32.81ms | 6.96B | 6.06M | 23.0mb |
Note:
Performance is measured on Kirin 980(4xA76+4xA55) ARM CPU based on ncnn.
NanoDet mAP(0.5:0.95) is validated on COCO val2017 dataset with no testing time augmentation.
YOLO mAP refers from Scaled-YOLOv4: Scaling Cross Stage Partial Network
NanoDet is a FCOS-style one-stage anchor-free object detection model which using ATSS for target sampling and using Generalized Focal Loss for classification and box regression. Please refer to these papers for more detail.
Fcos: Fully convolutional one-stage object detection
ATSS:Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection
Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection
知乎中文介绍
Android demo project is in demo_android_ncnn folder. Please refer to Android demo guide.
C++ demo based on ncnn is in demo_ncnn folder. Please refer to Cpp demo guide.
First, install requirements and setup NanoDet following installation guide. Then download COCO pretrain weight from here.
python demo/demo.py image --config CONFIG_PATH --model MODEL_PATH --path IMAGE_PATH
python demo/demo.py video --config CONFIG_PATH --model MODEL_PATH --path VIDEO_PATH
python demo/demo.py webcam --config CONFIG_PATH --model MODEL_PATH --camid YOUR_CAMERA_ID
conda create -n nanodet python=3.8 -y
conda activate nanodet
conda install pytorch torchvision cudatoolkit=11.0 -c pytorch
pip install Cython termcolor numpy tensorboard pycocotools matplotlib pyaml opencv-python tqdm
git clone https://github.com/RangiLyu/nanodet.git
cd nanodet
python setup.py develop
Prepare dataset
Convert your dataset annotations to MS COCO format(COCO annotation format details).
If your dataset annotations are pascal voc xml format, using this repo to convert data. voc2coco
Prepare config file
Copy and modify an example yml config file in config/ folder.
Change save_path to where you want to save model.
Change num_classes in model->arch->head.
Change image path and annotation path in both data->train data->val.
Set gpu, workers and batch size in device to fit your device.
Set total_epochs, lr and lr_schedule according to your dataset and batchsize.
If you want to modify network, data augmentation or other things, please refer to Config File Detail
Start training
For single GPU, run
python tools/train.py CONFIG_PATH
For multi-GPU, NanoDet using distributed training. (Notice: Windows not support distributed training before pytorch1.7) Please run
python -m torch.distributed.launch --nproc_per_node GPU_NUM --master_port 29501 tools/train.py CONFIG_PATH
NanoDet provide C++ and Android demo based on ncnn library.
Convert model
To convert NanoDet pytorch model to ncnn, you can choose this way: pytorch->onnx->ncnn
To export onnx model, run tools/export.py. Then using onnx-simplifier to simplify onnx structure.
Run onnx2ncnn in ncnn tools to generate ncnn .param and .bin file
Run NanoDet model with C++
Please refer to demo_ncnn.
Run NanoDet on Android
Please refer to android_demo.
https://github.com/Tencent/ncnn
https://github.com/open-mmlab/mmdetection
https://github.com/implus/GFocal
https://github.com/cmdbug/YOLOv5_NCNN
https://github.com/rbgirshick/yacs