开源软件名称（OpenSource Name）：

开源软件地址(OpenSource Url)：

开源编程语言(OpenSource Language)：

开源软件介绍(OpenSource Introduction)：

mobilenetv3-ssd

• train mobilenetv3-ssd use pytorch(provide *.pth model)
• convert to ncnn model(provide *.param, *.bin)

Backbone

Reference paper: MobileNetv3 https://arxiv.org/pdf/1905.02244.pdf

We mainly train mobilenetv3-ssd detection network rather than classification network, for convenience, we use trained mobiletnetv3-large network from https://github.com/xiaolai-sqlai/mobilenetv3 (We are also trying to use https://github.com/rwightman/gen-efficientnet-pytorch provided mobilenetv3-large classification network)

open-source mobilenetv3-large classification network

For extra-body, we use 1x1 conv + 3x3 dw conv + 1x1 conv block follow mobilenetv2-ssd setting(official tensorflow version), details below:

1x1 256 conv -> 3x3 256 s=2 conv -> 1x1 512 conv

1x1 128 conv -> 3x3 128 s=2 conv -> 1x1 256 conv

1x1 128 conv -> 3x3 128 s=2 conv -> 1x1 256 conv

1x1 64 conv -> 3x3 64 s=2 conv -> 1x1 128 conv

Head

For head, we use 3x3 dw conv + 1x1 conv block follow mobilenetv2-ssd-lite setting(official tensorflow version)

We choose 6 feature maps to predict box coordinates and label, their dimenstions are 19x19, 10x10, 5x5, 3x3, 2x2, 1x1. their anchor numbers are 4, 6, 6, 6, 4, 4.

Training

We train mobilenetv3-ssd use mmdetection framework(based on pytorch), we use PASCAL VOC0712 trainval dataset to train, it reaches 71.7mAP on VOC2007 test dataset.

img test:

Convert mobilenetv3-ssd pytorch model to ncnn framework

1. convert .pth model to onnx(not included priorbox layer, detection_output layer) -> I provide origin pytorch model
2. use onnx-simplifier to simplify onnx model
3. convert simplified .onnx model to ncnn
4. modify .param manually(add priorbox layer, detection_output layer, etc.) -> I provide converted ncnn model

How to use mobilenetv3-ssd in ncnn framework

you can refer to https://github.com/Tencent/ncnn/blob/master/examples/mobilenetv3ssdlite.cpp

model link

mobilenetv3-ssd pytorch model 百度网盘链接: https://pan.baidu.com/s/1sTGrTHxpv4yZJUpTJD8BNw 提取码: sid9 mobilenetv3-ssd ncnn model 百度网盘链接: https://pan.baidu.com/s/1zBqGnp4utJGi6-IzYs7lTg 提取码: phdx google drive link: https://drive.google.com/file/d/11_C_ko-arXnzM60udcXOMM5_PDNXuCcs/view?usp=sharing