/Person_Segmentation

The inference implementation of the deeplabV3+ person segementation algorithm.

Primary LanguageC++

1. 文件目录说明

2.实验结果

Backbone Pixel Accuracy Mean_IoU Background IoU Person IoU
Mobilenetv2_1.0 0.971 0.943 0.953 0.933
Mobilenetv2_0.5 0.966 0.933 0.944 0.922
Mobilenetv2_0.35 0.961 0.922 0.935 0.909
Mobilenetv2_0.25 0.955 0.911 0.926 0.896
Backbone Params FLOPS
Mobilenetv2_1.0 5.794M 23.260G
Mobilenetv2_0.5 3.282M 20.597G
Mobilenetv2_0.35 2.697M 19.993G
Mobilenetv2_0.25 2.344M 19.632G
  • 数据分布、及组成待补充
  • 速度对比待补充
Original Result
org1 res1
org2 res2

3.引用

[1] Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
[2] Inverted Residuals and Linear Bottlenecks: Mobile Networks for Classification, Detection and Segmentation
[3] https://github.com/Tencent/ncnn
[4] https://github.com/pytorch/pytorch
[5] https://github.com/NVIDIA/TensorRT
其他引用待补充