TensorRT implementation of the official DDRNet

DDRNet-23-slim outperform other light weight segmentation method,see

• 1. get model.wts

  Convert pytorch model to wts model using getwts.py, or download the wts [model](url: https://pan.baidu.com/s/1Cm1A2mq6RxCFhUJrOJBSrw ;passworld: p6hy ) convert from official implementation.

  note that we do not use extral segmentation head while inference(set augment=False in https://github.com/ydhongHIT/DDRNet/blob/76a875084afdc7dedd20e2c2bdc0a93f8f481e81/segmentation/DDRNet_23_slim.py#L345).

• 2. cmake and make

     config ur cmakelist and

  mkdir build
  cd build
  cmake ..
  make -j8
  ./ddrnet -s             // serialize model to plan file i.e. 'DDRNet.engine'
  ./ddrnet -d  ../images // deserialize plan file and run inference, the images in samples will be processed.
  

for INT8 support:

#define USE_INT8  // comment out this if want to use INT8
//#define USE_FP16  // comment out this if want to use FP32

mkdir "calib" and put around 1k images(cityscape val/test images) into folder "calib".

Test on RTX2070

Pytorch-aug means augment=True.

we use Upsample with "nearest" other than "bilinear",which may lead to lower accuracy .

Finetune with "nearest" upsample may recover the accuracy.

Here we convert from the official model directly.

1. refer to:https://github.com/chenjun2hao/DDRNet.pytorch
2. generate wts model with getwts.py

https://github.com/midasklr/DDRNet.Pytorch wirte your own dataset and finetune the model with cityscape.