fixed some issues (wang-xinyu#400)

* 1 动态输入
2 图像预处理和后处理和pytorch同步
3 代码格式统一

* 重新梳理代码

* tab 替换为4 space

* HRNet-Semantic-Segmentation

* update result img

* update readme

* Synchronize

* Modify some bugs

Author: BaofengZan

dbnet/common.hpp

@@ -110,8 +110,8 @@ ILayer* convBnLeaky(INetworkDefinition *network, std::map<std::string, Weights>&
     conv1->setPaddingNd(DimsHW{ p, p });
     conv1->setNbGroups(g);
     //IScaleLayer* bn1 = addBatchNorm2d(network, weightMap, *conv1->getOutput(0), lname + ".bn", 1e-4);
-    IScaleLayer* bn1 = addBatchNorm2d(network, weightMap, *conv1->getOutput(0), lname.substr(0, lname.find_last_of(".")) + bnname, 1e-3);
-    auto lr = network->addActivation(*bn1->getOutput(0), ActivationType::kLEAKY_RELU);
+    IScaleLayer* bn1 = addBatchNorm2d(network, weightMap, *conv1->getOutput(0), lname.substr(0, lname.find_last_of(".")) + bnname, 1e-5);
+    auto lr = network->addActivation(*bn1->getOutput(0), ActivationType::kRELU);
     lr->setAlpha(0.1);
     return lr;
 }

hrnet/hrnet-semantic-segmentation/README.md

@@ -1,13 +1,13 @@
 # HRNet-Semantic-Segmentation
 
-The Pytorch implementation is [HRNet-Semantic-Segmentation](https://github.com/HRNet/HRNet-Semantic-Segmentation).  The implemented model is **HRNetV2-W18-Small-v2**
+The Pytorch implementation is [HRNet-Semantic-Segmentation-v1.1](https://github.com/HRNet/HRNet-Semantic-Segmentation/tree/pytorch-v1.1).  The implemented model is **HRNetV2-W18-Small-v2**
 
 
 ## How to Run
 
 * 1. generate .wts
 
-  Download code and model from [HRNet-Semantic-Segmentation](https://github.com/HRNet/HRNet-Semantic-Segmentation) and config your environments.
+  Download code and model from [HRNet-Semantic-Segmentation-v1.1](https://github.com/HRNet/HRNet-Semantic-Segmentation/tree/pytorch-v1.1) and config your environments.
 
   Put `demo.py`  in the `YOUR_ROOT_DIR\HRNet-Semantic-Segmentation\tools `  folder, set `savewts in  main()` as `True`, and run, the .wts will be generated.