Merge branch 'master' into tensorrt8

include/tkDNN/SegmentationNN.h

@@ -185,6 +185,7 @@ class SegmentationNN {
             checkCuda(cudaMemcpyAsync(stddev_d, stddev.data(), stddev.size() * sizeof(float), cudaMemcpyHostToDevice, netRT->stream));
             return true;
 
+            return true;
         }
         
         /**

include/tkDNN/utils.h

@@ -23,6 +23,7 @@
 #include <ios>
 #include <chrono>
 
+#include <yaml-cpp/yaml.h>
 
 
 
@@ -176,5 +177,4 @@ inline T YAMLgetConf(YAML::Node conf, std::string key, T defaultVal) {
     return val;
 }
 
-
 #endif //UTILS_H