Merge branch 'dev_cpp' of https://github.com/fateshelled/YOLOX-ROS into dev_cpp

Author: fateshelled

README.md

@@ -71,7 +71,7 @@ If you have NVIDIA Graphics, you can run YOLOX-ROS on GPU.
 - CUDA toolkit (11.0)
 - torch+cuda
 
-### Step3 : Demo
+### Step : Demo
 
 Connect your web camera.
 

yolox_ros_cpp/yolox_cpp/src/yolox_openvino.cpp

@@ -48,7 +48,7 @@ namespace yolox_cpp{
         output_name_ = network_.getOutputsInfo().begin()->first;
 
         // output_info->setPrecision(Precision::FP16);
-        output_info->setPrecision(Precision::FP16);
+        output_info->setPrecision(Precision::FP32);
 
         //  Step 4. Loading a model to the device
         std::cout << "Loading a model to the device: " << device_name_ << std::endl;