Input width and height

[Nuzhny007]

Some questions.

1. In yolo.cpp you set condition: assert(m_InputW == m_InputH);
   Why? AlexeyAB write: set network size width=416 height=416 or any value multiple of 32
   And darknet trains and works with input size 960x768

2. And second question about this assert:

if (weights.size() != weightPtr)
     {
         std::cout << "Number of unused weights left : " << weights.size() - weightPtr << std::endl;
         assert(0);
     }

In my yolov4-tiny with size 608x608 this condition goes to assert but in release it works. And in my case weights.size() < weightPtr

[enazoe]

1.yeah , current version does not support daynamic input dimension.
2.the yolov4-tiny is not yet supported, but I am working on it and support soon. Because the yolov4-tiny route layer is different from yolov4. you could check this link. We need add a plugin layer at tensorrt like pytorch chunk to implementation the tiny route layer.

[Nuzhny007]

Thnx!