Ilya Zhenin

I've been thinking about the same, so I wont create new issue. I've been reading a lot of issues over this repository and DPT, as Im planning on training DPT,...

I have related impression from C++ tensorrt code, it tracks okay moving objects but if objects are standing still even with high confidence around 0.9, it wont track them.

Similar issue with C++ code.

Same problem

Same on RTX 2080 Ti. It eats so much memory

My last experiment with config for all Torchscript models with parameter: ``` parameters: { key: "ENABLE_CACHE_CLEANING" value: { string_value:"true" } } ``` shown no memory growth. Seems like clearing cache...

I will need share models for that, but I cannot. But as I mentioned issue is gone if cache clearing is enabled for pytorch.