Ilya Zhenin
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.
Ubuntu 22.04.4 LTS. ``` curl -v http://127.0.0.1:9090/metrics * Trying 127.0.0.1:9090... * Connected to 127.0.0.1 (127.0.0.1) port 9090 (#0) > GET /metrics HTTP/1.1 > Host: 127.0.0.1:9090 > User-Agent: curl/7.81.0 > Accept:...
Could be related, I have also running mongoose webserver on different port in the same app. When I make curl request mongoose seems to be logging some stuff I dont...
I rebuilded my app without creating web server with mongoose, but still am having same log output from mongoose. This gave me suspicion that something smelly goes on in linking,...