zihaomu

Hi @TrueWodzu, can you try to reproduce this issue with OpenCV 4.x branch?

Hi @ukoehler, in 4.8.0, we use the Winograd optimize for 3x3 stride 1 convolution, which speeds up the inference speed but costs more memory (maybe about 3 times). If you...

> Hmm, if that was merged Jan 8th, why do I still see such a high memory usage? hi @ukoehler plese check the detail, it is not fixed completely. And...

> you could disable it with net.enableWinograd(false); Right. but after disabling that, it still costs about twice the memory than 4.5.2, since we repack every convolution weight blob. We try...

> `net.enableWinograd(false)` makes it faster ??? That depends on your machine platform. For some models, the main time-consuming bottleneck is in memory rather than in computation, winograd will indeed lead...

Hi @asmorkalov, I will work on it.

Hi @ukoehler, how can I reproduce your issue? What I'm doing now is run the following code for an hour, and see if the memory is increasing or not. Test...

> Looks like memory is not cleaned after running forward() Hi @ukoehler, in opencv dnn, we will allocate memory for every layer by layer on the first run (for convolution...

> but is accumulating when running different nets one after the other. That's correct. We have found this issue, and try to fix it in the 5.x, which needs refactoring...

## Finish the 1 hour `net.forword()` running and without memory increansing. Hi @ukoehler, @asmorkalov. After running Forward of these models about 10000 times on CPU, I got the following image....