1 Reply by anders.nilsson

(9 replies, posted in Эксплуатация SVP)

Кто-нибудь может подтвердить, работает ли SVP в H96 MAX V58 android tv box? И что они работают с plex, kodi, emby и могут запускать dts-HD, TrueHD atmos и все другие цифровые аудиодорожки.

Go to forum: Эксплуатация SVP

2 Reply by anders.nilsson

(24 replies, posted in Using SVP)

Is there a android media box that svp works on? I tried on Nvida shield TV pro but it dosent, how els to get it to work on TV with plex, kodi, emby or some other media streamer smile Thanks!

Go to forum: Using SVP

3 Reply by anders.nilsson

(3 replies, posted in Using SVP)

https://drive.google.com/drive/folders/ … sp=sharing

Desktop 2024.03.09 - 11.25.59.05.mp4   Check the red carpet in right down corner. I tried to take the mouse pointer there, but it goes so fast.

Desktop 2024.03.09 - 11.24.04.04   - Check the windows white - I have the mouse pointer there.

Does anybody want the original "clips" if i cut them out with mkv tool nix, to tri with svp if u get same resaults, no RIFE.

Go to forum: Using SVP

4 Reply by anders.nilsson

(3 replies, posted in Using SVP)

No same things as before, no settings change what i now, not by me. If it change, by automatic then.

Go to forum: Using SVP

5 Topic by anders.nilsson

(3 replies, posted in Using SVP)

I changed the graphics card from gtx 1070 to rtx 4060 and experience much more artifacts especially when it is fence shaped materials, elements, railings, is there any setting in svp I could change to counteract this? or in Nvida control panels 3d settings for the software players?

Go to forum: Using SVP

6 Reply by anders.nilsson

(2,340 replies, posted in Using SVP)

Is there some comparing of RIFE and Standard svp engine? Cant find. Thanks

Go to forum: Using SVP

7 Reply by anders.nilsson

(9 replies, posted in Using SVP)

I turn G-Sync off and V-Sync on in nvida controll panel, and used 2x movie in svp and "Duplicate frames removal" "Do not remove, then i get 90% gpu usage and the picture in video flows fine smile

Go to forum: Using SVP

8 Reply by anders.nilsson

(9 replies, posted in Using SVP)

Thats crap, newer card should be faster, thanks for support, If i get new motherboard in the future that hade Pci E 4.0 insted of 3, if will be a boost to,

Go to forum: Using SVP

9 Reply by anders.nilsson

(9 replies, posted in Using SVP)

MAG79 wrote:

1080p x2 works good wirh RTX 3060 Ti. So, I think it must work with RTX 4060 Ti too.
Try Movie x2 option instead of To screen option.

Same, just lags and hacks

https://ibb.co/RYk4QbF
https://ibb.co/tBY93fS

Do i need to register account on nvida and download TensorRT  dev kit?
Or have svp it in with rife? Should just work right on with svp if have rife selected and installed from svp?

Go to forum: Using SVP

10 Topic by anders.nilsson

(9 replies, posted in Using SVP)

Should work on 1080p to get 60 fps, does not for me yikes? some settings? Tried like all in svt rife filter.
Do i need to register account on nvida and download TensorRT  dev kit?
I have only pci e gen 3, 16x, can it be that??

Go to forum: Using SVP

11 Topic by anders.nilsson

(2 replies, posted in Using SVP)

[W] [TRT] onnx2trt_utils.cpp:377: Your ONNX model has been generated with INT64 weights, while TensorRT does not natively support INT64. Attempting to cast down to INT32.

[W] Could not read timing cache from: C:\Users\......\AppData\Roaming\SVP4\cache\Program Files (x86)/SVP 4/rife\models\rife\rife_v4.4.onnx.min64x64_opt2560x1440_max2560x1440_fp16_trt-8502_cudnn_I-fp16_O-fp16_NVIDIA-GeForce-GTX-1070_a8b3b7a9.engine.cache.


[TRT] CUDA lazy loading is not enabled. Enabling it can significantly reduce device memory usage. See `CUDA_MODULE_LOADING` in https://docs.nvidia.com/cuda/cuda-c-pro … l#env-vars



Is something wrong with  NVIDIA TensorRT?
What to do?
I have read the:
Module loading

CUDA_MODULE_LOADING

DEFAULT, LAZY, EAGER

Specifies the module loading mode for the application. When set to EAGER, all kernels from a cubin, fatbin or a PTX file are fully loaded upon corresponding cuModuleLoad* API call. This is the same behavior as in all preceding CUDA releases. When set to LAZY, loading of a specific kernel is delayed to the point a CUfunc handle is extracted with cuModuleGetFunction API call. This mode allows for lowering initial module loading latency and decreasing initial module-related device memory consumption, at the cost of higher latency of cuModuleGetFunction API call. Default behavior is EAGER. Default behavior may change in future CUDA releases.

But i dont understand!

Go to forum: Using SVP