-
Hi @AlexeyAB @WongKinYiu Great work with Yolov7 btw
I trying to run the following code with yolo-pose
```
import torch
import cv2
from torchvision import transforms
import numpy as np
import tq…
-
- [ *] I have checked the known issues and searched Github to ensure this issue has not already been reported.
- [ *] This is not a feature request, I know those belong on Discord/Github Discussions.…
-
Hello, I have some queations about training settings.
1. In the inference code, there is a line that says:
conditional_latents_mask = mask_token.repeat(bsz_cfg, num_frames-2, 1, latent_h, latent…
-
I know this isn't everyone's cup of tea but I'm looking for a streamlined way to do frame interpolation with my videos using Avisynth scripts. I was wondering if it's technically possible to select an…
-
Testing results:
No problems. Game runs above 30FPS, support for up to 4 player (multiplayer or split screen has not been tested).
](https://user-images.githubusercontent.com/96869436/188928422-7d2bb1da-a4b8-4b37-9d84-56ac84691df9.png)
…
-
### Video processing should be performed on the GPU
The same video processing algorithm performed in the TA in #2 should also be applied to the GPU, so that we can assess the performance gains. Imple…
-
### We want to process video in the tee so that we can attest it.
- Transfer video data from the optee client to the ta
- We can use some sort of library to read video frames into a nice struct
-…
-
IFRNet: https://github.com/ltkong218/ifrnet
Even has an ncnn version: https://github.com/nihui/ifrnet-ncnn-vulkan
It seems to score much higher than even XVFI according to the papers at: https:/…