-
The following ops are currently not implemented for XPU backend and affect performance on select models: efficientnet, fbnet, yolov4,, ifrnet and rife:
- [ ] `aten::_prelu_kernel` (ifrnet, rife)
-…
-
**Information:**
- Chainner version: Alpha v0.18.7
- OS: Windows 10
**Description**
As title's description. Models are from [here](https://github.com/ltkong218/IFRNet#download-pre-trained-mo…
-
Is it possible to add other interpolation methods? I would assume IFRNet would be the easiest to implement because there is a Vulkan ported version. Is it possible to add some other interpolation from…
-
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:/…
-
## Bug Description
TensorRT throws error about fp32 tensors input despite I am using fp16 tensors as input.
I attached the file `IFRNet.py` adapted from [https://github.com/ltkong218/IFRNet/b…
-
I tested 8x interpolation using IFRNet_GoPro.pth and found that although the generated frames have good coherence, the generated frames are blurrier than the original frames. Why is this?
jhl13 updated
4 months ago
-
grid_sample is currently not implemented for XPU backend, see
https://github.com/intel/torch-xpu-ops/blob/8cc6d5102878cefd3c71245fc7509a4548d07da2/src/aten/XPUFallback.template#L249
The problem is…
-
**I found gpu memory leak when program runs into following lines. (It might be a bug in higher version of pytorch)**
https://github.com/ltkong218/IFRNet/blob/main/models/IFRNet_S.py#L44
https://gi…
-
Results are much better than RIFE.
Thank you very much in advance
-
Where can I find the RIFE-large pretrained model? I can only see RIFE and RIFE-m models in the github repository.