Practical-RIFE
Practical-RIFE copied to clipboard
hzwer
We are developing more practical approach for users based on RIFE.
Hi, Great work! Do you have any plan to upload the training for 4.22?
It's free and can be used with mpc-be for real times frame interpolation. Maybe you can add vapoursynth, vs-mlrt and avisynth_filter to README? https://github.com/vapoursynth/vapoursynth https://github.com/AmusementClub/vs-mlrt https://github.com/CrendKing/avisynth_filter avisynth_filter script ``` import...
一、转换代码如下： onnx_path = 'flownet.onnx' dummy_input = torch.randn(1, 6, 256, 448).to(device) torch.onnx.export(self.flownet, dummy_input, onnx_path, export_params=True, opset_version=16, do_constant_folding=True, input_names = ['input'], output_names = ['output'], ) print(f'Model has been exported to {onnx_path}') onnx_model...
你好，v4_18_0703里面有一个loss_smooth = self.sobel(flow[3], flow[3]*0).mean()，为什么是这样写呢，这样flow的真值是设为0？
Since I couldn't find anything about it, could you maybe add a small overview to what each model is meant to do / optimized for? atm. it's really unclear whether...
I'm currently using a AMD Ryzen 5 7600 with a 4080super, if i want to SVP rife ai interpolate using 4.18v2 faster with more detail by transcoding rather than plying...
When starting interpolation, it asks to enter the name of the model, which was not initially specified. When trying various options, it says "syntax error" or "model not defined". How...
np.float
Traceback (most recent call last): File "/host/home/yanai-lab/Sotsuken24/xiong-p/test/Practical-RIFE/inference_video.py", line 115, in lastframe = next(videogen) ^^^^^^^^^^^^^^ File "/home/yanai-lab/xiong-p/miniconda3/envs/RIFE/lib/python3.11/site-packages/skvideo/io/io.py", line 251, in vreader reader = FFmpegReader(fname, inputdict=inputdict, outputdict=outputdict, verbosity=verbosity) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/yanai-lab/xiong-p/miniconda3/envs/RIFE/lib/python3.11/site-packages/skvideo/io/ffmpeg.py", line...
Occurs in versions starting from 4.18, on older versions everything works fine 
I'm trying to encance the video using script "python3 inference_video_enhance.py --video=input.mp4", as described in the example, and I get the error: "NameError: name 'Model' is not defined". I downloaded the...
