haobo724

./ExtendedKF is the Executable files (output file of project), Follow the Readme.md and you will run through it without any problems

https://github.com/aladdinpersson/Machine-Learning-Collection/tree/master/ML/Pytorch/image_segmentation/semantic_segmentation_unet

> > I also get the same error "KeyError: 'params'".I just want to convert RealESRGAN_x4plus.pth to onnx. > > I used Chainner and it works great! Just import the model...

I met same issue! I used default pytorch2onnx.py script in repos. Then I got the onnx model but the inference speed is decreased (from 0.13s-0.21s).

> Hello, As google most likely has notified you when your pr failed due to unsigned CLA, please sign that as otherwise your pr will not be able to be...

> Hi, we fix the bug there #1829 @Jay-Humor hi, firstly thanks for this powerful framework. My question is that the FileNotFoundError is still there, right? not be fixed in...

有什么进展吗

just change the line 8 in file **degradations.py** from `from torchvision.transforms.functional_tensor import rgb_to_grayscale` to` from torchvision.transforms.functional import rgb_to_grayscale`

maybe not support torch 2.0.1+cu118? here is the bug log & C:/Users/94836/miniconda3/envs/dl/python.exe c:/Study/PythonApp/wisper-live/main.py Downloading: "https://github.com/snakers4/silero-vad/zipball/master" to C:\Users\94836/.cache\torch\hub\master.zip C:\Users\94836\miniconda3\envs\dl\lib\site-packages\torchaudio\backend\utils.py:74: UserWarning: No audio backend is available. warnings.warn("No audio backend is available.") Traceback...

> Did you install `pip install soundfile` also, is this using the latest version, with the latest onnx fix - [b5f9f1e](https://github.com/collabora/WhisperLive/commit/b5f9f1ed08c27c397fa984f37224bd2ec9af051b) I install package via pip. I saw the version...