Sermiazhko Mihail

It's fix this error from yaml import Loader with open(fname, 'r') as f: data = yaml.load(f, Loader=Loader)

https://github.com/TimoBolkart/BFM_to_FLAME it ishelp get this file

I rebuild cuda and get new error: ``` File "/PIXIE/pixielib/utils/tensor_cropper.py", line 78, in crop_tensor cropped_image = warp_affine( TypeError: warp_affine() got an unexpected keyword argument 'flags' ``` Code in project: `...

Thanks. But now i get error: ` File "/home/owner/PythonProjects/3dBodyFromImage/4/PIXIE/pixielib/utils/renderer.py", line 84, in forward pixel_vals = (bary_coords[..., None] * pixel_face_vals).sum(dim=-2) RuntimeError: CUDA out of memory. Tried to allocate 144.00 MiB (GPU...

I use one image and it is work, thanks!

Do you have an example of how your model works in c++? How can I use your model with onnx?

The original model from the example works well. I download model from https://k2-fsa.github.io/sherpa/onnx/pretrained_models/offline-transducer/nemo-transducer-models.html#sherpa-onnx-nemo-transducer-giga-am-russian-2024-10-24-russian And on line: `OnlineRecognizer recongizer = OnlineRecognizer::Create(config);` get error: `/home/user/CppProjects/SpeechToText/sherpa-onnx/sherpa-onnx/csrc/online-transducer-nemo-model.cc:InitEncoder:322 'window_size' does not exist in the metadata`...

Thanks, it's work. Do you know if I need to manually call destroy some objects? Or will the memory be cleared correctly with this code? ```cpp// https://github.com/salute-developers/GigaAM/issues/12 - onnx model...