Evgeniy Mamchenko

@beyondmetis, thanks for the quick answer. I tried once more with the following code with `verbosity=1` added: ``` writer = FFmpegWriter(vid_path, outputdict={ '-vcodec': codec_name, '-s': '{0}x{1}'.format(frame_width, frame_height), '-r': str(frame_rate), '-loglevel':...

For clarity I tested the issue with the latest version of the package as well: ``` pip list | grep video scikit-video 1.1.11 ``` the result is still ``` writer.writeFrame(frame)...

@sayakpaul >Could you try downgrading the tf2onnx version to 1.11.1? I tried this, unfortunately there is still an error that `PartitionedCall` is not supported. I also tried to downgrade tensorflow...

>Thanks for investigating. With your workaround, does the model work during inference as expected? Yes, I rerun the cells that were comparing outputs of a TF model and an ONNX...

In fact, `PartitionedCall` may not be the root cause of the problem. I looked at the ONNX file produced with TF 2.11.0 [in the notebook above](https://github.com/deep-diver/segformer-tf-transformers/blob/main/notebooks/TFSegFormer_ONNX.ipynb) by doing ``` onnx_model...