fxmarty
fxmarty
Hello, by stroke do you mean the black part surrounding the text in white, like outline? If so, you are interested in this part: https://github.com/fxmarty/rikai-mpv/blob/422fb1085b3e20b4790d0bb554cafe095514789f/subtitles_popup_graphics.py#L456 ```python def paintEvent(self, event): #...
I should look into it sometime again, I remember it was quite hacky
@gante thank you! What do you mean by work with padded tensors?
Oh yes, I think that's what I am suggesting here!
@lsrock1 Thank you for the PR. Regarding the issue https://github.com/huggingface/transformers/issues/29205, is it not possible to trace the model on the same device it is intended to be used? Overall, doing...
Do you mean that tracing on device 1, serializing, and loading on device 2 is impossible as well? For your use case, do you necessarily need to serialize the traced...
@lsrock1 I see. It is indeed not ideal.
Thank you! You could for example run: `RUN_SLOW=1 pytest tests/exporters/onnx -k "test_custom_model" -s -vvvvv`. As the test is decorated with `@slow`, it is not run in the normal CI (as...
@bhavika To solve ``` FAILED exporters/onnx/test_onnx_export.py::OnnxExportTestCase::test_all_models_tested - AssertionError: Not testing all models. Missing models: {'nomic-bert'} ``` can you add a `PYTORCH_REMOTE_CODE_MODELS` here https://github.com/huggingface/optimum/blob/d9bd7c35faa32fafe716a16dc0280cb59253cfc2/tests/exporters/exporters_utils.py#L303 and add it here https://github.com/huggingface/optimum/blob/d9bd7c35faa32fafe716a16dc0280cb59253cfc2/tests/exporters/onnx/test_onnx_export.py#L321-L326? And adapt...