This is a WIP implementation of converting a multimodal model (LayoutLMv3) to CoreML. While I was able to adapt the library to convert the model, the resulting model doesn't predict correctly (testing in both Swift on mobile as well as with coremltools in Python). I would appreciate any feedback to make it work.
I had to patch two pytorch ops:
clip: As it's an alias of clamp, I reused the same code from coremltools here.
one_hot: I used some help from Copilot and LLMs to write this and make it work. However, I am not sure if it's the correct implementation. I suspect that the error might lie in this one.
This is a WIP implementation of converting a multimodal model (LayoutLMv3) to CoreML. While I was able to adapt the library to convert the model, the resulting model doesn't predict correctly (testing in both Swift on mobile as well as with
coremltoolsin Python). I would appreciate any feedback to make it work.I had to patch two
pytorchops:clip: As it's an alias ofclamp, I reused the same code fromcoremltoolshere.one_hot: I used some help from Copilot and LLMs to write this and make it work. However, I am not sure if it's the correct implementation. I suspect that the error might lie in this one.