Wolfgang Pauli comments

Results 8 comments of


                                            Wolfgang Pauli

Active learning not working with custom model

Are there any updates on this issue. I'm running into the same problem. compared my model.json with the one contained in this repo, and cannot find any obvious differences. Is...

Active learning not working with custom model

I see, thanks. I had specific constraints that lead me to use VoTT (e.g. Azure blob storage support). Other options that directly support active learning are CoCo Annotator and Prodigy....

dead link in Readme.md

Hi @aseemw , sorry for skipping this important detail. It's on this page: https://github.com/onnx/onnx-coreml/tree/master/examples

unable to download s3dis

I was able to get it from here: https://web.archive.org/web/20200707221857/http://buildingparser.stanford.edu/dataset.html#Download

Great code, have you tried scaling the image data? ([0,255] -> [0,1])

I was also realizing that the model produced rather larger errors. I was able to get them into the correct range (e.g. around .2), by scaling the image data: return...

How can this module be trained?

Hi, I have been "able" to train the model, but the performance did not exceed the baseline comparison (MSE current frame vs previous frame should be higher than MSE current...

[Feature] Local fine-tuning support

Regrading the related note, I believe that this is the answer. Still curious about the local fine-tuning though. ``` import dspy model_name = "hosted_vllm/deepseek-ai/deepseek-llm-7b-chat" vllm_mpt = dspy.LM( model_name, api_base="http://localhost:8000/v1/", provider=LocalProvider(),...