-
Thanks for the work, this is a good step forward.
To make easier integration of new interpretation framework,
Can you detail in docs :
API to include new Interpretation models.
…
-
It looks like we already renamed the `/mlmodels` endpoint to `/models`. I think it would be a good idea to rename any instance of an `mlmodel` parameter to `model` for consistency and simplicity, for …
-
This is great work.
What about the design
to integrate new models ?
-
I'd like to rename `mlmodels` to just `models` in the endpoint url. I don't think `ml` adds anything, and is kinda arbitrary and hard to remember. None of the other queries have qualifiers before thei…
-
## 🐞Describe the bug
When the model uses softmax_nd, the axis is inferred incorrectly when the target is 11.2 and 12, but correctly in 13.
## To Reproduce
Unfortunately, I couldn't provide reproduc…
-
This issue tracks work to support Conda in R projects.
From separate discussion thread...
```
It would be great to support Conda environments for R projects too for users who include a conda.ya…
-
I have trained a regression model and I have uploaded it to a container in Blob Storage. This is the method that I use to upload the model to blob storage:
`public async Task TrainAndUploadModelAsy…
-
Hi Guys,
I've converted my ActivityClassifier trained with TuriCreate to updatable CoreML model. But now I have a compilation error in Xcode.
`coremlc: Error: compiler error: Encountered an error…
mecid updated
4 years ago
-
My original .pb model has an input with a shape of [12], but it's converted to [1,1,1] in my .mlmodel.
The original shape is supposed to be a sequence of 12 doubles to distribute weights on a style …
-
@dongbohu The [model query](https://py3-adage.greenelab.com/api/v1/mlmodels/) returns some useful metadata about the models, but it is all condensed into a single description field, `desc_html`.
I'…