User Portlet
Featured Contributor
| Discussions |
|---|
| This is very nice and well put together! Thanks for sharing it with the community |
| Hi Ethan, to answer your questions 1. We are working on a stable diffusion model for the [net repository][1]. 2. Compression tools for models are nice but right now the core priority is to provide support for multiple framework in order to get... |
| Giulio, Thank you. Your solution works well. Have a nice weekend. |
| What you are looking for seems to be ``` AggregationLayer[Max] ``` which will take `[channels, height, width]` and return `[channels]` using `Max` to aggregate the other dimensions. |
| Thank you very much for your help! |
| ![enter image description here][2] -- you have earned ***Featured Contributor Badge*** ![enter image description here][1] Your exceptional post has been selected for our editorial column ***Staff Picks*** http://wolfr.am/StaffPicks and [Your... |
| At the moment the clustering metrics are all internal and used to optimize hyper-parameters. We have a plan to expose them and if there is some interest all the better. For the time being, and keeping in mind that is code might change in the... |
| There was a bug found in the pre-processing BERT when the front-end language is not English (for instance when it is Chinese). We will update BERT to fix it. (and people who already downloaded the model will have to re-download it after having... |
| Thank you Giulio! This was really helpful. Regards, |
| I believe this is due to some overzealous standardization step in the automated processing pipeline (boolean vectors are converted to numerical vectors for processing). You can disable that using the "Minimal" feature extraction: data = {True,... |