Daniel Ecer

What `fps` do you get? Or what timings? (it should show timings of individual parts every second) I find that actually calculating individual part masks can take up a significant...

It wouldn't be difficult to add a predict on batch function. Internally (except for TF Lite I believe), it is using a batch already. I think were it becomes a...

Would you be happy to see whether you want to submit a PR to add batch support?

Hi @Shamino0 I think this is a duplicate of #50 (perhaps not clear from the issue title) I don't think it is very hard. It should just be working with...

Okay, fair point. I believe the corresponding JavaScript code is in [body-pix/src/multi_person/decode_multiple_masks_cpu.ts](https://github.com/tensorflow/tfjs-models/blob/c08dae1739f8cc42502c1770ce4f314052ece2e8/body-pix/src/multi_person/decode_multiple_masks_cpu.ts) (in particular `decodePersonInstancePartMasks`)

On further inspection it seems that in order to do it the same way as it is done in the upstream JS version, it would require the multi person pose...

Thank you for the PR. Have you seen and increased number having a negative effect? Do you have example media files you tested it with? (with permissible license) How did...

In case it helps. I have selected a videos from [pexels](https://www.pexels.com) and uploaded them to Dropbox to make it easier to download on-demand (It's not CC0 but the license seems...

I added support for the MediaPipe's Selfie Segmentation in my `layered-vision` project. It does indeed seem to be noticeably faster. It will probably be even faster when using the calculation...

> I had no segmentation faults (using tensorflow-cpu), but I see blocky artifacts above the head, with rather large blocks. I need to test it more, but it may be...