Mike Shi

Can you be more specific with the error you hit? I just tested on 0.13 and everything seems to be fine (but the demo is broken since it seems like...

Hi! You can check out [tfjs-node](https://github.com/tensorflow/tfjs-node) to use tfjs packages in Node. Otherwise you can check out models that can run on Python DL frameworks on [ModelDepot](https://modeldepot.io/mikeshi/yolov2).

@Nedomas awesome! It'd probably take a bit of work to merge the two things so that this package can support both node and browser. tbh never made a package before...

@jonaslund I believe you can check out his fork available here: https://github.com/Nedomas/tfjs-yolo-tiny I would love to see a PR to this repo adding node support. I decided to hold off...

What's happening there is that the data has to be transferred from GPU to CPU. I couldn't figure out a way to do something like boolean mask on GPU only....

@jacobgil wow that's really clever! 😍 I scratched my head quite a bit at how to not use gross data transferring and couldn't figure out how exactly to use `where`...

@jacobgil another note: you can also use tf.linspace and tf.zeros for `all_indices ` and `neg_indices` instead of creating a tensor via a JS array. It seems weird though that eliminating...

So doing a bit more digging, I surround `model.predict` using `performance.now()` but I'm pretty confident that 10ms per prediction is a fluke (either that or my MBP is has the...

@TheHidden1 do you have a set of tfjs weights that can be pointed to? :) Or do you need help converting the Keras model to tfjs format? Also, I don't...

I'm not sure how y'all are looking at timing, but my suspicion and I forgot if I already said this somewhere above is that because tensor.data() waits for the GPU...