Avi

What is the closest model that uses a lower resolution which can be run on my GPU?

I just tried running [my own model](https://github.com/avi12/lego-ai.js/tree/bb41aa57d238798dc80cbc8861676645cd0e3d19/public/web_model_lego) that's based on CocoSSD, and I got: 

The model was originally designed to work on Google Colab; I simply used `tensorflowjs_converter` to attempt to run it on a PWA

Is there a chance that I used `tensorflowjs_converter` incorrectly to convert the model?

The converter file: https://colab.research.google.com/drive/1L0_iDuJT21jjdlFZibabAC2VTaLn9Xtg?usp=sharing

What would be the correct way to preprocess the image and then, after the `model.executeAsync()`, extract `(x, y)` coordinates?

As a reference image, look into `lego-ai.js/public/sample.jpg`

FYI, [this](https://colab.research.google.com/drive/1VohLve2DtpbLajBAKhUAs9bTkH5qJUBd?usp=sharing) is the Python code that interacts with the model

@vladmandic After inspecting the non-strided model's code, I came up with [this code](https://github.com/avi12/lego-ai.js/blob/b6b9e48923de83ccd293544e19a8e7ba9469c591/src/App.svelte#L46-L57): ```ts const buffer = tf.browser.fromPixels(elImage); const [width, height] = buffer.shape; const resize = tf.image.resizeBilinear(buffer, [width, height]); const...

@danwexler > I'm confused by your tensorImage object This is based on [vladmandic/mb3-centernet](https://github.com/vladmandic/mb3-centernet/blob/6b743ba93a7a7612d6f468b60b6476204e5e0ff5/mb3-centernet.js#L63), as I have no experience with TensorFlow.js