Vladimir Mandic
Vladimir Mandic
when using `webgl` backend, `tensor.dataSync()` is about 35% faster than `await tensor.data()` when returning larger amounts of data (in my case, model takes 720x720x3 image as input and produces 720x720x3...
method `fromPixels` uses optimized code paths depending on the browser and using `webgl` calls results in 10x faster performance than fallback using `canvas.getImageData` however, method `toPixels` does not have any...
attempting to run nanodet object detection model converted from pytorch - conversion notes and example of model usage are at: ```log engine.ts:540 Uncaught (in promise) Error: Kernel 'SparseToDense' not registered...
TFHub "Updated" field for any model is always set to a current date This makes it impossible to see which models are recently added or updated I addition, I suggest...
This PR updates `MMdnn` for `TensorFlow` **v2** compatibility by utilizing legacy support in TF2 Main reason is that TF1 requires Python 3.7 or lower and new systems come with Python...
Now that TFJS 2.0 has been released, are there any plans to update face-api models to be compatible with it? Currently it fails due to batchNormalization being obsoleted in tfjs...
currently `handdetector.js` module downloads all results and processes per-class scores in js before going back to tfjs which causes large dataset transfers from tfjs backend (either gpu (when used with...
i just stumbled on your model and so far **i really like it** i do have few questions: ## what is the relationship of two different models? - model from...
In This should be: `'eyeRight', 'eyeLeft', 'nose', 'mouthRight', 'mouthLeft'`
In case anybody is interested, NanoDet works like a charm in TensorFlow and TensorFlow/JS Converted models, full JS code as well as conversion notes are at: I've re-implemented score &...