Wow, it is really surprising to me that bezier curve control points produced by an optimization process would be good inputs to a neural net model. Small perturbations to the inputs could produce radically different bezier control points depending on the decisions made by the curve optimizer, so this forces the neural network to learn about the characteristics of the optimizer as well as the input.
Neural nets usually thrive on raw high dimensional inputs, so dramatically reducing the dimensionality of the input seems like a strange decision. I'm sure it improves speed, but I would expect higher accuracy by processing the raw input.
this is so awesome!
but how is it that we have RNN solutions for handwriting when we don't even have a standard, canned RNN for OCR?
I know tesseract and related projects exist, but when I've tried them they have been fairly brittle with lower accuracy than I was expecting. Accuracy was especially problematic for letter combinations like "-ing" that would consistently be recognized as "-mg".
Is there a good ML OCR library I'm missing?
Really cool stuff! My phone isn't big enough to do handwriting on, so I'm not really sure where this is supposed to be used? On a tablet I guess?
How can I train an RNN to OCR my scribbles? It would be the perfect mix of physical paper and digital notes.
I miss the time when in Gboard you could use the slide typing to type multiple words at once. This was so useful and made people like me who are unable to type quickly on a virtual keyboard (touch) to type very fast.
Isn't swiping inherently faster? With sweeping you need 1 angle (corner) for letter. Typical letter uses much more than 1 corner.
I just switched from Android to iPhone, and Gboard on iPhone doesn't have the translation function. It also doesn't have multiple languages -- if I want to switch languages I have to exit out of Gboard and use the default iOS keyboard. Anyone know why these features for Gboard are missing on iOS?
I used it on windows phone 5 years back for chinese- wonder if this is new to android?
(on iPhone right now)
Iujnlk77bhbbtlvt pool ok Hmm so. you,
The "Making it Work, On-device" paragraph makes it seem like TensorFlow Lite will easily get your model running fast on-device, but in reality RNNs aren't currently supported by the TFLite Converter and the TFLiteLSTMCell example is super slow for training, so this is actually based on proprietary code not available to mere mortals using open source TensorFlow. If you were to actually try reproducing this work, you'd have to use several workarounds, dig deep into the TensorFlow source code, and possibly still end up with a suboptimal TFLite model.
Don't get me wrong, in terms of deployability and flexibility for production usage, TensorFlow/TFLite is really good, specially compared to other frameworks, but Google tends to oversell the abilities of open-source TensorFlow significantly in their marketing material, and you only find out when you go and try doing it yourself.