BmanClark

TransposeConv wrong shape?

15

The TFlite code doesn't like the shape of the Transpose Convolution node I have in my TinyNN converted network. It seems consistent across Transpose Convolutions that it expects the bias...

unnecessary float() variables cause quantization to fail.

7

I'm quantizing the [MI-GAN](https://github.com/Picsart-AI-Research/MI-GAN/) network that I have previously converted to tflite successfully with your help (thank-you!) I'm basing my conversion off your https://github.com/alibaba/TinyNeuralNetwork/blob/main/examples/quantization/post.py script, and I've managed to work...

3d Car Parking scenes invalid/corrupt

7

On Windows, Godot 4.1.2, both training and testing scene come up "invalid or corrupt" and don't load for the 3D Car Parking example.