Tflite2onnx

Update links. No functional changes.

2021-08-31, [Project](https://github.com/jackwish/tflite2onnx/projects/5)

* More operators, and API `getSupportedOperators()` to list the supported operators.
* Relax data type check, most for FP16 and INT8.
* FP16 quantization: fold FP16 tensors to unblock MediaPipe models. See 35 for details.
* API `enableDebugLog()` to dump log for debugging purpose.

Thanks for the contribution of erizmr briangrifiin and IkbeomJeon!

* New API `getSupportedOperators()` to know what operators have been supported. No longer need to maintain a list manually.
* FP16 quantization: fold FP16 tensors to unblock MediaPipe models. See https://github.com/jackwish/tflite2onnx/issues/35 for details.

2020-12-28, [Project](https://github.com/jackwish/tflite2onnx/projects/5)

* More operators, check [the support list](https://github.com/jackwish/tflite2onnx/blob/master/docs/operator-support-status.md).
* Relax data type check, most for FP16 and INT8.
* Interface `enableDebugLog()` to dump log for debugging purpose.

Thanks for the contribution of erizmr briangrifiin and IkbeomJeon!

* Now open source with [annocement blog](https://jackwish.net/2020/Convert-TensorFlow-Lite-models-to-ONNX.html).
* [Quantization support](https://github.com/jackwish/tflite2onnx/issues/10) enabled, and tried quantized MobileNetV1 an MobileNetV2.
* Drop [Transpose based layout handling](https://github.com/jackwish/tflite2onnx/issues/2) to save the effort of managing quantization.
* More [operators](https://github.com/jackwish/tflite2onnx/blob/master/docs/operator-support-status.md) added, and [tested models](https://github.com/jackwish/tflite2onnx/tree/more-model-test/assets/networks):
* MobileNetV1
* MobileNetV2
* DenseNet
* EfficientNet
* MnasNet
* SqueezeNet
* NasNet

* Operator support of MobileNetV2.
* Infrastructure improvements.
* [Propagation based layout handling](https://github.com/jackwish/tflite2onnx/issues/2).