FrozenGene opened a new issue #5823: URL: https://github.com/apache/incubator-tvm/issues/5823
TensorFlow Lite now supports converting weights to 16-bit floating point values during model conversion from TensorFlow to TensorFlow Lite's flat buffer format. This results in a 2x reduction in model size. However, this will insert new `dequantize` for ops (like `conv2d`) used for `dequantize` fp16 weight to fp32. TVM doesn't support this behavior. List the things we mainly should to do: - Support float16 type inside tflite parser - Extend `dequantize` to support fp16 to fp32 ---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: [email protected]
