Hacker News Reader

Exactly, especially in the age of ridiculously rapid development that we have found ourselves in over the past few years. This is exactly why TensorFlow is dying

View on HN

I do not believe TensorFlow is anywhere close to dying.

:) it still is impossible to bring a cnn rnn network in pytorch to mobile, which works fine with tflite...

I don't think that's a problem for the vast majority of pytorch users

Not sure if you have heard of Pytorch Mobile but it is very possible[0]

[0] https://pytorch.org/tutorials/beginner/deeplabv3_on_ios.html

The big thing that PyTorch Mobile is lacking compared to TF Lite is on-device accelerator support (GPU/DSP/etc.) (there's experimental support for NNAPI https://pytorch.org/tutorials/prototype/nnapi_mobilenetv2.ht..., but this is a hack).

Reply on news.ycombinator.com