ML Community Day 2021 Recap — The TensorFlow Blog
TensorFlow 2.7 is here! This release offers performance and usability improvements, including TFLite use of XNNPack for mobile inference performance boosts, training improvements on GPUs, and a dramatic improvement in debugging efficiency in Keras and TF.
We recently launched on-device training in TensorFlow Lite. When deploying TensorFlow Lite machine learning model to a mobile app, you may want to enable the model to be improved or personalized based on input from the device or end user.
https://youtu.be/Ka_qRt8_Glw?t=513
mobile nativeとwebでtraining pipeline reuse
qunantized modelもbrowserで動く★？？？
pruning/sparsity support via XNNPACK XNNPack向けのpolicyを設定して学習する
Quantization Debugger
fpとquantizeのMSEをレイヤごとに見て、どこで精度が落ちているかを見て、そこを量子化しないなど
Target Aware Authoring
モデル開発の早い段階で、それがtfliteで動くかをチェックする
model analyzer
gpu compatibility