pull code

* [Ascend] add fc op

* [Ascend] fix fc test

* [Ascend] fix code format

* [Ascend] modify the comment

Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle-Lite into PaddlePaddle-develop

* fix sequence pool grad compute error, test=develop

* fix sequence pool grad run, test=develop

* fix format test=develop

[Core] Fix the missing of the input and output scale after the lite_elementwise_activation_fuse_pass is applied (#4066)

* [ascend] add softmax and dropout op, test=develop

* [Ascend] address review comments, test=develop

* add support for three-dimentional input in reduce max test=develop

* add view suffix to read-only classes for flatbuffers, test=develop

* add some write-apis for flatbuffers, test=develop

* [ascend] add pool and elementwise op, test=develop

* [ascend] add batch_norm op and simpify tensor update, test=develop

test=develop

* change pooling3x3s2max padding right to intrisic. test=develop

* add int32->int64 cast arm cpu kernel. test=develop

* [test] flatbuffers io, test=develop

* determine the basic interfaces and help functions of flatbuffers, test=develop

[RKNPU] Adapting to the changing of the quantization parameters, and supporting the fully quantized mobilenetv1 model (#4046)

* [RKNPU] Adapting to the changing of the quantization parameters, and supporting the fully quantized mobilenetv1 model
test=develop

* [Doc] Update the doc for apu and rknpu
test=develop

* add ParamDesc, test=develop

* serialize tensor funcs, test=develop

pull

pull